{"data":{"models":[{"slug":"meta/muse-spark-1.2-contributor","hf_slug":null,"updated_at":"2026-08-21T21:32:16.397Z","created_at":"2026-08-21T18:21:16.610Z","hf_updated_at":null,"name":"Meta: Muse Spark 1.2 Contributor","short_name":"Muse Spark 1.2 Contributor","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark 1.2. Your prompts and outputs may be used to improve Meta’s products, making it ideal for experimentation, learning, and early-stage projects without worry about spend.\n\nIt is a reasoning model from Meta, tailored for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window. The model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":["age_18plus"],"is_private":false,"permaslug":"meta/muse-spark-1.2-contributor-20260805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"91327d91-f7af-4acb-81fe-4eafab2a4012","name":"Meta | meta/muse-spark-1.2-contributor-20260805","context_length":1048576,"model":{"slug":"meta/muse-spark-1.2-contributor","hf_slug":null,"updated_at":"2026-08-21T21:32:16.397595+00:00","created_at":"2026-08-21T18:21:16.61057+00:00","hf_updated_at":null,"name":"Meta: Muse Spark 1.2 Contributor","short_name":"Muse Spark 1.2 Contributor","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark 1.2. Your prompts and outputs may be used to improve Meta’s products, making it ideal for experimentation, learning, and early-stage projects without worry about spend.\n\nIt is a reasoning model from Meta, tailored for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window. The model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":["age_18plus"],"is_private":false,"permaslug":"meta/muse-spark-1.2-contributor-20260805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"meta/muse-spark-1.2-contributor","model_variant_permaslug":"meta/muse-spark-1.2-contributor-20260805","adapter_name":"InternalStreamMetaResponsesAdapter","provider_name":"Meta","provider_info":{"name":"Meta","displayName":"Meta","slug":"meta","baseUrl":"https://api.meta.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://ai.developer.meta.com/legal/terms-of-service","privacyPolicyURL":"https://www.facebook.com/privacy/policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"InternalStreamMetaResponsesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://ai.meta.com/&size=256"},"sendClientIp":false,"pricingStrategy":"meta_responses"},"provider_display_name":"Meta","provider_slug":"meta","provider_model_id":"openrouter_muse-spark-1.2-contributor","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://ai.developer.meta.com/legal/terms-of-service","privacyPolicyURL":"https://www.facebook.com/privacy/policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.000000002","web_search":"0.0025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.0025","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.0025","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.0000001","openai_responses:completion_tokens":"0.0000002","openai_responses:cached_prompt_tokens":"0.000000002"},"pricing_version_id":"3ba3f51f-4e5e-445a-88e7-911ac194600e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":300,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-21T21:32:31.216Z","status":0}},{"slug":"deepseek/deepseek-v4-flash-vision-exp","hf_slug":null,"updated_at":"2026-08-21T11:48:52.711Z","created_at":"2026-08-21T11:26:03.963Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","short_name":"DeepSeek V4 Flash Vision Exp","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.\n\nIt is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-flash-vision-exp-20260821","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"d6cd6c56-b90c-4328-8901-2774024bc62f","name":"DeepSeek | deepseek/deepseek-v4-flash-vision-exp-20260821","context_length":1048576,"model":{"slug":"deepseek/deepseek-v4-flash-vision-exp","hf_slug":null,"updated_at":"2026-08-21T11:48:52.711219+00:00","created_at":"2026-08-21T11:26:03.963897+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","short_name":"DeepSeek V4 Flash Vision Exp","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.\n\nIt is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-flash-vision-exp-20260821","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v4-flash-vision-exp","model_variant_permaslug":"deepseek/deepseek-v4-flash-vision-exp-20260821","adapter_name":"DeepSeekAdapter","provider_name":"DeepSeek","provider_info":{"name":"DeepSeek","displayName":"DeepSeek","slug":"deepseek","baseUrl":"https://api.deepseek.com/beta","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://chat.deepseek.com/downloads/DeepSeek%20Terms%20of%20Use.html","privacyPolicyURL":"https://chat.deepseek.com/downloads/DeepSeek%20Privacy%20Policy.html","requiresUserIDs":false},"headquarters":"CN","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepSeekAdapter","statusPageUrl":"https://status.deepseek.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepSeek.png"},"sendClientIp":false,"pricingStrategy":"deepseek"},"provider_display_name":"DeepSeek","provider_slug":"deepseek","provider_model_id":"deepseek-v4-flash-vision-exp","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":384000,"max_tokens_per_image":384,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","tools","tool_choice","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://chat.deepseek.com/downloads/DeepSeek%20Terms%20of%20Use.html","privacyPolicyURL":"https://chat.deepseek.com/downloads/DeepSeek%20Privacy%20Policy.html"},"pricing":{"prompt":"0.00000022","completion":"0.00000066","input_cache_read":"0.000000007","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000066","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000066","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"deepseek:cache_hit_tokens":"0.000000007","deepseek:cache_miss_tokens":"0.00000022","deepseek:completion_tokens":"0.00000066","deepseek:peak_cache_hit_tokens":"0.000000014","deepseek:peak_cache_miss_tokens":"0.00000044","deepseek:peak_completion_tokens":"0.00000132"},"pricing_version_id":"46db92f8-d850-4d30-828d-15f1b89cc17f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_implicit_caching":true,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-21T11:26:22.203Z","status":0}},{"slug":"stealth/ox-alpha","hf_slug":null,"updated_at":"2026-08-20T20:47:37.940Z","created_at":"2026-08-20T20:04:55.369Z","hf_updated_at":null,"name":"Ox Alpha","short_name":"Ox Alpha","author":"stealth","author_display_name":"Stealth","author_icon_uri":null,"description":"Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.\n\nOx Alpha is a stealth model. It is developed and operated by a third-party provider who has chosen to remain anonymous during this preview. OpenRouter routes requests to it and is not its developer, owner, or provider. Prompts and completions are retained by the provider and are not used for training; all other use is governed by the [Stealth Model Terms](https://openrouter.ai/terms/stealth).","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"This stealth model is developed and operated by a third-party model provider. Prompts and completions for this model are retained by the provider and are not used for training; all other use is governed by the [Stealth Model Terms](https://openrouter.ai/terms/stealth).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"stealth/ox-alpha","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"da0a73a5-417d-4684-afbb-92e9e826e084","name":"Stealth | stealth/ox-alpha","context_length":1048576,"model":{"slug":"stealth/ox-alpha","hf_slug":null,"updated_at":"2026-08-20T20:47:37.940306+00:00","created_at":"2026-08-20T20:04:55.369+00:00","hf_updated_at":null,"name":"Ox Alpha","short_name":"Ox Alpha","author":"stealth","author_display_name":"Stealth","author_icon_uri":null,"description":"Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.\n\nOx Alpha is a stealth model. It is developed and operated by a third-party provider who has chosen to remain anonymous during this preview. OpenRouter routes requests to it and is not its developer, owner, or provider. Prompts and completions are retained by the provider and are not used for training; all other use is governed by the [Stealth Model Terms](https://openrouter.ai/terms/stealth).","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"This stealth model is developed and operated by a third-party model provider. Prompts and completions for this model are retained by the provider and are not used for training; all other use is governed by the [Stealth Model Terms](https://openrouter.ai/terms/stealth).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"stealth/ox-alpha","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"stealth/ox-alpha","model_variant_permaslug":"stealth/ox-alpha","adapter_name":"StealthAdapter","provider_name":"Stealth","provider_info":{"name":"Stealth","displayName":"Stealth","slug":"stealth","baseUrl":" ","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openrouter.ai/terms/stealth","requiresUserIDs":true},"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"StealthAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"/images/icons/Stealth.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Stealth","provider_slug":"stealth","provider_model_id":"stealth/ox-alpha","quantization":"unknown","variant":"standard","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openrouter.ai/terms/stealth","requiresUserIDs":true},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0","openai:cached_prompt_tokens":"0"},"pricing_version_id":"6d8ef5e9-ba53-4631-a71a-918e77d5a5ce","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":500,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":false,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2098-12-31T16:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-20T20:49:38.204Z","status":0}},{"slug":"tencent/hy-mt2-1.8b","hf_slug":"tencent/Hy-MT2-1.8B","updated_at":"2026-08-20T13:13:01.797Z","created_at":"2026-08-20T13:13:01.796Z","hf_updated_at":null,"name":"Tencent: Hy-MT2-1.8B","short_name":"Hy-MT2-1.8B","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy-mt2-1.8b-20260521","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"da6a7d6d-fab7-4273-a9ed-488d61d19477","name":"Tencent | tencent/hy-mt2-1.8b-20260521","context_length":8192,"model":{"slug":"tencent/hy-mt2-1.8b","hf_slug":"tencent/Hy-MT2-1.8B","updated_at":"2026-08-20T13:13:01.797167+00:00","created_at":"2026-08-20T13:13:01.796+00:00","hf_updated_at":null,"name":"Tencent: Hy-MT2-1.8B","short_name":"Hy-MT2-1.8B","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy-mt2-1.8b-20260521","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"tencent/hy-mt2-1.8b","model_variant_permaslug":"tencent/hy-mt2-1.8b-20260521","adapter_name":"OpenAIAdapter","provider_name":"Tencent","provider_info":{"name":"Tencent","displayName":"Tencent Cloud","slug":"tencent","baseUrl":"https://tokenhub-intl.tencentcloudmaas.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.tencentcloud.com/en/document/product/301/78869","privacyPolicyURL":"https://www.tencentcloud.com/en/document/product/1300/78952","requiresUserIDs":false},"headquarters":"CN","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.tencentcloud.com","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.tencentcloud.com&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Tencent Cloud","provider_slug":"tencent/fp8","provider_model_id":"hy-mt2-lite","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.tencentcloud.com/en/document/product/301/78869","privacyPolicyURL":"https://www.tencentcloud.com/en/document/product/1300/78952"},"pricing":{"prompt":"0.000000044","completion":"0.000000177","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000177","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000177","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000044","openai:completion_tokens":"0.000000177"},"pricing_version_id":"7c031447-5b09-4603-877c-290300c9959f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-19T14:08:09.043Z","status":0}},{"slug":"tencent/hy-mt2-30b-a3b","hf_slug":"tencent/Hy-MT2-30B-A3B","updated_at":"2026-08-20T13:12:41.940Z","created_at":"2026-08-20T13:12:41.940Z","hf_updated_at":null,"name":"Tencent: Hy-MT2-30B-A3B","short_name":"Hy-MT2-30B-A3B","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation. It uses 3B active parameters out of 30B total.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy-mt2-30b-a3b-20260521","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"16cf5d0b-f9e4-45c2-acb3-47ca2adb0159","name":"Tencent | tencent/hy-mt2-30b-a3b-20260521","context_length":8192,"model":{"slug":"tencent/hy-mt2-30b-a3b","hf_slug":"tencent/Hy-MT2-30B-A3B","updated_at":"2026-08-20T13:12:41.940774+00:00","created_at":"2026-08-20T13:12:41.94+00:00","hf_updated_at":null,"name":"Tencent: Hy-MT2-30B-A3B","short_name":"Hy-MT2-30B-A3B","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation. It uses 3B active parameters out of 30B total.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy-mt2-30b-a3b-20260521","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"tencent/hy-mt2-30b-a3b","model_variant_permaslug":"tencent/hy-mt2-30b-a3b-20260521","adapter_name":"OpenAIAdapter","provider_name":"Tencent","provider_info":{"name":"Tencent","displayName":"Tencent Cloud","slug":"tencent","baseUrl":"https://tokenhub-intl.tencentcloudmaas.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.tencentcloud.com/en/document/product/301/78869","privacyPolicyURL":"https://www.tencentcloud.com/en/document/product/1300/78952","requiresUserIDs":false},"headquarters":"CN","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.tencentcloud.com","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.tencentcloud.com&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Tencent Cloud","provider_slug":"tencent/fp8","provider_model_id":"hy-mt2-pro","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.tencentcloud.com/en/document/product/301/78869","privacyPolicyURL":"https://www.tencentcloud.com/en/document/product/1300/78952"},"pricing":{"prompt":"0.000000074","completion":"0.000000295","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000074","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000295","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000074","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000295","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000074","openai:completion_tokens":"0.000000295"},"pricing_version_id":"17037d14-6c85-4bff-bbc8-c7fb929d79d0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-19T14:08:05.897Z","status":0}},{"slug":"~z-ai/glm-latest","hf_slug":null,"updated_at":null,"created_at":"2026-08-19T14:50:53.713Z","hf_updated_at":null,"name":"Z.ai: GLM Latest","short_name":"GLM Latest","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"This model always redirects to the latest GLM model from Z.ai.","model_version_group_id":"004949da-f6a5-4322-93d0-447f6ec002f0","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~z-ai/glm-latest","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~z-ai/glm-latest","name":"Z.AI | z-ai/glm-5.3-20260816","context_length":1048576,"model":{"slug":"~z-ai/glm-latest","hf_slug":null,"updated_at":null,"created_at":"2026-08-19T14:50:53.713Z","hf_updated_at":null,"name":"Z.ai: GLM Latest","short_name":"GLM Latest","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"This model always redirects to the latest GLM model from Z.ai.","model_version_group_id":"004949da-f6a5-4322-93d0-447f6ec002f0","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~z-ai/glm-latest","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~z-ai/glm-latest","model_variant_permaslug":"~z-ai/glm-latest","adapter_name":"ZAIAdapter","provider_name":"Z.AI","provider_info":{"name":"Z.AI","displayName":"Z.ai","slug":"z-ai","baseUrl":"https://api.z.ai/api/paas/v4","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"ZAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://z.ai/model-api&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Z.ai","provider_slug":"z-ai/fp8","provider_model_id":"glm-5.3","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy"},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000014","openai:completion_tokens":"0.0000044","openai:cached_prompt_tokens":"0.00000026"},"pricing_version_id":"c67be574-2e19-4060-8bce-de8442665e64","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2098-12-31T16:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T18:06:03.786Z","status":0}},{"slug":"tencent/hy-mt2-7b","hf_slug":"tencent/Hy-MT2-7B","updated_at":"2026-08-19T14:13:17.727Z","created_at":"2026-08-19T14:13:17.727Z","hf_updated_at":null,"name":"Tencent: Hy-MT2-7B","short_name":"Hy-MT2-7B","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy-mt2-7b-20260521","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f8e78ec2-a9f6-4437-91e7-2e76267afdb7","name":"Tencent | tencent/hy-mt2-7b-20260521","context_length":8192,"model":{"slug":"tencent/hy-mt2-7b","hf_slug":"tencent/Hy-MT2-7B","updated_at":"2026-08-19T14:13:17.727182+00:00","created_at":"2026-08-19T14:13:17.727+00:00","hf_updated_at":null,"name":"Tencent: Hy-MT2-7B","short_name":"Hy-MT2-7B","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy-mt2-7b-20260521","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"tencent/hy-mt2-7b","model_variant_permaslug":"tencent/hy-mt2-7b-20260521","adapter_name":"OpenAIAdapter","provider_name":"Tencent","provider_info":{"name":"Tencent","displayName":"Tencent Cloud","slug":"tencent","baseUrl":"https://tokenhub-intl.tencentcloudmaas.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.tencentcloud.com/en/document/product/301/78869","privacyPolicyURL":"https://www.tencentcloud.com/en/document/product/1300/78952","requiresUserIDs":false},"headquarters":"CN","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.tencentcloud.com","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.tencentcloud.com&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Tencent Cloud","provider_slug":"tencent/fp8","provider_model_id":"hy-mt2-plus","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.tencentcloud.com/en/document/product/301/78869","privacyPolicyURL":"https://www.tencentcloud.com/en/document/product/1300/78952"},"pricing":{"prompt":"0.000000074","completion":"0.000000295","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000074","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000295","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000074","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000295","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000074","openai:completion_tokens":"0.000000295"},"pricing_version_id":"7e894887-85c1-4786-9ddb-312bc0ee1a01","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-19T14:08:07.505Z","status":0}},{"slug":"z-ai/glm-5.3","hf_slug":null,"updated_at":"2026-08-19T14:50:53.049Z","created_at":"2026-08-18T20:57:35.738Z","hf_updated_at":null,"name":"Z.ai: GLM 5.3","short_name":"GLM 5.3","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.\n\nReasoning is always on and cannot be disabled. Reasoning efforts `low`, `high`, and `max` are supported; `max` is the default.","model_version_group_id":"004949da-f6a5-4322-93d0-447f6ec002f0","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.3-20260816","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"db975786-e7f6-4838-9e56-3e0b77f1bdc2","name":"Z.AI | z-ai/glm-5.3-20260816","context_length":1048576,"model":{"slug":"z-ai/glm-5.3","hf_slug":null,"updated_at":"2026-08-19T14:50:53.04952+00:00","created_at":"2026-08-18T20:57:35.738+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5.3","short_name":"GLM 5.3","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.\n\nReasoning is always on and cannot be disabled. Reasoning efforts `low`, `high`, and `max` are supported; `max` is the default.","model_version_group_id":"004949da-f6a5-4322-93d0-447f6ec002f0","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.3-20260816","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5.3","model_variant_permaslug":"z-ai/glm-5.3-20260816","adapter_name":"ZAIAdapter","provider_name":"Z.AI","provider_info":{"name":"Z.AI","displayName":"Z.ai","slug":"z-ai","baseUrl":"https://api.z.ai/api/paas/v4","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"ZAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://z.ai/model-api&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Z.ai","provider_slug":"z-ai/fp8","provider_model_id":"glm-5.3","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy"},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000014","openai:completion_tokens":"0.0000044","openai:cached_prompt_tokens":"0.00000026"},"pricing_version_id":"c67be574-2e19-4060-8bce-de8442665e64","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2098-12-31T16:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T18:06:03.786Z","status":0}},{"slug":"qwen/qwen3.8-27b","hf_slug":"Qwen/Qwen3.8-27B","updated_at":"2026-08-14T17:44:34.834Z","created_at":"2026-08-14T15:55:10.434Z","hf_updated_at":null,"name":"Qwen: Qwen3.8 27B","short_name":"Qwen3.8 27B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.8-27b-20260814","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"864c5d5b-af7f-4dda-a797-eb7d1e566f2f","name":"Chutes | qwen/qwen3.8-27b-20260814","context_length":262144,"model":{"slug":"qwen/qwen3.8-27b","hf_slug":"Qwen/Qwen3.8-27B","updated_at":"2026-08-14T17:44:34.834475+00:00","created_at":"2026-08-14T15:55:10.434+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.8 27B","short_name":"Qwen3.8 27B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.8-27b-20260814","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.8-27b","model_variant_permaslug":"qwen/qwen3.8-27b-20260814","adapter_name":"ChutesAdapter","provider_name":"Chutes","provider_info":{"name":"Chutes","displayName":"Chutes","slug":"chutes","baseUrl":"https://llm.chutes.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://chutes.ai/tos","privacyPolicyURL":"https://chutes.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ChutesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Chutes","provider_slug":"chutes/fp8","provider_model_id":"Qwen/Qwen3.8-27B-TEE","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://chutes.ai/tos","privacyPolicyURL":"https://chutes.ai/privacy"},"pricing":{"prompt":"0.00000035","completion":"0.00000275","input_cache_read":"0.000000035","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000275","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000035","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000275","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000035","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000035","openai:completion_tokens":"0.00000275","openai:cached_prompt_tokens":"0.000000035"},"pricing_version_id":"7ff23b60-9c94-47f8-b834-2ab367473d2f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-16T12:01:32.058Z","status":0}},{"slug":"dots-studio/dots-3-note-preview","hf_slug":null,"updated_at":"2026-08-14T04:06:01.117Z","created_at":"2026-08-14T04:06:01.117Z","hf_updated_at":null,"name":"Dots Studio: Dots3-Note Preview (free)","short_name":"Dots3-Note Preview (free)","author":"dots-studio","author_display_name":"Dots Studio","author_icon_uri":"DotsStudio.png","description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is suited for reasoning, coding, multimodal understanding, long-context processing, and multi-step agent workflows.","model_version_group_id":null,"context_length":512000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"dots-studio/dots-3-note-preview-20260813","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"2b0adee4-4900-4027-98f1-e49712ae42b8","name":"AtlasCloud | dots-studio/dots-3-note-preview-20260813:free","context_length":512000,"model":{"slug":"dots-studio/dots-3-note-preview","hf_slug":null,"updated_at":"2026-08-14T04:06:01.117695+00:00","created_at":"2026-08-14T04:06:01.117+00:00","hf_updated_at":null,"name":"Dots Studio: Dots3-Note Preview","short_name":"Dots3-Note Preview","author":"dots-studio","author_display_name":"Dots Studio","author_icon_uri":"DotsStudio.png","description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is suited for reasoning, coding, multimodal understanding, long-context processing, and multi-step agent workflows.","model_version_group_id":null,"context_length":512000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"dots-studio/dots-3-note-preview-20260813","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"dots-studio/dots-3-note-preview:free","model_variant_permaslug":"dots-studio/dots-3-note-preview-20260813:free","adapter_name":"AtlasCloudAdapter","provider_name":"AtlasCloud","provider_info":{"name":"AtlasCloud","displayName":"AtlasCloud","slug":"atlas-cloud","baseUrl":"https://api.atlascloud.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"privacyPolicyURL":"https://www.atlascloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"AtlasCloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.atlascloud.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"AtlasCloud","provider_slug":"atlas-cloud/fp8","provider_model_id":"dots-studio/dots-3-note-prev-free","quantization":"fp8","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":512000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"privacyPolicyURL":"https://www.atlascloud.ai/privacy"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"5471b650-d62e-4357-a79c-a85fe5dc9cfc","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2026-09-30T13:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-13T14:30:06.720Z","status":0}},{"slug":"google/gemini-3.7-flash","hf_slug":null,"updated_at":"2026-08-13T19:49:56.298Z","created_at":"2026-08-13T17:03:01.688Z","hf_updated_at":null,"name":"Google: Gemini 3.7 Flash (batch)","short_name":"Gemini 3.7 Flash (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.7-flash-20260813","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/global"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":300,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"27ade0e4-3ed8-4624-b147-102c76c5d1be","name":"Google | google/gemini-3.7-flash-20260813:batch","context_length":1048576,"model":{"slug":"google/gemini-3.7-flash","hf_slug":null,"updated_at":"2026-08-13T19:49:56.298856+00:00","created_at":"2026-08-13T17:03:01.688+00:00","hf_updated_at":null,"name":"Google: Gemini 3.7 Flash","short_name":"Gemini 3.7 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.7-flash-20260813","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/global"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":300,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.7-flash:batch","model_variant_permaslug":"google/gemini-3.7-flash-20260813:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.7-flash","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.0000001875","completion":"0.0000009375","image":"0.0000001875","audio":"0.0000001875","input_audio_cache":"0.00000001875","input_cache_read":"0.00000001875","input_cache_write":"0.000000020833333333333335","web_search":"0.014","internal_reasoning":"0.0000009375","discount":0.75,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000020833333333333335","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.00000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000020833333333333335","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.00000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"gemini:prompt_tokens":"0.00000075","gemini:reasoning_tokens":"0.00000375","gemini:cache_read_tokens":"0.000000075","gemini:completion_tokens":"0.00000375","gemini:text_input_tokens":"0.00000075","gemini:audio_input_tokens":"0.00000075","gemini:image_input_tokens":"0.00000075","gemini:video_input_tokens":"0.00000075","gemini:cache_read_text_tokens":"0.000000075","gemini:cache_read_audio_tokens":"0.000000075","gemini:cache_read_image_tokens":"0.000000075","gemini:cache_read_video_tokens":"0.000000075","gemini:cache_write_storage_hours":"0.000001","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"75a61e44-ae79-44db-92d6-e3b6668d910c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-12T14:13:54.411Z","status":0}},{"slug":"google/gemini-3.7-flash","hf_slug":null,"updated_at":"2026-08-13T19:49:56.298Z","created_at":"2026-08-13T17:03:01.688Z","hf_updated_at":null,"name":"Google: Gemini 3.7 Flash","short_name":"Gemini 3.7 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.7-flash-20260813","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/global"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":300,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"e28074f6-26f6-4ba2-adf9-0bb807bc970e","name":"Google | google/gemini-3.7-flash-20260813","context_length":1048576,"model":{"slug":"google/gemini-3.7-flash","hf_slug":null,"updated_at":"2026-08-13T19:49:56.298856+00:00","created_at":"2026-08-13T17:03:01.688+00:00","hf_updated_at":null,"name":"Google: Gemini 3.7 Flash","short_name":"Gemini 3.7 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.7-flash-20260813","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/global"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":300,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.7-flash","model_variant_permaslug":"google/gemini-3.7-flash-20260813","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.7-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","input_cache_read":"0.0000000375","input_cache_write":"0.000000020833333333333335","web_search":"0.014","internal_reasoning":"0.000001875","discount":0.75,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000020833333333333335","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000020833333333333335","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"gemini:prompt_tokens":"0.0000015","gemini:reasoning_tokens":"0.0000075","gemini:web_search_calls":"0.014","gemini:cache_read_tokens":"0.00000015","gemini:completion_tokens":"0.0000075","gemini:text_input_tokens":"0.0000015","gemini:audio_input_tokens":"0.0000015","gemini:image_input_tokens":"0.0000015","gemini:video_input_tokens":"0.0000015","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.00000015","gemini:cache_read_audio_tokens":"0.00000015","gemini:cache_read_image_tokens":"0.00000015","gemini:cache_read_video_tokens":"0.00000015","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"0.000001","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"6657c55f-e921-43ff-b361-742728707831","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-12T14:13:50.546Z","status":0}},{"slug":"bytedance-seed/seed-2-1-turbo","hf_slug":null,"updated_at":"2026-08-12T16:29:36.465Z","created_at":"2026-08-12T16:29:36.465Z","hf_updated_at":null,"name":"ByteDance Seed: Seed 2.1 Turbo","short_name":"Seed 2.1 Turbo","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and video content, with capabilities for planning, debugging, and self-correction.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2-1-turbo-20260810","supports_reasoning":true,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d4339029-2784-4408-bd78-2d9f6193b667","name":"Seed | bytedance-seed/seed-2-1-turbo-20260810","context_length":262144,"model":{"slug":"bytedance-seed/seed-2-1-turbo","hf_slug":null,"updated_at":"2026-08-12T16:29:36.465461+00:00","created_at":"2026-08-12T16:29:36.465+00:00","hf_updated_at":null,"name":"ByteDance Seed: Seed 2.1 Turbo","short_name":"Seed 2.1 Turbo","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and video content, with capabilities for planning, debugging, and self-correction.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2-1-turbo-20260810","supports_reasoning":true,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance-seed/seed-2-1-turbo","model_variant_permaslug":"bytedance-seed/seed-2-1-turbo-20260810","adapter_name":"BytePlusAdapter","provider_name":"Seed","provider_info":{"name":"Seed","displayName":"Seed","slug":"seed","baseUrl":"https://ark.ap-southeast.bytepluses.com/api/v3","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"BytePlusAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256"},"sendClientIp":false,"pricingStrategy":"byteplus"},"provider_display_name":"Seed","provider_slug":"seed/fp8","provider_model_id":"ep-20260731012100-ld4rq","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","stop","tools","response_format","structured_outputs","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy"},"pricing":{"prompt":"0.0000005","completion":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"byteplus:prompt_tokens":"0.0000005","byteplus:completion_tokens":"0.0000025"},"pricing_version_id":"a0e8cd3a-1a20-4807-8aff-656f29d35444","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-10T20:04:54.359Z","status":0}},{"slug":"qwen/qwen3.8-2.4t-a95b","hf_slug":"Qwen/Qwen3.8-2.4T-A95B","updated_at":"2026-08-12T21:31:58.599Z","created_at":"2026-08-12T16:21:42.451Z","hf_updated_at":null,"name":"Qwen: Qwen3.8 2.4T A95B","short_name":"Qwen3.8 2.4T A95B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.8-2.4t-a95b-20260812","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"57870cab-954a-44ee-8231-e525460f55a9","name":"DeepInfra | qwen/qwen3.8-2.4t-a95b-20260812","context_length":262144,"model":{"slug":"qwen/qwen3.8-2.4t-a95b","hf_slug":"Qwen/Qwen3.8-2.4T-A95B","updated_at":"2026-08-12T21:31:58.599576+00:00","created_at":"2026-08-12T16:21:42.451+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.8 2.4T A95B","short_name":"Qwen3.8 2.4T A95B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.8-2.4t-a95b-20260812","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.8-2.4t-a95b","model_variant_permaslug":"qwen/qwen3.8-2.4t-a95b-20260812","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"Qwen/Qwen3.8-2.4T-A95B","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000002","openai:completion_tokens":"0.000006","openai:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"5d5b5405-df89-45d1-80ef-babb29531080","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-13T00:02:08.355Z","status":0}},{"slug":"bytedance-seed/seed-2.0-code","hf_slug":null,"updated_at":"2026-08-12T16:05:01.200Z","created_at":"2026-08-12T16:05:01.201Z","hf_updated_at":null,"name":"ByteDance Seed: Seed-2.0-Code","short_name":"Seed-2.0-Code","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude Code, Kilo, and OpenCode.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2.0-code-20260730","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c8534af4-90fc-4a27-9f4e-de565f89a92b","name":"Seed | bytedance-seed/seed-2.0-code-20260730","context_length":262144,"model":{"slug":"bytedance-seed/seed-2.0-code","hf_slug":null,"updated_at":"2026-08-12T16:05:01.200757+00:00","created_at":"2026-08-12T16:05:01.201+00:00","hf_updated_at":null,"name":"ByteDance Seed: Seed-2.0-Code","short_name":"Seed-2.0-Code","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude Code, Kilo, and OpenCode.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2.0-code-20260730","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance-seed/seed-2.0-code","model_variant_permaslug":"bytedance-seed/seed-2.0-code-20260730","adapter_name":"BytePlusAdapter","provider_name":"Seed","provider_info":{"name":"Seed","displayName":"Seed","slug":"seed","baseUrl":"https://ark.ap-southeast.bytepluses.com/api/v3","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"BytePlusAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256"},"sendClientIp":false,"pricingStrategy":"byteplus"},"provider_display_name":"Seed","provider_slug":"seed/fp8","provider_model_id":"ep-20260730233431-2ph9m","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy"},"pricing":{"prompt":"0.0000005","completion":"0.000003","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.000001","completion":"0.000006"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000005"},{"sku_label":">128K","price":"0.000001"}]},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000003"},{"sku_label":">128K","price":"0.000006"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000005"},{"sku_label":">128K","price":"0.000001"}]},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000003"},{"sku_label":">128K","price":"0.000006"}]}],"pricing_json":{"byteplus:prompt_tokens":"0.0000005","byteplus:completion_tokens":"0.000003","byteplus:long_context_threshold":"128000","byteplus:prompt_tokens_long_context":"0.000001","byteplus:completion_tokens_long_context":"0.000006"},"pricing_version_id":"ea0c90d1-96f1-4d31-95cd-a22ab1ad252c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-30T22:48:49.520Z","status":0}},{"slug":"deepseek/deepseek-v4-pro-0813","hf_slug":"deepseek-ai/DeepSeek-V4-Pro-0813","updated_at":"2026-08-13T12:34:01.231Z","created_at":"2026-08-12T15:42:44.768Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Pro 0813","short_name":"DeepSeek V4 Pro 0813","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-pro-20260813","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e719d276-b080-47ee-ae4f-63ed656a0b7a","name":"Alibaba | deepseek/deepseek-v4-pro-20260813","context_length":1000000,"model":{"slug":"deepseek/deepseek-v4-pro-0813","hf_slug":"deepseek-ai/DeepSeek-V4-Pro-0813","updated_at":"2026-08-13T12:34:01.231072+00:00","created_at":"2026-08-12T15:42:44.768395+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Pro 0813","short_name":"DeepSeek V4 Pro 0813","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-pro-20260813","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v4-pro-0813","model_variant_permaslug":"deepseek/deepseek-v4-pro-20260813","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"deepseek-v4-pro-0813","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":393216,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.0000005808","completion":"0.0000017424","input_cache_read":"0.00000005808","discount":0,"overrides":[{"utc_start":0,"utc_end":1400,"prompt":"0.000001122","completion":"0.000003366","input_cache_read":"0.0000001122"},{"utc_start":1400,"utc_end":0,"prompt":"0.0000005808","completion":"0.0000017424","input_cache_read":"0.00000005808"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005808","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"Off-peak","price":"0.0000005808"},{"sku_label":"Peak","price":"0.000001122"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000017424","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"Off-peak","price":"0.0000017424"},{"sku_label":"Peak","price":"0.000003366"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000005808","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"Off-peak","price":"0.00000005808"},{"sku_label":"Peak","price":"0.0000001122"}]},{"kind":"schedule","sku_label":"Off-peak Hours","price":"0","displayMultiplier":1,"unitLabel":"","scheduleWindows":[{"utc_start":1400,"utc_end":0}]},{"kind":"schedule","sku_label":"Peak Hours","price":"0","displayMultiplier":1,"unitLabel":"","scheduleWindows":[{"utc_start":0,"utc_end":1400}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005808","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"Off-peak","price":"0.0000005808"},{"sku_label":"Peak","price":"0.000001122"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000017424","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"Off-peak","price":"0.0000017424"},{"sku_label":"Peak","price":"0.000003366"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000005808","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"Off-peak","price":"0.00000005808"},{"sku_label":"Peak","price":"0.0000001122"}]},{"kind":"schedule","sku_label":"Off-peak Hours","price":"0","displayMultiplier":1,"unitLabel":"","scheduleWindows":[{"utc_start":1400,"utc_end":0}]},{"kind":"schedule","sku_label":"Peak Hours","price":"0","displayMultiplier":1,"unitLabel":"","scheduleWindows":[{"utc_start":0,"utc_end":1400}]}],"pricing_json":{"openai:prompt_tokens":"0.0000005808","openai:completion_tokens":"0.0000017424","openai:cached_prompt_tokens":"0.00000005808","openai_extended:peak_window_0_end":1400,"openai_extended:peak_prompt_tokens":"0.000001122","openai_extended:peak_window_0_start":0,"openai_extended:peak_completion_tokens":"0.000003366","openai_extended:peak_cached_prompt_tokens":"0.0000001122"},"pricing_version_id":"855b6159-5fdf-460e-9dcc-b2dfb18b45be","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-17T21:02:06.005Z","status":0}},{"slug":"x-ai/grok-4.6","hf_slug":null,"updated_at":"2026-08-12T15:35:57.756Z","created_at":"2026-08-12T15:35:57.755Z","hf_updated_at":null,"name":"SpaceXAI: Grok 4.6","short_name":"Grok 4.6","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.6-20260810","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"67ed3d9b-4f05-4e79-9bb6-1e8423a6c276","name":"xAI | x-ai/grok-4.6-20260810","context_length":500000,"model":{"slug":"x-ai/grok-4.6","hf_slug":null,"updated_at":"2026-08-12T15:35:57.756259+00:00","created_at":"2026-08-12T15:35:57.755+00:00","hf_updated_at":null,"name":"SpaceXAI: Grok 4.6","short_name":"Grok 4.6","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.6-20260810","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"x-ai/grok-4.6","model_variant_permaslug":"x-ai/grok-4.6-20260810","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai/zdr","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI (ZDR)","provider_slug":"xai/zdr","provider_model_id":"grok-4.6","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":["reasoning_effort"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.000001"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000005"},{"sku_label":">200K","price":"0.000001"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000005"},{"sku_label":">200K","price":"0.000001"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"0.000002","xai_responses:completion_tokens":"0.000006","xai_responses:cached_prompt_tokens":"0.0000005","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"0.000004","xai_responses:completion_tokens_high_context":"0.000012","xai_responses:cached_prompt_tokens_high_context":"0.000001"},"pricing_version_id":"cb585f4e-dbc3-4e10-82fa-82f45470c68a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-12T11:25:23.177Z","status":0}},{"slug":"liquid/lfm-2.5-2.6b","hf_slug":"LiquidAI/LFM2.5-2.6B","updated_at":"2026-08-11T20:28:40.538Z","created_at":"2026-08-11T17:48:39.909Z","hf_updated_at":null,"name":"LiquidAI: LFM2.5-2.6B (free)","short_name":"LFM2.5-2.6B (free)","author":"liquid","author_display_name":"Liquid","author_icon_uri":null,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or knowledge-heavy tasks.\n\nPrompts and outputs may be retained and used to train Liquid models.","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"liquid/lfm-2.5-2.6b-20260811","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.1,"top_k":50,"repetition_penalty":1.1},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"789f02b8-56f5-48d0-bae5-91b4957376c7","name":"Liquid | liquid/lfm-2.5-2.6b-20260811:free","context_length":65536,"model":{"slug":"liquid/lfm-2.5-2.6b","hf_slug":"LiquidAI/LFM2.5-2.6B","updated_at":"2026-08-11T20:28:40.538093+00:00","created_at":"2026-08-11T17:48:39.909826+00:00","hf_updated_at":null,"name":"LiquidAI: LFM2.5-2.6B","short_name":"LFM2.5-2.6B","author":"liquid","author_display_name":"Liquid","author_icon_uri":null,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or knowledge-heavy tasks.\n\nPrompts and outputs may be retained and used to train Liquid models.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"liquid/lfm-2.5-2.6b-20260811","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.1,"top_k":50,"repetition_penalty":1.1},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"liquid/lfm-2.5-2.6b:free","model_variant_permaslug":"liquid/lfm-2.5-2.6b-20260811:free","adapter_name":"OpenAIAdapter","provider_name":"Liquid","provider_info":{"name":"Liquid","displayName":"Liquid","slug":"liquid","baseUrl":"https://api.liquid.ai/openrouter/v1","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.liquid.ai/terms-conditions","privacyPolicyURL":"https://www.liquid.ai/privacy-policy","requiresUserIDs":true},"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.liquid.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Liquid","provider_slug":"liquid/fp8","provider_model_id":"openrouter:LiquidAI/LFM2.5-2.6B:free","quantization":"fp8","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","max_completion_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.liquid.ai/terms-conditions","privacyPolicyURL":"https://www.liquid.ai/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"7a726bfc-36d6-4a18-bf3f-ea86a142d49f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-11T17:53:15.599Z","status":0}},{"slug":"nvidia/nemotron-3.5-lightning","hf_slug":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","updated_at":"2026-08-11T16:53:47.025Z","created_at":"2026-08-11T12:52:31.833Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3.5 Lightning (free)","short_name":"Nemotron 3.5 Lightning (free)","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](<https://www.nvidia.com/en-us/about-nvidia/privacy-policy/>). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](<https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf>)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3.5-lightning-20260807","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"022e8198-179c-47a3-a359-9147cb1b8909","name":"Nvidia | nvidia/nemotron-3.5-lightning-20260807:free","context_length":1000000,"model":{"slug":"nvidia/nemotron-3.5-lightning","hf_slug":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","updated_at":"2026-08-11T16:53:47.025929+00:00","created_at":"2026-08-11T12:52:31.833+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3.5 Lightning","short_name":"Nemotron 3.5 Lightning","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](<https://www.nvidia.com/en-us/about-nvidia/privacy-policy/>). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](<https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf>)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3.5-lightning-20260807","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3.5-lightning:free","model_variant_permaslug":"nvidia/nemotron-3.5-lightning-20260807:free","adapter_name":"NvidiaAdapter","provider_name":"Nvidia","provider_info":{"name":"Nvidia","displayName":"NVIDIA","slug":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"NvidiaAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.nvidia.com/en-us/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NVIDIA","provider_slug":"nvidia/nvfp4","provider_model_id":"private/nvidia/nemotron-3.5-lightning-30b-a3b","quantization":"nvfp4","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"367936e4-1bed-4925-954e-df30080626d4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["reasoning_budget","chat_template_kwargs"],"capacity_tpm":null,"created_at":"2026-08-07T17:16:51.370Z","status":0}},{"slug":"nvidia/nemotron-3.5-lightning","hf_slug":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","updated_at":"2026-08-11T16:53:47.025Z","created_at":"2026-08-11T12:52:31.833Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3.5 Lightning","short_name":"Nemotron 3.5 Lightning","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](<https://www.nvidia.com/en-us/about-nvidia/privacy-policy/>). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](<https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf>)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3.5-lightning-20260807","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"9675f992-cf53-4946-a49b-e4f5a3e82584","name":"DeepInfra | nvidia/nemotron-3.5-lightning-20260807","context_length":262144,"model":{"slug":"nvidia/nemotron-3.5-lightning","hf_slug":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","updated_at":"2026-08-11T16:53:47.025929+00:00","created_at":"2026-08-11T12:52:31.833+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3.5 Lightning","short_name":"Nemotron 3.5 Lightning","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](<https://www.nvidia.com/en-us/about-nvidia/privacy-policy/>). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](<https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf>)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3.5-lightning-20260807","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3.5-lightning","model_variant_permaslug":"nvidia/nemotron-3.5-lightning-20260807","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000008","completion":"0.0000002","input_cache_read":"0.00000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000008","openai:completion_tokens":"0.0000002","openai:cached_prompt_tokens":"0.00000004"},"pricing_version_id":"9b6b1f05-0e73-4efe-aec0-76fe82522c04","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-11T17:38:18.922Z","status":0}},{"slug":"sakana/sakana-namazu","hf_slug":null,"updated_at":"2026-08-11T02:53:53.250Z","created_at":"2026-08-11T01:02:09.982Z","hf_updated_at":null,"name":"Sakana: Sakana Namazu","short_name":"Sakana Namazu","author":"sakana","author_display_name":"sakana","author_icon_uri":"https://sakana.ai","description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following, business writing, mathematics, coding, research, and multi-step agent workflows.\n\nSakana AI may use inputs for model training and improvement by default, with an opt-out available in the Sakana Console. Processing entirely within Japan is not guaranteed.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sakana/namazu-20260811","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"7c5c9b97-46c3-439c-8c85-d7844c95fa22","name":"Sakana AI | sakana/namazu-20260811","context_length":262144,"model":{"slug":"sakana/sakana-namazu","hf_slug":null,"updated_at":"2026-08-11T02:53:53.250308+00:00","created_at":"2026-08-11T01:02:09.982768+00:00","hf_updated_at":null,"name":"Sakana: Sakana Namazu","short_name":"Sakana Namazu","author":"sakana","author_display_name":"sakana","author_icon_uri":"https://sakana.ai","description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following, business writing, mathematics, coding, research, and multi-step agent workflows.\n\nSakana AI may use inputs for model training and improvement by default, with an opt-out available in the Sakana Console. Processing entirely within Japan is not guaranteed.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sakana/namazu-20260811","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"sakana/sakana-namazu","model_variant_permaslug":"sakana/namazu-20260811","adapter_name":"SakanaAIAdapter","provider_name":"Sakana AI","provider_info":{"name":"Sakana AI","displayName":"Sakana","slug":"sakana","baseUrl":"https://api.sakana.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://console.sakana.ai/terms-of-service","privacyPolicyURL":"https://console.sakana.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"SakanaAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://sakana.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"sakana_responses"},"provider_display_name":"Sakana","provider_slug":"sakana","provider_model_id":"sakana-namazu","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options"],"excluded_parameters":["response_format"],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://console.sakana.ai/terms-of-service","privacyPolicyURL":"https://console.sakana.ai/privacy-policy"},"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000015","web_search":"0.007","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.007","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true},{"kind":"unit","sku_label":"Code Execution","price":"0.12","displayMultiplier":1,"unitLabel":"/hour","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.007","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true},{"kind":"unit","sku_label":"Code Execution","price":"0.12","displayMultiplier":1,"unitLabel":"/hour","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.00000095","openai_responses:completion_tokens":"0.000004","openai_responses:cached_prompt_tokens":"0.00000015"},"pricing_version_id":"dddbfc29-f808-44de-8d46-bc4faf02db15","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_native_web_search":true,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-11T01:02:10.628Z","status":0}},{"slug":"upstage/solar-pro4","hf_slug":null,"updated_at":"2026-08-13T12:53:27.661Z","created_at":"2026-08-10T14:20:36.388Z","hf_updated_at":null,"name":"Upstage: Solar Pro 4","short_name":"Solar Pro 4","author":"upstage","author_display_name":"upstage","author_icon_uri":null,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.","model_version_group_id":null,"context_length":524288,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"upstage/solar-pro4-20260810","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"000381e4-18ad-455e-937b-ceeb3863fd67","name":"Upstage | upstage/solar-pro4-20260810","context_length":524288,"model":{"slug":"upstage/solar-pro4","hf_slug":null,"updated_at":"2026-08-13T12:53:27.661415+00:00","created_at":"2026-08-10T14:20:36.388676+00:00","hf_updated_at":null,"name":"Upstage: Solar Pro 4","short_name":"Solar Pro 4","author":"upstage","author_display_name":"upstage","author_icon_uri":null,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.","model_version_group_id":null,"context_length":524288,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"upstage/solar-pro4-20260810","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"upstage/solar-pro4","model_variant_permaslug":"upstage/solar-pro4-20260810","adapter_name":"UpstageAdapter","provider_name":"Upstage","provider_info":{"name":"Upstage","displayName":"Upstage","slug":"upstage","baseUrl":"https://api.upstage.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.upstage.ai/terms-of-service","privacyPolicyURL":"https://www.upstage.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"UpstageAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://upstage.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Upstage","provider_slug":"upstage","provider_model_id":"solar-pro4","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.upstage.ai/terms-of-service","privacyPolicyURL":"https://www.upstage.ai/privacy-policy"},"pricing":{"prompt":"0.00000003","completion":"0.00000012","input_cache_read":"0.000000006","discount":0.9,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000012","openai:cached_prompt_tokens":"0.00000006"},"pricing_version_id":"86180929-2b94-4cce-9cea-c7677693b226","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":1500000,"created_at":"2026-08-10T14:20:37.870Z","status":0}},{"slug":"meta/muse-glimmer-30b","hf_slug":"meta-models/Muse-Glimmer-30B","updated_at":"2026-08-10T21:31:11.461Z","created_at":"2026-08-09T19:06:34.984Z","hf_updated_at":null,"name":"Meta: Muse Glimmer 30B","short_name":"Muse Glimmer 30B","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta/muse-glimmer-30b-20260810","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"6244f10e-1e45-488b-a47f-f575e0edd12b","name":"Phala | meta/muse-glimmer-30b-20260810","context_length":131072,"model":{"slug":"meta/muse-glimmer-30b","hf_slug":"meta-models/Muse-Glimmer-30B","updated_at":"2026-08-10T21:31:11.461647+00:00","created_at":"2026-08-09T19:06:34.984983+00:00","hf_updated_at":null,"name":"Meta: Muse Glimmer 30B","short_name":"Muse Glimmer 30B","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta/muse-glimmer-30b-20260810","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"meta/muse-glimmer-30b","model_variant_permaslug":"meta/muse-glimmer-30b-20260810","adapter_name":"PhalaAdapter","provider_name":"Phala","provider_info":{"name":"Phala","displayName":"Phala","slug":"phala","baseUrl":"https://api.redpill.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://redpill.ai/terms","privacyPolicyURL":"https://redpill.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"PhalaAdapter","statusPageUrl":"https://status.phala.network/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://phala.network/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Phala","provider_slug":"phala","provider_model_id":"phala/muse-glimmer-30b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","tool_choice","response_format"],"excluded_parameters":["logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://redpill.ai/terms","privacyPolicyURL":"https://redpill.ai/privacy"},"pricing":{"prompt":"0.0000003","completion":"0.0000011","input_cache_read":"0.00000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000011","openai:cached_prompt_tokens":"0.00000004"},"pricing_version_id":"f3167b95-9cfd-482a-a3b5-ceaa943eff1b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-13T03:56:55.216Z","status":0}},{"slug":"meta/muse-spark-1.2","hf_slug":null,"updated_at":"2026-08-07T14:07:15.947Z","created_at":"2026-08-05T19:48:07.643Z","hf_updated_at":null,"name":"Meta: Muse Spark 1.2","short_name":"Muse Spark 1.2","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window.\n\nThe model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":["age_18plus"],"is_private":false,"permaslug":"meta/muse-spark-1.2-20260805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"ffc8e76e-808a-44d2-bd21-c6ac16e721cb","name":"Meta | meta/muse-spark-1.2-20260805","context_length":1048576,"model":{"slug":"meta/muse-spark-1.2","hf_slug":null,"updated_at":"2026-08-07T14:07:15.947073+00:00","created_at":"2026-08-05T19:48:07.643+00:00","hf_updated_at":null,"name":"Meta: Muse Spark 1.2","short_name":"Muse Spark 1.2","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window.\n\nThe model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":["age_18plus"],"is_private":false,"permaslug":"meta/muse-spark-1.2-20260805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"meta/muse-spark-1.2","model_variant_permaslug":"meta/muse-spark-1.2-20260805","adapter_name":"InternalStreamMetaResponsesAdapter","provider_name":"Meta","provider_info":{"name":"Meta","displayName":"Meta","slug":"meta","baseUrl":"https://api.meta.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://ai.developer.meta.com/legal/terms-of-service","privacyPolicyURL":"https://www.facebook.com/privacy/policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"InternalStreamMetaResponsesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://ai.meta.com/&size=256"},"sendClientIp":false,"pricingStrategy":"meta_responses"},"provider_display_name":"Meta","provider_slug":"meta","provider_model_id":"openrouter_muse-spark-1.2","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://ai.developer.meta.com/legal/terms-of-service","privacyPolicyURL":"https://www.facebook.com/privacy/policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00000425","input_cache_read":"0.00000015","web_search":"0.0025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000425","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.0025","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000425","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.0025","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.00000125","openai_responses:completion_tokens":"0.00000425","openai_responses:cached_prompt_tokens":"0.00000015"},"pricing_version_id":"422da434-c3d0-4d9c-be50-d47ff1b26709","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-05T00:21:41.856Z","status":0}},{"slug":"qwen/qwen3.8-max","hf_slug":null,"updated_at":"2026-08-12T15:24:59.894Z","created_at":"2026-08-03T04:33:32.259Z","hf_updated_at":null,"name":"Qwen: Qwen3.8 Max","short_name":"Qwen3.8 Max","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding, coding, and agentic workflows.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.8-max-20260803","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"6332e9fd-e0c4-4cae-8c17-d25bc774864a","name":"Alibaba | qwen/qwen3.8-max-20260803","context_length":1000000,"model":{"slug":"qwen/qwen3.8-max","hf_slug":null,"updated_at":"2026-08-12T15:24:59.894725+00:00","created_at":"2026-08-03T04:33:32.259838+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.8 Max","short_name":"Qwen3.8 Max","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding, coding, and agentic workflows.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.8-max-20260803","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.8-max","model_variant_permaslug":"qwen/qwen3.8-max-20260803","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.8-max","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.00000017","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.00000017","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000002","alibaba:completion_tokens":"0.000006","alibaba:cached_prompt_tokens":"0.00000025","alibaba:cache_creation_tokens":"0.0000025","alibaba:explicit_cached_prompt_tokens":"0.00000017"},"pricing_version_id":"ddd6f55a-25d7-46b2-a331-4088c24d889f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-03T04:34:25.231Z","status":0}},{"slug":"~deepseek/deepseek-v4-flash-latest","hf_slug":null,"updated_at":"2026-08-01T17:58:19.741Z","created_at":"2026-08-01T17:40:09.038Z","hf_updated_at":null,"name":"DeepSeek V4 Flash Latest","short_name":"DeepSeek V4 Flash Latest","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","model_version_group_id":"82f5b893-9a91-488e-b71d-77410fdf15d6","context_length":1310720,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~deepseek/deepseek-v4-flash-latest","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":[],"endpoint":{"id":"tilde-latest-~deepseek/deepseek-v4-flash-latest","name":"Relace | deepseek/deepseek-v4-flash-20260731","context_length":1048576,"model":{"slug":"~deepseek/deepseek-v4-flash-latest","hf_slug":null,"updated_at":"2026-08-01T17:58:19.741Z","created_at":"2026-08-01T17:40:09.038Z","hf_updated_at":null,"name":"DeepSeek V4 Flash Latest","short_name":"DeepSeek V4 Flash Latest","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","model_version_group_id":"82f5b893-9a91-488e-b71d-77410fdf15d6","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~deepseek/deepseek-v4-flash-latest","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":[]},"model_variant_slug":"~deepseek/deepseek-v4-flash-latest","model_variant_permaslug":"~deepseek/deepseek-v4-flash-latest","adapter_name":"VLLMOpenAIAdapter","provider_name":"Relace","provider_info":{"name":"Relace","displayName":"Relace","slug":"relace","baseUrl":"https://models.relace.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://relace.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Relace","provider_slug":"relace/fp4","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":1048576,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","seed","structured_outputs","response_format","logprobs","top_logprobs","parallel_tool_calls","reasoning_effort","top_a"],"excluded_parameters":["response_format","structured_outputs","logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy"},"pricing":{"prompt":"0.00000004","completion":"0.00000008","input_cache_read":"0.000000008","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000004","openai:completion_tokens":"0.00000008","openai:cached_prompt_tokens":"0.000000008"},"pricing_version_id":"5517e842-2a8d-4b3e-a35b-2a4121ef9138","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-11T06:35:58.413Z","status":0}},{"slug":"deepseek/deepseek-v4-flash-0731","hf_slug":"deepseek-ai/DeepSeek-V4-Flash-0731","updated_at":"2026-08-12T17:58:58.882Z","created_at":"2026-07-31T06:21:48.816Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Flash 0731","short_name":"DeepSeek V4 Flash 0731","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.","model_version_group_id":"82f5b893-9a91-488e-b71d-77410fdf15d6","context_length":1310720,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-flash-20260731","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":[],"endpoint":{"id":"57c1bfab-049c-4d6a-ab34-ac1007a6043b","name":"Relace | deepseek/deepseek-v4-flash-20260731","context_length":1048576,"model":{"slug":"deepseek/deepseek-v4-flash-0731","hf_slug":"deepseek-ai/DeepSeek-V4-Flash-0731","updated_at":"2026-08-12T17:58:58.882066+00:00","created_at":"2026-07-31T06:21:48.816855+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Flash 0731","short_name":"DeepSeek V4 Flash 0731","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.","model_version_group_id":"82f5b893-9a91-488e-b71d-77410fdf15d6","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-flash-20260731","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","max","low"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":[]},"model_variant_slug":"deepseek/deepseek-v4-flash-0731","model_variant_permaslug":"deepseek/deepseek-v4-flash-20260731","adapter_name":"VLLMOpenAIAdapter","provider_name":"Relace","provider_info":{"name":"Relace","displayName":"Relace","slug":"relace","baseUrl":"https://models.relace.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://relace.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Relace","provider_slug":"relace/fp4","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":1048576,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty"],"excluded_parameters":["response_format","structured_outputs","logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy"},"pricing":{"prompt":"0.00000004","completion":"0.00000008","input_cache_read":"0.000000008","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000004","openai:completion_tokens":"0.00000008","openai:cached_prompt_tokens":"0.000000008"},"pricing_version_id":"5517e842-2a8d-4b3e-a35b-2a4121ef9138","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-11T06:35:58.413Z","status":0}},{"slug":"thinkingmachines/inkling-small","hf_slug":"thinkingmachines/Inkling-Small","updated_at":"2026-08-21T16:46:30.544Z","created_at":"2026-07-30T20:25:17.934Z","hf_updated_at":null,"name":"Thinking Machines: Inkling Small (free)","short_name":"Inkling Small (free)","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling Small endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-small-20260730","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e27a9a6d-1451-4be4-876e-292ffcbf1e71","name":"Thinking Machines | thinkingmachines/inkling-small-20260730:free","context_length":262144,"model":{"slug":"thinkingmachines/inkling-small","hf_slug":"thinkingmachines/Inkling-Small","updated_at":"2026-08-21T16:46:30.54463+00:00","created_at":"2026-07-30T20:25:17.93417+00:00","hf_updated_at":null,"name":"Thinking Machines: Inkling Small","short_name":"Inkling Small","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling Small endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-small-20260730","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"thinkingmachines/inkling-small:free","model_variant_permaslug":"thinkingmachines/inkling-small-20260730:free","adapter_name":"ThinkingMachinesAdapter","provider_name":"Thinking Machines","provider_info":{"name":"Thinking Machines","displayName":"Thinking Machines","slug":"thinkingmachines","baseUrl":"https://airlock.thinkingmachines.dev/openrouter/v1","dataPolicy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf","privacyPolicyURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf","requiresUserIDs":true},"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"ThinkingMachinesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://thinkingmachines.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Thinking Machines","provider_slug":"thinkingmachines/nvfp4","provider_model_id":"thinkingmachines/Inkling-Small:free","quantization":"nvfp4","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","frequency_penalty","presence_penalty","seed","tools"],"excluded_parameters":["tool_choice"],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf","privacyPolicyURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf","requiresUserIDs":true},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"283f3f91-2450-4dfc-9a8c-2407c11ec1b7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":100,"limit_rpd":10000,"has_completions":false,"has_chat_completions":true,"features":{"disable_free_endpoint_limits":true,"supports_tool_choice":{"literal_none":false,"literal_auto":false,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-31T22:17:02.824Z","status":0}},{"slug":"thinkingmachines/inkling-small","hf_slug":"thinkingmachines/Inkling-Small","updated_at":"2026-08-21T16:46:30.544Z","created_at":"2026-07-30T20:25:17.934Z","hf_updated_at":null,"name":"Thinking Machines: Inkling Small","short_name":"Inkling Small","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling Small endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-small-20260730","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d1d9657b-3c3a-49b5-8f81-33204e7c71c3","name":"DeepInfra | thinkingmachines/inkling-small-20260730","context_length":524288,"model":{"slug":"thinkingmachines/inkling-small","hf_slug":"thinkingmachines/Inkling-Small","updated_at":"2026-08-21T16:46:30.54463+00:00","created_at":"2026-07-30T20:25:17.93417+00:00","hf_updated_at":null,"name":"Thinking Machines: Inkling Small","short_name":"Inkling Small","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling Small endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-small-20260730","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"thinkingmachines/inkling-small","model_variant_permaslug":"thinkingmachines/inkling-small-20260730","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"thinkingmachines/Inkling-Small","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias"],"excluded_parameters":["response_format","response_format","structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000045","completion":"0.0000012","input_cache_read":"0.0000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000045","openai:completion_tokens":"0.0000012","openai:cached_prompt_tokens":"0.0000001"},"pricing_version_id":"3b78d579-2b0c-47e1-b6f3-094d8b9b668a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-31T13:55:52.979Z","status":0}},{"slug":"qwen/qwen3.7-flash","hf_slug":null,"updated_at":"2026-07-27T23:59:29.321Z","created_at":"2026-07-27T22:16:01.027Z","hf_updated_at":null,"name":"Qwen: Qwen3.7 Flash","short_name":"Qwen3.7 Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.7-flash-20260727","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"5a9a0ee6-874a-4d03-92be-e5094c0df4e7","name":"Alibaba | qwen/qwen3.7-flash-20260727","context_length":1000000,"model":{"slug":"qwen/qwen3.7-flash","hf_slug":null,"updated_at":"2026-07-27T23:59:29.321717+00:00","created_at":"2026-07-27T22:16:01.027832+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.7 Flash","short_name":"Qwen3.7 Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.7-flash-20260727","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.7-flash","model_variant_permaslug":"qwen/qwen3.7-flash-20260727","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.7-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":["structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.000000006","input_cache_write":"0.000000038","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000002","input_cache_write":"0.000000125"},{"min_prompt_tokens":256000,"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000004","input_cache_write":"0.00000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000003"},{"sku_label":"≤256K","price":"0.0000001"},{"sku_label":">256K","price":"0.0000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000013"},{"sku_label":"≤256K","price":"0.0000004"},{"sku_label":">256K","price":"0.0000008"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000006"},{"sku_label":"≤256K","price":"0.00000002"},{"sku_label":">256K","price":"0.00000004"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000038","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000038"},{"sku_label":"≤256K","price":"0.000000125"},{"sku_label":">256K","price":"0.00000025"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000003"},{"sku_label":"≤256K","price":"0.00000001"},{"sku_label":">256K","price":"0.00000002"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000003"},{"sku_label":"≤256K","price":"0.0000001"},{"sku_label":">256K","price":"0.0000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000013"},{"sku_label":"≤256K","price":"0.0000004"},{"sku_label":">256K","price":"0.0000008"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000006"},{"sku_label":"≤256K","price":"0.00000002"},{"sku_label":">256K","price":"0.00000004"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000038","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000038"},{"sku_label":"≤256K","price":"0.000000125"},{"sku_label":">256K","price":"0.00000025"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000003"},{"sku_label":"≤256K","price":"0.00000001"},{"sku_label":">256K","price":"0.00000002"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000003","alibaba:tier2_threshold":"32000","alibaba:tier3_threshold":"256000","alibaba:completion_tokens":"0.00000013","alibaba:prompt_tokens_tier2":"0.0000001","alibaba:prompt_tokens_tier3":"0.0000002","alibaba:cached_prompt_tokens":"0.000000006","alibaba:cache_creation_tokens":"0.000000038","alibaba:completion_tokens_tier2":"0.0000004","alibaba:completion_tokens_tier3":"0.0000008","alibaba:cached_prompt_tokens_tier2":"0.00000002","alibaba:cached_prompt_tokens_tier3":"0.00000004","alibaba:cache_creation_tokens_tier2":"0.000000125","alibaba:cache_creation_tokens_tier3":"0.00000025","alibaba:explicit_cached_prompt_tokens":"0.000000003","alibaba:explicit_cached_prompt_tokens_tier2":"0.00000001","alibaba:explicit_cached_prompt_tokens_tier3":"0.00000002"},"pricing_version_id":"219a49e4-4ebd-423d-a826-4bab6d9f7baf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-27T22:16:01.755Z","status":0}},{"slug":"anthropic/claude-opus-5-fast","hf_slug":null,"updated_at":"2026-07-29T18:24:07.276Z","created_at":"2026-07-24T17:02:26.533Z","hf_updated_at":null,"name":"Claude Opus 5 (Fast)","short_name":"Claude Opus 5 (Fast)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-opus-5-fast-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["anthropic"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a42a3d15-779d-403b-b151-d3482546b474","name":"Anthropic | anthropic/claude-opus-5-fast-20260723","context_length":1000000,"model":{"slug":"anthropic/claude-opus-5-fast","hf_slug":null,"updated_at":"2026-07-29T18:24:07.27668+00:00","created_at":"2026-07-24T17:02:26.533+00:00","hf_updated_at":null,"name":"Claude Opus 5 (Fast)","short_name":"Claude Opus 5 (Fast)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-opus-5-fast-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["anthropic"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-5-fast","model_variant_permaslug":"anthropic/claude-opus-5-fast-20260723","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"20e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"20e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"10e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"1e-6","anthropic:completion_tokens":"50e-6","anthropic:cache_write_1h_tokens":"20e-6","anthropic:cache_write_5m_tokens":"12.5e-6"},"pricing_version_id":"b1c89121-7aab-4899-af20-0ddb6cc65923","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":250,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T17:23:18.195Z","status":0}},{"slug":"anthropic/claude-opus-5","hf_slug":null,"updated_at":"2026-08-17T21:55:56.059Z","created_at":"2026-07-24T17:02:24.129Z","hf_updated_at":null,"name":"Claude Opus 5 (batch)","short_name":"Claude Opus 5 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-opus-5-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"1881dacf-5279-4a4c-b428-7d75a383dfd5","name":"Anthropic | anthropic/claude-opus-5-20260723:batch","context_length":1000000,"model":{"slug":"anthropic/claude-opus-5","hf_slug":null,"updated_at":"2026-08-17T21:55:56.05929+00:00","created_at":"2026-07-24T17:02:24.129+00:00","hf_updated_at":null,"name":"Claude Opus 5","short_name":"Claude Opus 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-opus-5-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-5:batch","model_variant_permaslug":"anthropic/claude-opus-5-20260723:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-5","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-06","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-05","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-07","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"3.125e-06","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"5e-06","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-06","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-05","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-07","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"3.125e-06","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"5e-06","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"2.5e-06","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"2.5e-07","anthropic:completion_tokens":"1.25e-05","anthropic:cache_write_1h_tokens":"5e-06","anthropic:cache_write_5m_tokens":"3.125e-06"},"pricing_version_id":"f725531a-dedc-4369-b3ac-75dc5c2955a2","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_web_fetch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:10.571Z","status":0}},{"slug":"anthropic/claude-opus-5","hf_slug":null,"updated_at":"2026-08-17T21:55:56.059Z","created_at":"2026-07-24T17:02:24.129Z","hf_updated_at":null,"name":"Claude Opus 5","short_name":"Claude Opus 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-opus-5-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"2edf66f3-04ad-4c38-b05a-bc69cf1a29ef","name":"Claude Platform on AWS | anthropic/claude-opus-5-20260723","context_length":1000000,"model":{"slug":"anthropic/claude-opus-5","hf_slug":null,"updated_at":"2026-08-17T21:55:56.05929+00:00","created_at":"2026-07-24T17:02:24.129+00:00","hf_updated_at":null,"name":"Claude Opus 5","short_name":"Claude Opus 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-opus-5-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-5","model_variant_permaslug":"anthropic/claude-opus-5-20260723","adapter_name":"ClaudeOnAwsAdapter","provider_name":"Claude Platform on AWS","provider_info":{"name":"Claude Platform on AWS","displayName":"Claude Platform on AWS","slug":"claude-on-aws","baseUrl":"https://aws-external-anthropic.us-east-1.api.aws/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"ClaudeOnAwsAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":false,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Claude Platform on AWS","provider_slug":"claude-on-aws","provider_model_id":"claude-opus-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"5e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":".5e-6","anthropic:completion_tokens":"25e-6","anthropic:cache_write_1h_tokens":"10e-6","anthropic:cache_write_5m_tokens":"6.25e-6"},"pricing_version_id":"e9e376f5-5c81-4454-88b8-1063473daef1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":250,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_web_fetch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-25T19:49:17.571Z","status":0}},{"slug":"inclusionai/ling-3.0-flash","hf_slug":"inclusionAI/Ling-3.0-flash","updated_at":"2026-08-05T23:46:41.312Z","created_at":"2026-07-23T14:56:20.920Z","hf_updated_at":null,"name":"Ling-3.0-flash","short_name":"Ling-3.0-flash","author":"inclusionai","author_display_name":"inclusionai","author_icon_uri":null,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.\n\nThe model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"inclusionai/ling-3.0-flash-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"ad853a79-97b2-4260-8163-fbe2a796cebf","name":"Novita | inclusionai/ling-3.0-flash-20260723","context_length":262144,"model":{"slug":"inclusionai/ling-3.0-flash","hf_slug":"inclusionAI/Ling-3.0-flash","updated_at":"2026-08-05T23:46:41.31286+00:00","created_at":"2026-07-23T14:56:20.920601+00:00","hf_updated_at":null,"name":"Ling-3.0-flash","short_name":"Ling-3.0-flash","author":"inclusionai","author_display_name":"inclusionai","author_icon_uri":null,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.\n\nThe model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"inclusionai/ling-3.0-flash-20260723","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"inclusionai/ling-3.0-flash","model_variant_permaslug":"inclusionai/ling-3.0-flash-20260723","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita","provider_model_id":"inclusionai/ling-3.0-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":["structured_outputs","response_format"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.000000021","completion":"0.000000063","input_cache_read":"0.0000000042","discount":0.65,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000021","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000063","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000042","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000021","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000063","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000042","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000006","openai:completion_tokens":"0.00000018","openai:cached_prompt_tokens":"0.000000012"},"pricing_version_id":"53ed7b8d-04f6-4cce-9644-936a5242df89","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{},"supported_image_parameters":{"n":{},"input_references":{},"output_compression":{}},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-06T18:38:59.052Z","status":0}},{"slug":"poolside/laguna-s-2.1","hf_slug":"poolside/Laguna-S-2.1","updated_at":"2026-07-31T12:24:19.274Z","created_at":"2026-07-21T16:51:23.607Z","hf_updated_at":null,"name":"Poolside: Laguna S 2.1 (free)","short_name":"Laguna S 2.1 (free)","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.\n\nLaguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](<https://openmdw.ai/license/1-1/>), and should be used consistently with Poolside's [Acceptable Use Policy](<https://poolside.ai/legal/acceptable-use-policy>). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](<mailto:security@poolside.ai>).\n\nIf you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-s-2.1-20260720","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"1671d9aa-18c8-444a-96c7-f5f6231591bb","name":"Poolside | poolside/laguna-s-2.1-20260720:free","context_length":262144,"model":{"slug":"poolside/laguna-s-2.1","hf_slug":"poolside/Laguna-S-2.1","updated_at":"2026-07-31T12:24:19.274341+00:00","created_at":"2026-07-21T16:51:23.607+00:00","hf_updated_at":null,"name":"Poolside: Laguna S 2.1","short_name":"Laguna S 2.1","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.\n\nLaguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](<https://openmdw.ai/license/1-1/>), and should be used consistently with Poolside's [Acceptable Use Policy](<https://poolside.ai/legal/acceptable-use-policy>). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](<mailto:security@poolside.ai>).\n\nIf you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-s-2.1-20260720","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"poolside/laguna-s-2.1:free","model_variant_permaslug":"poolside/laguna-s-2.1-20260720:free","adapter_name":"VLLMOpenAIAdapter","provider_name":"Poolside","provider_info":{"name":"Poolside","displayName":"Poolside","slug":"poolside","baseUrl":"https://inference.poolside.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://poolside.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Poolside","provider_slug":"poolside/fp4","provider_model_id":"poolside/laguna-s-2.1","quantization":"fp4","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"excluded_parameters":["response_format","structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"613946c7-c046-4c53-ba17-ef145c679846","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T14:22:26.860Z","status":0}},{"slug":"poolside/laguna-s-2.1","hf_slug":"poolside/Laguna-S-2.1","updated_at":"2026-07-31T12:24:19.274Z","created_at":"2026-07-21T16:51:23.607Z","hf_updated_at":null,"name":"Poolside: Laguna S 2.1","short_name":"Laguna S 2.1","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.\n\nLaguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](<https://openmdw.ai/license/1-1/>), and should be used consistently with Poolside's [Acceptable Use Policy](<https://poolside.ai/legal/acceptable-use-policy>). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](<mailto:security@poolside.ai>).\n\nIf you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-s-2.1-20260720","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"ab7f9e97-1af5-4b81-b099-cc932f54234e","name":"Poolside | poolside/laguna-s-2.1-20260720","context_length":1048576,"model":{"slug":"poolside/laguna-s-2.1","hf_slug":"poolside/Laguna-S-2.1","updated_at":"2026-07-31T12:24:19.274341+00:00","created_at":"2026-07-21T16:51:23.607+00:00","hf_updated_at":null,"name":"Poolside: Laguna S 2.1","short_name":"Laguna S 2.1","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.\n\nLaguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](<https://openmdw.ai/license/1-1/>), and should be used consistently with Poolside's [Acceptable Use Policy](<https://poolside.ai/legal/acceptable-use-policy>). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](<mailto:security@poolside.ai>).\n\nIf you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-s-2.1-20260720","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"poolside/laguna-s-2.1","model_variant_permaslug":"poolside/laguna-s-2.1-20260720","adapter_name":"VLLMOpenAIAdapter","provider_name":"Poolside","provider_info":{"name":"Poolside","displayName":"Poolside","slug":"poolside","baseUrl":"https://inference.poolside.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://poolside.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Poolside","provider_slug":"poolside/fp4","provider_model_id":"poolside/laguna-s-2.1:fast","quantization":"fp4","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","temperature","max_tokens"],"excluded_parameters":["response_format","structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":90,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy"},"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000009","discount":0.1,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000009","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000009","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000002","openai:cached_prompt_tokens":"0.00000001"},"pricing_version_id":"d2d2a866-78ad-4f08-a263-be05c1095c87","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":50,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T14:22:28.186Z","status":0}},{"slug":"google/gemini-3.6-flash","hf_slug":null,"updated_at":"2026-07-21T15:27:53.845Z","created_at":"2026-07-21T15:12:13.976Z","hf_updated_at":null,"name":"Google: Gemini 3.6 Flash (batch)","short_name":"Gemini 3.6 Flash (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.6-flash-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"c72615be-0575-485f-b97f-5188235aa134","name":"Google | google/gemini-3.6-flash-20260721:batch","context_length":1048576,"model":{"slug":"google/gemini-3.6-flash","hf_slug":null,"updated_at":"2026-07-21T15:27:53.845731+00:00","created_at":"2026-07-21T15:12:13.976+00:00","hf_updated_at":null,"name":"Google: Gemini 3.6 Flash","short_name":"Gemini 3.6 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.6-flash-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.6-flash:batch","model_variant_permaslug":"google/gemini-3.6-flash-20260721:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.6-flash","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","input_cache_read":"0.0000000375","input_cache_write":"0.00000004166666666666667","web_search":"0.014","internal_reasoning":"0.000001875","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"4.166666666666667e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"4.166666666666667e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.000000375","gemini:reasoning_tokens":"0.000001875","gemini:web_search_calls":"0.014","gemini:cache_read_tokens":"0.0000000375","gemini:completion_tokens":"0.000001875","gemini:text_input_tokens":"0.000000375","gemini:audio_input_tokens":"0.000000375","gemini:image_input_tokens":"0.000000375","gemini:video_input_tokens":"0.000000375","gemini:cache_read_text_tokens":"0.0000000375","gemini:cache_read_audio_tokens":"0.0000000375","gemini:cache_read_image_tokens":"0.0000000375","gemini:cache_read_video_tokens":"0.0000000375","gemini:cache_write_storage_hours":"0.0000005","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"4c1760f6-4af0-4092-9a6f-1764cec757fe","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T13:16:17.763Z","status":0}},{"slug":"google/gemini-3.6-flash","hf_slug":null,"updated_at":"2026-07-21T15:27:53.845Z","created_at":"2026-07-21T15:12:13.976Z","hf_updated_at":null,"name":"Google: Gemini 3.6 Flash","short_name":"Gemini 3.6 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.6-flash-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"5d6d133d-a953-4781-a835-7ee76f4e1388","name":"Google AI Studio | google/gemini-3.6-flash-20260721","context_length":1048576,"model":{"slug":"google/gemini-3.6-flash","hf_slug":null,"updated_at":"2026-07-21T15:27:53.845731+00:00","created_at":"2026-07-21T15:12:13.976+00:00","hf_updated_at":null,"name":"Google: Gemini 3.6 Flash","short_name":"Gemini 3.6 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.6-flash-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.6-flash","model_variant_permaslug":"google/gemini-3.6-flash-20260721","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.6-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","input_cache_read":"0.000000075","input_cache_write":"0.00000004166666666666667","web_search":"0.014","internal_reasoning":"0.00000375","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"4.166666666666667e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"4.166666666666667e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.00000075","gemini:reasoning_tokens":"0.00000375","gemini:web_search_calls":"0.014","gemini:cache_read_tokens":"0.000000075","gemini:completion_tokens":"0.00000375","gemini:text_input_tokens":"0.00000075","gemini:audio_input_tokens":"0.00000075","gemini:image_input_tokens":"0.00000075","gemini:video_input_tokens":"0.00000075","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.000000075","gemini:cache_read_audio_tokens":"0.000000075","gemini:cache_read_image_tokens":"0.000000075","gemini:cache_read_video_tokens":"0.000000075","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"0.0000005","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"7f5b4817-62e9-4e48-8de2-0b49c5ca77ee","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T13:16:18.588Z","status":0}},{"slug":"google/gemini-3.5-flash-lite","hf_slug":null,"updated_at":"2026-07-22T12:18:03.891Z","created_at":"2026-07-21T15:12:06.691Z","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash Lite (batch)","short_name":"Gemini 3.5 Flash Lite (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-lite-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"e5e2c3a1-ff6d-427b-9028-30fddbe28967","name":"Google | google/gemini-3.5-flash-lite-20260721:batch","context_length":1048576,"model":{"slug":"google/gemini-3.5-flash-lite","hf_slug":null,"updated_at":"2026-07-22T12:18:03.891112+00:00","created_at":"2026-07-21T15:12:06.691+00:00","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash Lite","short_name":"Gemini 3.5 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-lite-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.5-flash-lite:batch","model_variant_permaslug":"google/gemini-3.5-flash-lite-20260721:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.5-flash-lite","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.00000015","input_audio_cache":"0.000000015","input_cache_read":"0.000000015","web_search":"0.014","internal_reasoning":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.015e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.015e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.015e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.015e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.15e-6","gemini:reasoning_tokens":"1.25e-6","gemini:web_search_calls":"0.014","gemini:cache_read_tokens":"0.015e-6","gemini:completion_tokens":"1.25e-6","gemini:text_input_tokens":"0.15e-6","gemini:audio_input_tokens":"0.15e-6","gemini:image_input_tokens":"0.15e-6","gemini:video_input_tokens":"0.15e-6","gemini:cache_read_text_tokens":"0.015e-6","gemini:cache_read_audio_tokens":"0.015e-6","gemini:cache_read_image_tokens":"0.015e-6","gemini:cache_read_video_tokens":"0.015e-6","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"ad3fc38c-d7ba-483e-900c-481b70340472","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T13:16:19.719Z","status":0}},{"slug":"google/gemini-3.5-flash-lite","hf_slug":null,"updated_at":"2026-07-22T12:18:03.891Z","created_at":"2026-07-21T15:12:06.691Z","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash Lite","short_name":"Gemini 3.5 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-lite-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"6bd8f433-79e1-416c-b407-1772eb796c9a","name":"Google AI Studio | google/gemini-3.5-flash-lite-20260721","context_length":1048576,"model":{"slug":"google/gemini-3.5-flash-lite","hf_slug":null,"updated_at":"2026-07-22T12:18:03.891112+00:00","created_at":"2026-07-21T15:12:06.691+00:00","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash Lite","short_name":"Gemini 3.5 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-lite-20260721","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.5-flash-lite","model_variant_permaslug":"google/gemini-3.5-flash-lite-20260721","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.5-flash-lite","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.0000003","input_audio_cache":"0.00000003","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.03e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.03e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.03e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.03e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.3e-6","gemini:reasoning_tokens":"2.5e-6","gemini:cache_read_tokens":"0.03e-6","gemini:completion_tokens":"2.5e-6","gemini:text_input_tokens":"0.3e-6","gemini:audio_input_tokens":"0.3e-6","gemini:image_input_tokens":"0.3e-6","gemini:video_input_tokens":"0.3e-6","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.03e-6","gemini:cache_read_audio_tokens":"0.03e-6","gemini:cache_read_image_tokens":"0.03e-6","gemini:cache_read_video_tokens":"0.03e-6","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"1e-6","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"2bb77b2d-fd7e-46c1-ba10-cd7c341ef373","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T13:16:20.332Z","status":0}},{"slug":"meituan/longcat-2.0","hf_slug":"meituan-longcat/LongCat-2.0","updated_at":"2026-07-20T13:40:55.842Z","created_at":"2026-07-20T13:37:38.452Z","hf_updated_at":null,"name":"Meituan: LongCat 2.0","short_name":"LongCat 2.0","author":"meituan","author_display_name":"meituan","author_icon_uri":null,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows.","model_version_group_id":null,"context_length":1048756,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meituan/longcat-2.0-20260720","supports_reasoning":true,"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1c1713d4-6398-47a1-9ff7-a6488c16e6c0","name":"AtlasCloud | meituan/longcat-2.0-20260720","context_length":1048756,"model":{"slug":"meituan/longcat-2.0","hf_slug":"meituan-longcat/LongCat-2.0","updated_at":"2026-07-20T13:40:55.842432+00:00","created_at":"2026-07-20T13:37:38.452658+00:00","hf_updated_at":null,"name":"Meituan: LongCat 2.0","short_name":"LongCat 2.0","author":"meituan","author_display_name":"meituan","author_icon_uri":null,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows.","model_version_group_id":null,"context_length":1048756,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meituan/longcat-2.0-20260720","supports_reasoning":true,"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meituan/longcat-2.0","model_variant_permaslug":"meituan/longcat-2.0-20260720","adapter_name":"AtlasCloudAdapter","provider_name":"AtlasCloud","provider_info":{"name":"AtlasCloud","displayName":"AtlasCloud","slug":"atlas-cloud","baseUrl":"https://api.atlascloud.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"privacyPolicyURL":"https://www.atlascloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"AtlasCloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.atlascloud.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"AtlasCloud","provider_slug":"atlas-cloud/fp8","provider_model_id":"meituan-longcat/longcat-2.0","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","stop","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"privacyPolicyURL":"https://www.atlascloud.ai/privacy"},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006","discount":0.6,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000075","openai:completion_tokens":"0.000003","openai:cached_prompt_tokens":"0.000000015"},"pricing_version_id":"494081e3-14ef-4123-b3bb-90f298d92c8e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T13:37:39.177Z","status":0}},{"slug":"thinkingmachines/inkling","hf_slug":"thinkingmachines/Inkling","updated_at":"2026-08-21T16:46:29.472Z","created_at":"2026-07-17T22:05:56.456Z","hf_updated_at":null,"name":"Thinking Machines: Inkling (free)","short_name":"Inkling (free)","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"89249263-425e-4099-a555-ea5c9698ba76","name":"Thinking Machines | thinkingmachines/inkling-20260715:free","context_length":262144,"model":{"slug":"thinkingmachines/inkling","hf_slug":"thinkingmachines/Inkling","updated_at":"2026-08-21T16:46:29.472449+00:00","created_at":"2026-07-17T22:05:56.456+00:00","hf_updated_at":null,"name":"Thinking Machines: Inkling","short_name":"Inkling","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"thinkingmachines/inkling:free","model_variant_permaslug":"thinkingmachines/inkling-20260715:free","adapter_name":"ThinkingMachinesAdapter","provider_name":"Thinking Machines","provider_info":{"name":"Thinking Machines","displayName":"Thinking Machines","slug":"thinkingmachines","baseUrl":"https://airlock.thinkingmachines.dev/openrouter/v1","dataPolicy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf","privacyPolicyURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf","requiresUserIDs":true},"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"ThinkingMachinesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://thinkingmachines.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Thinking Machines","provider_slug":"thinkingmachines/nvfp4","provider_model_id":"thinkingmachines/Inkling:free","quantization":"nvfp4","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","frequency_penalty","presence_penalty","seed","tools"],"excluded_parameters":["tool_choice","logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf","privacyPolicyURL":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf","requiresUserIDs":true},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"b2027cff-7259-429b-bbc4-d6c8abf759d4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":100,"limit_rpd":10000,"has_completions":false,"has_chat_completions":true,"features":{"disable_free_endpoint_limits":true,"supports_tool_choice":{"literal_none":false,"literal_auto":false,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-31T22:17:01.426Z","status":0}},{"slug":"thinkingmachines/inkling","hf_slug":"thinkingmachines/Inkling","updated_at":"2026-08-21T16:46:29.472Z","created_at":"2026-07-17T22:05:56.456Z","hf_updated_at":null,"name":"Thinking Machines: Inkling","short_name":"Inkling","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e","name":"DeepInfra | thinkingmachines/inkling-20260715","context_length":524288,"model":{"slug":"thinkingmachines/inkling","hf_slug":"thinkingmachines/Inkling","updated_at":"2026-08-21T16:46:29.472449+00:00","created_at":"2026-07-17T22:05:56.456+00:00","hf_updated_at":null,"name":"Thinking Machines: Inkling","short_name":"Inkling","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"thinkingmachines/inkling","model_variant_permaslug":"thinkingmachines/inkling-20260715","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"thinkingmachines/Inkling","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000095","completion":"0.00000405","input_cache_read":"0.00000016","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000405","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000016","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000405","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000016","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000095","openai:completion_tokens":"0.00000405","openai:cached_prompt_tokens":"0.00000016"},"pricing_version_id":"21d3d581-2fa6-442c-816d-480d03ea2c16","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T09:41:15.666Z","status":0}},{"slug":"thinkingmachines/inkling","hf_slug":"thinkingmachines/Inkling","updated_at":"2026-08-21T16:46:29.472Z","created_at":"2026-07-17T22:05:56.456Z","hf_updated_at":null,"name":"Thinking Machines: Inkling (batch)","short_name":"Inkling (batch)","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_version_group_id":null,"context_length":524288,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"35e3278d-b652-4a9c-990c-bc837a77546a","name":"Together | thinkingmachines/inkling-20260715:batch","context_length":524288,"model":{"slug":"thinkingmachines/inkling","hf_slug":"thinkingmachines/Inkling","updated_at":"2026-08-21T16:46:29.472449+00:00","created_at":"2026-07-17T22:05:56.456+00:00","hf_updated_at":null,"name":"Thinking Machines: Inkling","short_name":"Inkling","author":"thinkingmachines","author_display_name":"thinkingmachines","author_icon_uri":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.\n\nBy using this free endpoint, you agree to the [TML Free Research API Terms of Service](https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf). For more information about Thinking Machines Lab's data processing practices, see this [Privacy Notice](https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thinkingmachines/inkling-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["max","high","medium","low","minimal","none"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"thinkingmachines/inkling:batch","model_variant_permaslug":"thinkingmachines/inkling-20260715:batch","adapter_name":"TogetherBatchAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherBatchAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"thinkingmachines/Inkling","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000405","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000017","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000405","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000017","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000001","openai:completion_tokens":"0.00000405","openai:cached_prompt_tokens":"0.00000017"},"pricing_version_id":"26b90d91-937a-4997-885c-93445e33d5c3","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-27T21:36:53.308Z","status":0}},{"slug":"openrouter/auto-beta","hf_slug":null,"updated_at":"2026-07-17T19:30:35.933Z","created_at":"2026-07-17T17:59:25.582Z","hf_updated_at":null,"name":"Auto Router (Beta)","short_name":"Auto Router (Beta)","author":"openrouter","author_display_name":"OpenRouter","author_icon_uri":null,"description":"Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your selected [cost-quality tradeoff](/docs/guides/routing/routers/auto-router#cost-/-quality-tradeoff).\n\nTo see which model was used, visit [Activity](/activity), or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model.\n\nLearn more, including how to customize the models for routing, in our [docs](/docs/guides/routing/routers/auto-router). For another way to route, see [Pareto Code](/openrouter/pareto-code).","model_version_group_id":null,"context_length":2000000,"input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openrouter/auto-beta","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":null},{"slug":"moonshotai/kimi-k3","hf_slug":"moonshotai/Kimi-K3","updated_at":"2026-08-11T06:24:45.691Z","created_at":"2026-07-16T15:30:58.110Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K3","short_name":"Kimi K3","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","model_version_group_id":"4c6ad0bc-8b01-4b5f-8466-129136e36ef7","context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k3-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"57615dec-899a-41e7-8cab-1e2914497f0c","name":"Sail Research | moonshotai/kimi-k3-20260715","context_length":974842,"model":{"slug":"moonshotai/kimi-k3","hf_slug":"moonshotai/Kimi-K3","updated_at":"2026-08-11T06:24:45.691696+00:00","created_at":"2026-07-16T15:30:58.11+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K3","short_name":"Kimi K3","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","model_version_group_id":"4c6ad0bc-8b01-4b5f-8466-129136e36ef7","context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k3-20260715","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k3","model_variant_permaslug":"moonshotai/kimi-k3-20260715","adapter_name":"SailResearchAdapter","provider_name":"Sail Research","provider_info":{"name":"Sail Research","displayName":"Sail Research","slug":"sail-research","baseUrl":"https://api.sailresearch.com/partner/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.sailresearch.com/terms","privacyPolicyURL":"https://www.sailresearch.com/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"SailResearchAdapter","statusPageUrl":"https://status.sailresearch.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.sailresearch.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Sail Research","provider_slug":"sail-research/fp4","provider_model_id":"moonshotai/Kimi-K3","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":974842,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.sailresearch.com/terms","privacyPolicyURL":"https://www.sailresearch.com/privacy"},"pricing":{"prompt":"0.0000026","completion":"0.000013","input_cache_read":"0.00000029","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000026","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000029","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000026","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000029","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000026","openai:completion_tokens":"0.000013","openai:cached_prompt_tokens":"0.00000029"},"pricing_version_id":"1fda5b4f-bffd-4eac-a045-75429ba92867","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":false,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":false,"supports_base64_video_input":false,"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":2100000,"created_at":"2026-08-06T23:52:02.825Z","status":0}},{"slug":"meta/muse-spark-1.1","hf_slug":null,"updated_at":"2026-08-06T00:36:49.409Z","created_at":"2026-07-16T15:29:01.377Z","hf_updated_at":null,"name":"Meta: Muse Spark 1.1","short_name":"Muse Spark 1.1","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.\n\nThe model is designed to orchestrate multi-agent workflows, acting as either a main agent that plans and delegates or as a subagent, and generalizes zero-shot to new tools, MCP servers, and custom skills. It supports structured output, parallel function calling, built-in search with citations, and configurable reasoning effort. Meta reports strong performance on real-world coding across large codebases, computer-use workflows, and visual-to-code generation.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":["age_18plus"],"is_private":false,"permaslug":"meta/muse-spark-1.1-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b2b9f6f9-8880-41c1-bd0c-867650fd5238","name":"Meta | meta/muse-spark-1.1-20260709","context_length":1048576,"model":{"slug":"meta/muse-spark-1.1","hf_slug":null,"updated_at":"2026-08-06T00:36:49.409761+00:00","created_at":"2026-07-16T15:29:01.377+00:00","hf_updated_at":null,"name":"Meta: Muse Spark 1.1","short_name":"Muse Spark 1.1","author":"meta","author_display_name":"Meta","author_icon_uri":null,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.\n\nThe model is designed to orchestrate multi-agent workflows, acting as either a main agent that plans and delegates or as a subagent, and generalizes zero-shot to new tools, MCP servers, and custom skills. It supports structured output, parallel function calling, built-in search with citations, and configurable reasoning effort. Meta reports strong performance on real-world coding across large codebases, computer-use workflows, and visual-to-code generation.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":["age_18plus"],"is_private":false,"permaslug":"meta/muse-spark-1.1-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"meta/muse-spark-1.1","model_variant_permaslug":"meta/muse-spark-1.1-20260709","adapter_name":"InternalStreamMetaResponsesAdapter","provider_name":"Meta","provider_info":{"name":"Meta","displayName":"Meta","slug":"meta","baseUrl":"https://api.meta.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://ai.developer.meta.com/legal/terms-of-service","privacyPolicyURL":"https://www.facebook.com/privacy/policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"InternalStreamMetaResponsesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://ai.meta.com/&size=256"},"sendClientIp":false,"pricingStrategy":"meta_responses"},"provider_display_name":"Meta","provider_slug":"meta","provider_model_id":"openrouter_muse-spark-1.1","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://ai.developer.meta.com/legal/terms-of-service","privacyPolicyURL":"https://www.facebook.com/privacy/policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00000425","input_cache_read":"0.00000015","web_search":"0.0025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000425","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.0025","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000425","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.0025","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.00000125","openai_responses:completion_tokens":"0.00000425","openai_responses:cached_prompt_tokens":"0.00000015"},"pricing_version_id":"ffae7af6-28bd-404b-9b0f-47a7d4a0adac","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-11T03:32:11.530Z","status":0}},{"slug":"kwaipilot/kat-coder-air-v2.5","hf_slug":null,"updated_at":"2026-07-14T15:38:32.195Z","created_at":"2026-07-10T20:16:30.659Z","hf_updated_at":null,"name":"Kwaipilot: KAT-Coder-Air V2.5","short_name":"KAT-Coder-Air V2.5","author":"kwaipilot","author_display_name":"kwaipilot","author_icon_uri":null,"description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make modifications, and complete the entire process in the actual repository. At the same time, it seamlessly integrates multiple experts to fully retain the front-end aesthetic generation capability of V2.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"kwaipilot/kat-coder-air-v2.5-20260710","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"9af3f328-0015-4f68-9057-1caf8620d313","name":"StreamLake | kwaipilot/kat-coder-air-v2.5-20260710","context_length":256000,"model":{"slug":"kwaipilot/kat-coder-air-v2.5","hf_slug":null,"updated_at":"2026-07-14T15:38:32.195096+00:00","created_at":"2026-07-10T20:16:30.659136+00:00","hf_updated_at":null,"name":"Kwaipilot: KAT-Coder-Air V2.5","short_name":"KAT-Coder-Air V2.5","author":"kwaipilot","author_display_name":"kwaipilot","author_icon_uri":null,"description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make modifications, and complete the entire process in the actual repository. At the same time, it seamlessly integrates multiple experts to fully retain the front-end aesthetic generation capability of V2.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"kwaipilot/kat-coder-air-v2.5-20260710","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"kwaipilot/kat-coder-air-v2.5","model_variant_permaslug":"kwaipilot/kat-coder-air-v2.5-20260710","adapter_name":"StreamLakeAdapter","provider_name":"StreamLake","provider_info":{"name":"StreamLake","displayName":"StreamLake","slug":"streamlake","baseUrl":"https://vanchin.streamlake.ai/api/gateway/v1/endpoints","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"StreamLakeAdapter","statusPageUrl":"https://status.streamlake.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.streamlake.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"StreamLake","provider_slug":"streamlake","provider_model_id":"kat-coder-air-v2.5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":80000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","presence_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54"},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000015","openai:completion_tokens":"0.0000006","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"af4fc7d3-271d-42e3-8311-0c447e43594d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-10T20:16:41.456Z","status":0}},{"slug":"kwaipilot/kat-coder-pro-v2.5","hf_slug":null,"updated_at":"2026-07-14T15:38:42.199Z","created_at":"2026-07-10T20:16:29.989Z","hf_updated_at":null,"name":"Kwaipilot: KAT-Coder-Pro V2.5","short_name":"KAT-Coder-Pro V2.5","author":"kwaipilot","author_display_name":"kwaipilot","author_icon_uri":null,"description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make modifications, and complete the entire process in the actual repository. At the same time, it seamlessly integrates multiple experts to fully retain the front-end aesthetic generation capability of V2.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"kwaipilot/kat-coder-pro-v2.5-20260710","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"f8bf6b99-c193-48c5-ba1f-133c503de185","name":"StreamLake | kwaipilot/kat-coder-pro-v2.5-20260710","context_length":256000,"model":{"slug":"kwaipilot/kat-coder-pro-v2.5","hf_slug":null,"updated_at":"2026-07-14T15:38:42.199289+00:00","created_at":"2026-07-10T20:16:29.989091+00:00","hf_updated_at":null,"name":"Kwaipilot: KAT-Coder-Pro V2.5","short_name":"KAT-Coder-Pro V2.5","author":"kwaipilot","author_display_name":"kwaipilot","author_icon_uri":null,"description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make modifications, and complete the entire process in the actual repository. At the same time, it seamlessly integrates multiple experts to fully retain the front-end aesthetic generation capability of V2.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"kwaipilot/kat-coder-pro-v2.5-20260710","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"kwaipilot/kat-coder-pro-v2.5","model_variant_permaslug":"kwaipilot/kat-coder-pro-v2.5-20260710","adapter_name":"StreamLakeAdapter","provider_name":"StreamLake","provider_info":{"name":"StreamLake","displayName":"StreamLake","slug":"streamlake","baseUrl":"https://vanchin.streamlake.ai/api/gateway/v1/endpoints","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"StreamLakeAdapter","statusPageUrl":"https://status.streamlake.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.streamlake.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"StreamLake","provider_slug":"streamlake","provider_model_id":"kat-coder-pro-v2.5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":80000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","presence_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54"},"pricing":{"prompt":"0.00000074","completion":"0.00000296","input_cache_read":"0.00000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000074","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000296","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000074","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000296","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000074","openai:completion_tokens":"0.00000296","openai:cached_prompt_tokens":"0.00000015"},"pricing_version_id":"881b3fef-6c64-4d6c-8c72-dfacdf729fa5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-10T20:16:40.891Z","status":0}},{"slug":"openai/gpt-5.6-luna-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:57.045Z","created_at":"2026-07-09T09:54:27.822Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna Pro (batch)","short_name":"GPT-5.6 Luna Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6c251ade-2801-424a-b7cb-2cdbca9dee28","name":"OpenAI | openai/gpt-5.6-luna-pro-20260709:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.6-luna-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:57.04513+00:00","created_at":"2026-07-09T09:54:27.822+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna Pro","short_name":"GPT-5.6 Luna Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-luna-pro:batch","model_variant_permaslug":"openai/gpt-5.6-luna-pro-20260709:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-luna","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000001","completion":"0.0000006","input_cache_read":"0.00000001","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.0000009","input_cache_read":"0.00000002"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"token","sku_label":"Output Price","price":"6e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-07"},{"sku_label":">272K","price":"9e-07"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-08","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-08"},{"sku_label":">272K","price":"2e-08"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"token","sku_label":"Output Price","price":"6e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-07"},{"sku_label":">272K","price":"9e-07"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-08","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-08"},{"sku_label":">272K","price":"2e-08"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1e-07","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"6e-07","openai_responses:cached_prompt_tokens":"1e-08","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"2e-07","openai_responses:completion_tokens_high_context":"9e-07","openai_responses:cached_prompt_tokens_high_context":"2e-08"},"pricing_version_id":"84416e3d-3248-4f34-892a-d4165b6e81fa","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:12.390Z","status":0}},{"slug":"openai/gpt-5.6-luna-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:57.045Z","created_at":"2026-07-09T09:54:27.822Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna Pro","short_name":"GPT-5.6 Luna Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0ffa892c-07fc-43d2-8bf5-ba0892060aa3","name":"Azure | openai/gpt-5.6-luna-pro-20260709","context_length":1050000,"model":{"slug":"openai/gpt-5.6-luna-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:57.04513+00:00","created_at":"2026-07-09T09:54:27.822+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna Pro","short_name":"GPT-5.6 Luna Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-luna-pro","model_variant_permaslug":"openai/gpt-5.6-luna-pro-20260709","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.6-luna","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.0000002","completion":"0.0000012","input_cache_read":"0.00000002","input_cache_write":"0.00000025","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000012"},{"sku_label":">272K","price":"0.0000018"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000002"},{"sku_label":">272K","price":"0.00000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000025"},{"sku_label":">272K","price":"0.0000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000012"},{"sku_label":">272K","price":"0.0000018"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000002"},{"sku_label":">272K","price":"0.00000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000025"},{"sku_label":">272K","price":"0.0000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.0000002","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.0000012","openai_responses:cache_write_tokens":"0.00000025","openai_responses:cached_prompt_tokens":"0.00000002","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"0.0000004","openai_responses:completion_tokens_high_context":"0.0000018","openai_responses:cache_write_tokens_high_context":"0.0000005","openai_responses:cached_prompt_tokens_high_context":"0.00000004"},"pricing_version_id":"bf8049f2-c746-46bc-96bc-3c7bcf033572","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:17.567Z","status":0}},{"slug":"openai/gpt-5.6-luna","hf_slug":null,"updated_at":"2026-07-09T17:03:32.067Z","created_at":"2026-07-09T09:54:24.706Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna (batch)","short_name":"GPT-5.6 Luna (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d43bcaad-59ce-4805-a4a8-4274bb06c768","name":"OpenAI | openai/gpt-5.6-luna-20260709:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.6-luna","hf_slug":null,"updated_at":"2026-07-09T17:03:32.067353+00:00","created_at":"2026-07-09T09:54:24.706+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna","short_name":"GPT-5.6 Luna","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-luna:batch","model_variant_permaslug":"openai/gpt-5.6-luna-20260709:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-luna","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000001","completion":"0.0000006","input_cache_read":"0.00000001","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.0000009","input_cache_read":"0.00000002"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"token","sku_label":"Output Price","price":"6e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-07"},{"sku_label":">272K","price":"9e-07"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-08","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-08"},{"sku_label":">272K","price":"2e-08"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"token","sku_label":"Output Price","price":"6e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-07"},{"sku_label":">272K","price":"9e-07"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-08","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-08"},{"sku_label":">272K","price":"2e-08"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1e-07","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"6e-07","openai_responses:cached_prompt_tokens":"1e-08","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"2e-07","openai_responses:completion_tokens_high_context":"9e-07","openai_responses:cached_prompt_tokens_high_context":"2e-08"},"pricing_version_id":"5e432411-70df-491b-9a51-b3b984c35fd8","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:11.366Z","status":0}},{"slug":"openai/gpt-5.6-luna","hf_slug":null,"updated_at":"2026-07-09T17:03:32.067Z","created_at":"2026-07-09T09:54:24.706Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna","short_name":"GPT-5.6 Luna","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3e1fe018-94f7-4499-874b-34254ca271a7","name":"Azure | openai/gpt-5.6-luna-20260709","context_length":1050000,"model":{"slug":"openai/gpt-5.6-luna","hf_slug":null,"updated_at":"2026-07-09T17:03:32.067353+00:00","created_at":"2026-07-09T09:54:24.706+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Luna","short_name":"GPT-5.6 Luna","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-luna-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-luna","model_variant_permaslug":"openai/gpt-5.6-luna-20260709","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.6-luna","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.0000002","completion":"0.0000012","input_cache_read":"0.00000002","input_cache_write":"0.00000025","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000012"},{"sku_label":">272K","price":"0.0000018"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000002"},{"sku_label":">272K","price":"0.00000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000025"},{"sku_label":">272K","price":"0.0000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000012"},{"sku_label":">272K","price":"0.0000018"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000002"},{"sku_label":">272K","price":"0.00000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000025"},{"sku_label":">272K","price":"0.0000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.0000002","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.0000012","openai_responses:cache_write_tokens":"0.00000025","openai_responses:cached_prompt_tokens":"0.00000002","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"0.0000004","openai_responses:completion_tokens_high_context":"0.0000018","openai_responses:cache_write_tokens_high_context":"0.0000005","openai_responses:cached_prompt_tokens_high_context":"0.00000004"},"pricing_version_id":"baf3437a-6521-411a-b107-9eb5f8483250","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:14.913Z","status":-2}},{"slug":"openai/gpt-5.6-terra-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:55.757Z","created_at":"2026-07-09T09:54:21.715Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra Pro (batch)","short_name":"GPT-5.6 Terra Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a18c5dd5-5f04-4997-ae6f-1c8fc1225fe0","name":"OpenAI | openai/gpt-5.6-terra-pro-20260709:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.6-terra-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:55.757192+00:00","created_at":"2026-07-09T09:54:21.715+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra Pro","short_name":"GPT-5.6 Terra Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-terra-pro:batch","model_variant_permaslug":"openai/gpt-5.6-terra-pro-20260709:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-terra","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000006","input_cache_read":"0.0000001","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.000009","input_cache_read":"0.0000002"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-06"},{"sku_label":">272K","price":"2e-06"}]},{"kind":"token","sku_label":"Output Price","price":"6e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-06"},{"sku_label":">272K","price":"9e-06"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-06"},{"sku_label":">272K","price":"2e-06"}]},{"kind":"token","sku_label":"Output Price","price":"6e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-06"},{"sku_label":">272K","price":"9e-06"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1e-06","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"6e-06","openai_responses:cached_prompt_tokens":"1e-07","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"2e-06","openai_responses:completion_tokens_high_context":"9e-06","openai_responses:cached_prompt_tokens_high_context":"2e-07"},"pricing_version_id":"ec50d656-2a41-4698-9b65-a00b857cc18d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:14.969Z","status":0}},{"slug":"openai/gpt-5.6-terra-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:55.757Z","created_at":"2026-07-09T09:54:21.715Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra Pro","short_name":"GPT-5.6 Terra Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"977689ed-f4b0-42f4-8b88-6f9fe3bb3d93","name":"Azure | openai/gpt-5.6-terra-pro-20260709","context_length":1050000,"model":{"slug":"openai/gpt-5.6-terra-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:55.757192+00:00","created_at":"2026-07-09T09:54:21.715+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra Pro","short_name":"GPT-5.6 Terra Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-terra-pro","model_variant_permaslug":"openai/gpt-5.6-terra-pro-20260709","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.6-terra","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.000002","completion":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000012"},{"sku_label":">272K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000012"},{"sku_label":">272K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000002","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.000012","openai_responses:cache_write_tokens":"0.0000025","openai_responses:cached_prompt_tokens":"0.0000002","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"0.000004","openai_responses:completion_tokens_high_context":"0.000018","openai_responses:cache_write_tokens_high_context":"0.000005","openai_responses:cached_prompt_tokens_high_context":"0.0000004"},"pricing_version_id":"918dacc9-3603-4439-a25f-59bce0a97d22","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:12.156Z","status":0}},{"slug":"openai/gpt-5.6-terra","hf_slug":null,"updated_at":"2026-07-09T17:03:34.784Z","created_at":"2026-07-09T09:54:17.907Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra (batch)","short_name":"GPT-5.6 Terra (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a4e49d78-5c47-4e7e-b8ca-1e85ff06b0d9","name":"OpenAI | openai/gpt-5.6-terra-20260709:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.6-terra","hf_slug":null,"updated_at":"2026-07-09T17:03:34.784462+00:00","created_at":"2026-07-09T09:54:17.907+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra","short_name":"GPT-5.6 Terra","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-terra:batch","model_variant_permaslug":"openai/gpt-5.6-terra-20260709:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-terra","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000006","input_cache_read":"0.0000001","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.000009","input_cache_read":"0.0000002"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-06"},{"sku_label":">272K","price":"2e-06"}]},{"kind":"token","sku_label":"Output Price","price":"6e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-06"},{"sku_label":">272K","price":"9e-06"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-06"},{"sku_label":">272K","price":"2e-06"}]},{"kind":"token","sku_label":"Output Price","price":"6e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"6e-06"},{"sku_label":">272K","price":"9e-06"}]},{"kind":"token","sku_label":"Cache Read","price":"1e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1e-07"},{"sku_label":">272K","price":"2e-07"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1e-06","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"6e-06","openai_responses:cached_prompt_tokens":"1e-07","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"2e-06","openai_responses:completion_tokens_high_context":"9e-06","openai_responses:cached_prompt_tokens_high_context":"2e-07"},"pricing_version_id":"63b04dd7-8463-44ba-9725-9dbd0b4b42f6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:14.304Z","status":0}},{"slug":"openai/gpt-5.6-terra","hf_slug":null,"updated_at":"2026-07-09T17:03:34.784Z","created_at":"2026-07-09T09:54:17.907Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra","short_name":"GPT-5.6 Terra","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3cc89000-ae34-4dde-9c7d-5ce009c8af0b","name":"OpenAI | openai/gpt-5.6-terra-20260709","context_length":1050000,"model":{"slug":"openai/gpt-5.6-terra","hf_slug":null,"updated_at":"2026-07-09T17:03:34.784462+00:00","created_at":"2026-07-09T09:54:17.907+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Terra","short_name":"GPT-5.6 Terra","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-terra-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-terra","model_variant_permaslug":"openai/gpt-5.6-terra-20260709","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-terra","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_cache_write":"0.000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2e-06"},{"sku_label":">272K","price":"4e-06"}]},{"kind":"token","sku_label":"Output Price","price":"1.2e-05","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.2e-05"},{"sku_label":">272K","price":"1.8e-05"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2e-07"},{"sku_label":">272K","price":"4e-07"}]},{"kind":"token","sku_label":"Cache Write","price":"2.5e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.5e-06"},{"sku_label":">272K","price":"5e-06"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2e-06"},{"sku_label":">272K","price":"4e-06"}]},{"kind":"token","sku_label":"Output Price","price":"1.2e-05","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.2e-05"},{"sku_label":">272K","price":"1.8e-05"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-07","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2e-07"},{"sku_label":">272K","price":"4e-07"}]},{"kind":"token","sku_label":"Cache Write","price":"2.5e-06","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.5e-06"},{"sku_label":">272K","price":"5e-06"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"2e-06","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"1.2e-05","openai_responses:cache_write_tokens":"2.5e-06","openai_responses:cached_prompt_tokens":"2e-07","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"4e-06","openai_responses:completion_tokens_high_context":"1.8e-05","openai_responses:cache_write_tokens_high_context":"5e-06","openai_responses:cached_prompt_tokens_high_context":"4e-07"},"pricing_version_id":"2fc0f7e1-4138-4068-b61f-aa064a636ded","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:08.672Z","status":0}},{"slug":"openai/gpt-5.6-sol-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:54.353Z","created_at":"2026-07-09T09:54:14.664Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol Pro (batch)","short_name":"GPT-5.6 Sol Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"35e7ec32-49ee-4789-97ad-c6aa17680ccc","name":"OpenAI | openai/gpt-5.6-sol-pro-20260709:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.6-sol-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:54.353411+00:00","created_at":"2026-07-09T09:54:14.664+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol Pro","short_name":"GPT-5.6 Sol Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-sol-pro:batch","model_variant_permaslug":"openai/gpt-5.6-sol-pro-20260709:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-sol","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.0000001","input_cache_write":"0.00000125","web_search":"0.01","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.0000075","input_cache_read":"0.0000002","input_cache_write":"0.0000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000001"},{"sku_label":">272K","price":"0.000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000005"},{"sku_label":">272K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000001"},{"sku_label":">272K","price":"0.0000002"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000125"},{"sku_label":">272K","price":"0.0000025"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000001"},{"sku_label":">272K","price":"0.000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000005"},{"sku_label":">272K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000001"},{"sku_label":">272K","price":"0.0000002"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000125"},{"sku_label":">272K","price":"0.0000025"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000002","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.00001","openai_responses:cache_write_tokens":"0.0000025","openai_responses:cached_prompt_tokens":"0.0000002","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"0.000004","openai_responses:completion_tokens_high_context":"0.000015","openai_responses:cache_write_tokens_high_context":"0.000005","openai_responses:cached_prompt_tokens_high_context":"0.0000004"},"pricing_version_id":"d04ab6ec-a2c1-47bf-b625-0f1aef21342a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:13.729Z","status":0}},{"slug":"openai/gpt-5.6-sol-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:54.353Z","created_at":"2026-07-09T09:54:14.664Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol Pro","short_name":"GPT-5.6 Sol Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"24801a82-7216-49bb-89a6-5480320ae736","name":"OpenAI | openai/gpt-5.6-sol-pro-20260709","context_length":1050000,"model":{"slug":"openai/gpt-5.6-sol-pro","hf_slug":null,"updated_at":"2026-07-09T17:57:54.353411+00:00","created_at":"2026-07-09T09:54:14.664+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol Pro","short_name":"GPT-5.6 Sol Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-pro-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-sol-pro","model_variant_permaslug":"openai/gpt-5.6-sol-pro-20260709","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-sol","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00001"},{"sku_label":">272K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00001"},{"sku_label":">272K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000004","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.00002","openai_responses:cache_write_tokens":"0.000005","openai_responses:cached_prompt_tokens":"0.0000004","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"0.000008","openai_responses:completion_tokens_high_context":"0.00003","openai_responses:cache_write_tokens_high_context":"0.00001","openai_responses:cached_prompt_tokens_high_context":"0.0000008"},"pricing_version_id":"2b815b37-7ab5-4652-b85f-e9dafd0bda7b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:05.594Z","status":0}},{"slug":"openai/gpt-5.6-sol","hf_slug":null,"updated_at":"2026-07-09T17:03:37.014Z","created_at":"2026-07-09T09:54:10.415Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol (batch)","short_name":"GPT-5.6 Sol (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"e92a9dd7-2d27-46ce-aa29-aef883ba6db6","name":"OpenAI | openai/gpt-5.6-sol-20260709:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.6-sol","hf_slug":null,"updated_at":"2026-07-09T17:03:37.014274+00:00","created_at":"2026-07-09T09:54:10.415+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol","short_name":"GPT-5.6 Sol","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-sol:batch","model_variant_permaslug":"openai/gpt-5.6-sol-20260709:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-sol","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.0000001","input_cache_write":"0.00000125","web_search":"0.01","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.0000075","input_cache_read":"0.0000002","input_cache_write":"0.0000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000001"},{"sku_label":">272K","price":"0.000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000005"},{"sku_label":">272K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000001"},{"sku_label":">272K","price":"0.0000002"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000125"},{"sku_label":">272K","price":"0.0000025"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000001"},{"sku_label":">272K","price":"0.000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000005"},{"sku_label":">272K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000001"},{"sku_label":">272K","price":"0.0000002"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00000125"},{"sku_label":">272K","price":"0.0000025"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000002","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.00001","openai_responses:cache_write_tokens":"0.0000025","openai_responses:cached_prompt_tokens":"0.0000002","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"0.000004","openai_responses:completion_tokens_high_context":"0.000015","openai_responses:cache_write_tokens_high_context":"0.000005","openai_responses:cached_prompt_tokens_high_context":"0.0000004"},"pricing_version_id":"456937e2-a36b-44c3-8289-978f9d5ae2bf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-28T15:36:13.055Z","status":0}},{"slug":"openai/gpt-5.6-sol","hf_slug":null,"updated_at":"2026-07-09T17:03:37.014Z","created_at":"2026-07-09T09:54:10.415Z","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol","short_name":"GPT-5.6 Sol","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a54c5de0-89bf-4ad7-a212-cf977eed918a","name":"OpenAI | openai/gpt-5.6-sol-20260709","context_length":1050000,"model":{"slug":"openai/gpt-5.6-sol","hf_slug":null,"updated_at":"2026-07-09T17:03:37.014274+00:00","created_at":"2026-07-09T09:54:10.415+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.6 Sol","short_name":"GPT-5.6 Sol","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.6-sol-20260709","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.6-sol","model_variant_permaslug":"openai/gpt-5.6-sol-20260709","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-sol","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00001"},{"sku_label":">272K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00001"},{"sku_label":">272K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000004","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.00002","openai_responses:cache_write_tokens":"0.000005","openai_responses:cached_prompt_tokens":"0.0000004","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"0.000008","openai_responses:completion_tokens_high_context":"0.00003","openai_responses:cache_write_tokens_high_context":"0.00001","openai_responses:cached_prompt_tokens_high_context":"0.0000008"},"pricing_version_id":"18f0d69c-c23d-4deb-9254-75118a94371b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:02.541Z","status":0}},{"slug":"x-ai/grok-4.5","hf_slug":null,"updated_at":"2026-08-12T15:38:31.753Z","created_at":"2026-07-08T15:05:54.846Z","hf_updated_at":null,"name":"SpaceXAI: Grok 4.5","short_name":"Grok 4.5","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.5-20260708","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"78a73286-52c4-4d1d-9d13-c1870c25b143","name":"xAI | x-ai/grok-4.5-20260708","context_length":500000,"model":{"slug":"x-ai/grok-4.5","hf_slug":null,"updated_at":"2026-08-12T15:38:31.753033+00:00","created_at":"2026-07-08T15:05:54.846+00:00","hf_updated_at":null,"name":"SpaceXAI: Grok 4.5","short_name":"Grok 4.5","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.5-20260708","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"x-ai/grok-4.5","model_variant_permaslug":"x-ai/grok-4.5-20260708","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai/zdr","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI (ZDR)","provider_slug":"xai/zdr","provider_model_id":"grok-4.5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":["reasoning_effort"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000003","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.0000006"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-6"},{"sku_label":">200K","price":"4e-6"}]},{"kind":"token","sku_label":"Output Price","price":"6e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"6e-6"},{"sku_label":">200K","price":"12e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.3e-6"},{"sku_label":">200K","price":"0.6e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-6"},{"sku_label":">200K","price":"4e-6"}]},{"kind":"token","sku_label":"Output Price","price":"6e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"6e-6"},{"sku_label":">200K","price":"12e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.3e-6"},{"sku_label":">200K","price":"0.6e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"2e-6","xai_responses:x_search_calls":"0.005","xai_responses:web_search_calls":"0.005","xai_responses:completion_tokens":"6e-6","xai_responses:cached_prompt_tokens":"0.3e-6","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"4e-6","xai_responses:completion_tokens_high_context":"12e-6","xai_responses:usage_guidelines_violation_fee":"0.05","xai_responses:cached_prompt_tokens_high_context":"0.6e-6"},"pricing_version_id":"cd07e399-0eb0-4913-ab96-4c28e9a05516","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T19:25:19.704Z","status":0}},{"slug":"~x-ai/grok-latest","hf_slug":null,"updated_at":"2026-07-08T15:05:31.837Z","created_at":"2026-07-08T14:02:40.865Z","hf_updated_at":null,"name":"xAI: Grok Latest","short_name":"Grok Latest","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"This model always redirects to the latest Grok model from xAI.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~x-ai/grok-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~x-ai/grok-latest","name":"xAI | x-ai/grok-4.6-20260810","context_length":500000,"model":{"slug":"~x-ai/grok-latest","hf_slug":null,"updated_at":"2026-07-08T15:05:31.837Z","created_at":"2026-07-08T14:02:40.865Z","hf_updated_at":null,"name":"xAI: Grok Latest","short_name":"Grok Latest","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"This model always redirects to the latest Grok model from xAI.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~x-ai/grok-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~x-ai/grok-latest","model_variant_permaslug":"~x-ai/grok-latest","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai/zdr","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI (ZDR)","provider_slug":"xai/zdr","provider_model_id":"grok-4.6","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":["reasoning_effort"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.000001"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000005"},{"sku_label":">200K","price":"0.000001"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000005"},{"sku_label":">200K","price":"0.000001"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"0.000002","xai_responses:completion_tokens":"0.000006","xai_responses:cached_prompt_tokens":"0.0000005","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"0.000004","xai_responses:completion_tokens_high_context":"0.000012","xai_responses:cached_prompt_tokens_high_context":"0.000001"},"pricing_version_id":"cb585f4e-dbc3-4e10-82fa-82f45470c68a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-12T11:25:23.177Z","status":0}},{"slug":"aion-labs/aion-3.0-mini","hf_slug":null,"updated_at":"2026-07-07T19:17:03.625Z","created_at":"2026-07-07T16:51:36.409Z","hf_updated_at":null,"name":"AionLabs: Aion-3.0-Mini","short_name":"Aion-3.0-Mini","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-3.0-mini-20260707","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3","name":"AionLabs | aion-labs/aion-3.0-mini-20260707","context_length":131072,"model":{"slug":"aion-labs/aion-3.0-mini","hf_slug":null,"updated_at":"2026-07-07T19:17:03.625867+00:00","created_at":"2026-07-07T16:51:36.409278+00:00","hf_updated_at":null,"name":"AionLabs: Aion-3.0-Mini","short_name":"Aion-3.0-Mini","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-3.0-mini-20260707","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"aion-labs/aion-3.0-mini","model_variant_permaslug":"aion-labs/aion-3.0-mini-20260707","adapter_name":"OpenAIAdapter","provider_name":"AionLabs","provider_info":{"name":"AionLabs","displayName":"AionLabs","slug":"aion-labs","baseUrl":"https://api.aionlabs.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/","requiresUserIDs":false},"headquarters":"IL","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.aionlabs.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"AionLabs","provider_slug":"aion-labs","provider_model_id":"aion-labs/aion-3.0-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/"},"pricing":{"prompt":"0.0000007","completion":"0.0000014","input_cache_read":"0.00000018","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000007","openai:completion_tokens":"0.0000014","openai:cached_prompt_tokens":"0.00000018"},"pricing_version_id":"a0822a9b-7e7e-4a10-aa78-eb99cf8901b5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T16:51:46.359Z","status":0}},{"slug":"aion-labs/aion-3.0","hf_slug":null,"updated_at":"2026-07-07T19:17:06.600Z","created_at":"2026-07-07T16:51:35.786Z","hf_updated_at":null,"name":"AionLabs: Aion-3.0","short_name":"Aion-3.0","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-3.0-20260707","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8c8f827d-2bef-468a-8f9e-8e27b470de5e","name":"AionLabs | aion-labs/aion-3.0-20260707","context_length":131072,"model":{"slug":"aion-labs/aion-3.0","hf_slug":null,"updated_at":"2026-07-07T19:17:06.60086+00:00","created_at":"2026-07-07T16:51:35.786008+00:00","hf_updated_at":null,"name":"AionLabs: Aion-3.0","short_name":"Aion-3.0","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-3.0-20260707","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"aion-labs/aion-3.0","model_variant_permaslug":"aion-labs/aion-3.0-20260707","adapter_name":"OpenAIAdapter","provider_name":"AionLabs","provider_info":{"name":"AionLabs","displayName":"AionLabs","slug":"aion-labs","baseUrl":"https://api.aionlabs.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/","requiresUserIDs":false},"headquarters":"IL","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.aionlabs.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"AionLabs","provider_slug":"aion-labs","provider_model_id":"aion-labs/aion-3.0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/"},"pricing":{"prompt":"0.000003","completion":"0.000006","input_cache_read":"0.00000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000003","openai:completion_tokens":"0.000006","openai:cached_prompt_tokens":"0.00000075"},"pricing_version_id":"0a34d3ac-fa3a-4905-b56a-1cb27cca4467","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T16:51:45.840Z","status":0}},{"slug":"tencent/hy3","hf_slug":"tencent/Hy3","updated_at":"2026-07-20T17:07:53.472Z","created_at":"2026-07-06T13:20:48.963Z","hf_updated_at":null,"name":"Tencent: Hy3","short_name":"Hy3","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.\n\nTencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy3-20260706","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b57b0bfd-2bf0-47b6-9445-8263b3b0fa91","name":"Baidu | tencent/hy3-20260706","context_length":262144,"model":{"slug":"tencent/hy3","hf_slug":"tencent/Hy3","updated_at":"2026-07-20T17:07:53.472241+00:00","created_at":"2026-07-06T13:20:48.963648+00:00","hf_updated_at":null,"name":"Tencent: Hy3","short_name":"Hy3","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.\n\nTencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy3-20260706","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"tencent/hy3","model_variant_permaslug":"tencent/hy3-20260706","adapter_name":"BaiduAdapter","provider_name":"Baidu","provider_info":{"name":"Baidu","displayName":"Baidu Qianfan","slug":"baidu","baseUrl":"https://api.baiduqianfan.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"BaiduAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://intl.cloud.baidu.com/en&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Baidu Qianfan","provider_slug":"baidu/fp8","provider_model_id":"hy3","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en"},"pricing":{"prompt":"0.0000001254","completion":"0.0000005016","input_cache_read":"0.00000003135","discount":0.05,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001254","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005016","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003135","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001254","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005016","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003135","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000132","openai:completion_tokens":"0.000000528","openai:cached_prompt_tokens":"0.000000033"},"pricing_version_id":"1787cd75-7814-4271-95fa-bda4643591af","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":27960000,"created_at":"2026-08-04T15:42:59.811Z","status":0}},{"slug":"poolside/laguna-xs-2.1","hf_slug":"poolside/Laguna-XS-2.1","updated_at":"2026-07-31T12:24:29.676Z","created_at":"2026-07-02T14:27:09.627Z","hf_updated_at":null,"name":"Poolside: Laguna XS 2.1 (free)","short_name":"Laguna XS 2.1 (free)","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.\n\nLaguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the [OpenMDW-1.1 License](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).\n\nIf you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-xs-2.1-20260625","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"9c35bcfc-edcc-405a-acee-a0b991ec61cb","name":"Poolside | poolside/laguna-xs-2.1-20260625:free","context_length":262144,"model":{"slug":"poolside/laguna-xs-2.1","hf_slug":"poolside/Laguna-XS-2.1","updated_at":"2026-07-31T12:24:29.676191+00:00","created_at":"2026-07-02T14:27:09.627+00:00","hf_updated_at":null,"name":"Poolside: Laguna XS 2.1","short_name":"Laguna XS 2.1","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.\n\nLaguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the [OpenMDW-1.1 License](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).\n\nIf you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-xs-2.1-20260625","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"poolside/laguna-xs-2.1:free","model_variant_permaslug":"poolside/laguna-xs-2.1-20260625:free","adapter_name":"VLLMOpenAIAdapter","provider_name":"Poolside","provider_info":{"name":"Poolside","displayName":"Poolside","slug":"poolside","baseUrl":"https://inference.poolside.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://poolside.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Poolside","provider_slug":"poolside/fp8","provider_model_id":"poolside/laguna-xs-2.1","quantization":"fp8","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"excluded_parameters":["response_format","structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"13fb57ef-d952-4302-b2a0-6831036b60fa","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-25T18:16:07.639Z","status":0}},{"slug":"poolside/laguna-xs-2.1","hf_slug":"poolside/Laguna-XS-2.1","updated_at":"2026-07-31T12:24:29.676Z","created_at":"2026-07-02T14:27:09.627Z","hf_updated_at":null,"name":"Poolside: Laguna XS 2.1","short_name":"Laguna XS 2.1","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.\n\nLaguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the [OpenMDW-1.1 License](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).\n\nIf you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-xs-2.1-20260625","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"089ec178-f6dc-4450-aff5-46f68798ce97","name":"Poolside | poolside/laguna-xs-2.1-20260625","context_length":262144,"model":{"slug":"poolside/laguna-xs-2.1","hf_slug":"poolside/Laguna-XS-2.1","updated_at":"2026-07-31T12:24:29.676191+00:00","created_at":"2026-07-02T14:27:09.627+00:00","hf_updated_at":null,"name":"Poolside: Laguna XS 2.1","short_name":"Laguna XS 2.1","author":"poolside","author_display_name":"poolside","author_icon_uri":null,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.\n\nLaguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the [OpenMDW-1.1 License](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\n\nPlease report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).\n\nIf you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"poolside/laguna-xs-2.1-20260625","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"poolside/laguna-xs-2.1","model_variant_permaslug":"poolside/laguna-xs-2.1-20260625","adapter_name":"VLLMOpenAIAdapter","provider_name":"Poolside","provider_info":{"name":"Poolside","displayName":"Poolside","slug":"poolside","baseUrl":"https://inference.poolside.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://poolside.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Poolside","provider_slug":"poolside/fp8","provider_model_id":"poolside/laguna-xs-2.1:fast","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"excluded_parameters":["response_format","structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":90,"canPublish":false,"termsOfServiceURL":"http://poolside.ai/legal","privacyPolicyURL":"https://poolside.ai/legal/privacy"},"pricing":{"prompt":"0.00000006","completion":"0.00000012","input_cache_read":"0.00000003","discount":0.4,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000002","openai:cached_prompt_tokens":"0.00000005"},"pricing_version_id":"5e2c8f9c-9109-4f5c-b390-01bd43bd383a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":50,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-25T18:16:08.126Z","status":0}},{"slug":"anthropic/claude-sonnet-5","hf_slug":null,"updated_at":"2026-08-17T21:55:11.801Z","created_at":"2026-06-30T18:11:23.921Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 5 (batch)","short_name":"Claude Sonnet 5 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-sonnet-5-20260630","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","azure/global","anthropic","amazon-bedrock/us-east-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"57cc41a4-501a-4f28-91d5-5a04990946d7","name":"Anthropic | anthropic/claude-sonnet-5-20260630:batch","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-5","hf_slug":null,"updated_at":"2026-08-17T21:55:11.801992+00:00","created_at":"2026-06-30T18:11:23.921+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 5","short_name":"Claude Sonnet 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-sonnet-5-20260630","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","azure/global","anthropic","amazon-bedrock/us-east-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-5:batch","model_variant_permaslug":"anthropic/claude-sonnet-5-20260630:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-sonnet-5","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.000001","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"0.0000001","anthropic:completion_tokens":"0.000005","anthropic:cache_write_1h_tokens":"0.000002","anthropic:cache_write_5m_tokens":"0.00000125"},"pricing_version_id":"73d5dc03-d12d-4665-a63d-7a44f02af5c6","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-14T13:33:37.216Z","status":0}},{"slug":"anthropic/claude-sonnet-5","hf_slug":null,"updated_at":"2026-08-17T21:55:11.801Z","created_at":"2026-06-30T18:11:23.921Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 5","short_name":"Claude Sonnet 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-sonnet-5-20260630","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","azure/global","anthropic","amazon-bedrock/us-east-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"0a2a206f-95f6-4173-9475-fe65a9a36171","name":"Anthropic | anthropic/claude-sonnet-5-20260630","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-5","hf_slug":null,"updated_at":"2026-08-17T21:55:11.801992+00:00","created_at":"2026-06-30T18:11:23.921+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 5","short_name":"Claude Sonnet 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-sonnet-5-20260630","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","azure/global","anthropic","amazon-bedrock/us-east-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-5","model_variant_permaslug":"anthropic/claude-sonnet-5-20260630","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-sonnet-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"2e-6","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":".2e-6","anthropic:completion_tokens":"10e-6","anthropic:cache_write_1h_tokens":"4e-6","anthropic:cache_write_5m_tokens":"2.5e-6"},"pricing_version_id":"1efcb581-a9a3-4500-a466-f7e855f95d96","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-29T20:28:52.700Z","status":0}},{"slug":"google/gemini-3.1-flash-lite-image","hf_slug":null,"updated_at":"2026-06-30T16:40:40.384Z","created_at":"2026-06-30T16:33:45.963Z","hf_updated_at":null,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","short_name":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation in roughly 4 seconds — about 2.7× faster than Gemini 3.1 Flash Image — while keeping the character consistency, precise editing, and real-world knowledge of the Nano Banana family.\n\nA single drop-in API handles text-to-image, image editing, and multi-image composition. As a multimodal model it also returns text alongside images. Outputs are generated at 1K resolution across 14 aspect ratios and carry an invisible SynthID watermark so they can be identified as AI-generated.\n\nPositioned as the best balance of quality and speed in the Nano Banana 2 line, it lets you generate thousands of images at a fraction of the cost of heavier production models — ideal for prototyping, real-time apps, and visual workflows at scale.","model_version_group_id":null,"context_length":65536,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-image-20260630","supports_reasoning":true,"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-lite-image-20260630/7c76aa10-681d-4d0f-a5d5-9bc4c188b096/original-0.jpg","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-lite-image-20260630/7c76aa10-681d-4d0f-a5d5-9bc4c188b096/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-lite-image-20260630/7c76aa10-681d-4d0f-a5d5-9bc4c188b096/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-01T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"55b53628-1e94-4ee3-9494-2c04e7f2c43a","name":"Google AI Studio | google/gemini-3.1-flash-lite-image-20260630","context_length":65536,"model":{"slug":"google/gemini-3.1-flash-lite-image","hf_slug":null,"updated_at":"2026-06-30T16:40:40.384071+00:00","created_at":"2026-06-30T16:33:45.963885+00:00","hf_updated_at":null,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","short_name":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation in roughly 4 seconds — about 2.7× faster than Gemini 3.1 Flash Image — while keeping the character consistency, precise editing, and real-world knowledge of the Nano Banana family.\n\nA single drop-in API handles text-to-image, image editing, and multi-image composition. As a multimodal model it also returns text alongside images. Outputs are generated at 1K resolution across 14 aspect ratios and carry an invisible SynthID watermark so they can be identified as AI-generated.\n\nPositioned as the best balance of quality and speed in the Nano Banana 2 line, it lets you generate thousands of images at a fraction of the cost of heavier production models — ideal for prototyping, real-time apps, and visual workflows at scale.","model_version_group_id":null,"context_length":65536,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-image-20260630","supports_reasoning":true,"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-01T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-flash-lite-image","model_variant_permaslug":"google/gemini-3.1-flash-lite-image-20260630","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.1-flash-lite-image","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image_output":"0.00003","web_search":"0.014","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":"0.00000025","gemini:completion_tokens":"0.0000015","gemini:image_output_tokens":"0.00003"},"pricing_version_id":"5def3eb4-21a7-4a4c-bf9e-016803df15dd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":{"resolutions":["1K"],"aspect_ratios":["1:1","1:4","1:8","2:3","3:2","3:4","4:1","4:3","4:5","5:4","8:1","9:16","16:9","21:9"],"n":{"min":1,"max":1},"input_references":{"min":0,"max":14}},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["cachedContent"],"capacity_tpm":null,"created_at":"2026-06-30T16:33:53.377Z","status":0}},{"slug":"nex-agi/nex-n2-mini","hf_slug":"nex-agi/Nex-N2-Mini","updated_at":"2026-07-06T18:57:30.368Z","created_at":"2026-06-24T14:56:04.369Z","hf_updated_at":null,"name":"Nex AGI: Nex-N2-Mini","short_name":"Nex-N2-Mini","author":"nex-agi","author_display_name":"nex-agi","author_icon_uri":null,"description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use, deep research, and long-horizon agentic workflows, with a 262K-token context window and native reasoning support.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nex-agi/nex-n2-mini","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"14abef89-df95-4906-bb3f-df4ce3614212","name":"Nex AGI | nex-agi/nex-n2-mini","context_length":262144,"model":{"slug":"nex-agi/nex-n2-mini","hf_slug":"nex-agi/Nex-N2-Mini","updated_at":"2026-07-06T18:57:30.368092+00:00","created_at":"2026-06-24T14:56:04.369692+00:00","hf_updated_at":null,"name":"Nex AGI: Nex-N2-Mini","short_name":"Nex-N2-Mini","author":"nex-agi","author_display_name":"nex-agi","author_icon_uri":null,"description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use, deep research, and long-horizon agentic workflows, with a 262K-token context window and native reasoning support.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nex-agi/nex-n2-mini","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nex-agi/nex-n2-mini","model_variant_permaslug":"nex-agi/nex-n2-mini","adapter_name":"NexAGIAdapter","provider_name":"Nex AGI","provider_info":{"name":"Nex AGI","displayName":"Nex AGI","slug":"nex-agi","baseUrl":"https://api.nex-agi.cn/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"privacyPolicyURL":"https://api.nex-agi.cn/privacy-policy","requiresUserIDs":false},"headquarters":"CN","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"NexAGIAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nex.sii.edu.cn/en/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Nex AGI","provider_slug":"nex-agi","provider_model_id":"nex-agi/Nex-N2-Mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","top_p","top_k","temperature","max_tokens","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"privacyPolicyURL":"https://api.nex-agi.cn/privacy-policy"},"pricing":{"prompt":"0.000000025","completion":"0.0000001","input_cache_read":"0.0000000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000025","openai:completion_tokens":"0.0000001","openai:cached_prompt_tokens":"0.0000000025"},"pricing_version_id":"968d84fa-94a3-4cd0-8d9f-e62e1ce4ff20","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-24T14:56:14.142Z","status":0}},{"slug":"sakana/fugu-ultra","hf_slug":null,"updated_at":"2026-06-24T04:45:03.384Z","created_at":"2026-06-24T04:45:03.368Z","hf_updated_at":null,"name":"Sakana: Fugu Ultra","short_name":"Fugu Ultra","author":"sakana","author_display_name":"sakana","author_icon_uri":"https://sakana.ai","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself.\n\nFugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sakana/fugu-ultra-20260615","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","xhigh","max"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","xhigh","max"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"99a9a85f-3c29-4b33-a21c-e5becb008160","name":"Sakana AI | sakana/fugu-ultra-20260615","context_length":1000000,"model":{"slug":"sakana/fugu-ultra","hf_slug":null,"updated_at":"2026-06-24T04:45:03.384807+00:00","created_at":"2026-06-24T04:45:03.368+00:00","hf_updated_at":null,"name":"Sakana: Fugu Ultra","short_name":"Fugu Ultra","author":"sakana","author_display_name":"sakana","author_icon_uri":"https://sakana.ai","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself.\n\nFugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sakana/fugu-ultra-20260615","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","xhigh","max"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["high","xhigh","max"],"default_reasoning_effort":"xhigh","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"sakana/fugu-ultra","model_variant_permaslug":"sakana/fugu-ultra-20260615","adapter_name":"SakanaAIAdapter","provider_name":"Sakana AI","provider_info":{"name":"Sakana AI","displayName":"Sakana","slug":"sakana","baseUrl":"https://api.sakana.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://console.sakana.ai/terms-of-service","privacyPolicyURL":"https://console.sakana.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"SakanaAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://sakana.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Sakana","provider_slug":"sakana","provider_model_id":"fugu-ultra-20260615","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options"],"excluded_parameters":["response_format"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://console.sakana.ai/terms-of-service","privacyPolicyURL":"https://console.sakana.ai/privacy-policy"},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"5e-6"},{"sku_label":">272K","price":"10e-6"}]},{"kind":"token","sku_label":"Output Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"45e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.5e-6"},{"sku_label":">272K","price":"1e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"5e-6"},{"sku_label":">272K","price":"10e-6"}]},{"kind":"token","sku_label":"Output Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"45e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.5e-6"},{"sku_label":">272K","price":"1e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"5e-6","openai_responses:completion_tokens":"30e-6","openai_responses:cached_prompt_tokens":"0.5e-6","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"10e-6","openai_responses:completion_tokens_high_context":"45e-6","openai_responses:cached_prompt_tokens_high_context":"1e-6"},"pricing_version_id":"5e1e1503-0d3a-41bc-9123-b835a07ce628","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"reasoning_return_mechanism":"reasoning","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-24T03:24:29.696Z","status":0}},{"slug":"google/gemini-3.1-flash-image","hf_slug":null,"updated_at":"2026-06-18T04:02:13.051Z","created_at":"2026-06-18T03:41:05.617Z","hf_updated_at":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","short_name":"Nano Banana 2 (Gemini 3.1 Flash Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-image-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-image-20260528/eb1b93d2-f9c1-4650-92ba-2b4b1d080c20/original-0.jpg","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-image-20260528/eb1b93d2-f9c1-4650-92ba-2b4b1d080c20/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-image-20260528/eb1b93d2-f9c1-4650-92ba-2b4b1d080c20/thumb-0.webp","preview_audio":null,"author_flagship_modalities":["image"],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"275d7d39-ae50-4df3-8140-5dd69c3ab883","name":"Google | google/gemini-3.1-flash-image-20260528","context_length":131072,"model":{"slug":"google/gemini-3.1-flash-image","hf_slug":null,"updated_at":"2026-06-18T04:02:13.05147+00:00","created_at":"2026-06-18T03:41:05.617619+00:00","hf_updated_at":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","short_name":"Nano Banana 2 (Gemini 3.1 Flash Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-image-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-flash-image","model_variant_permaslug":"google/gemini-3.1-flash-image-20260528","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.1-flash-image","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.0000005","gemini:web_search_calls":"0.014","gemini:completion_tokens":"0.000003","gemini:image_output_tokens":"0.00006"},"pricing_version_id":"6238213d-aebe-4b5d-b85a-96fd7c05dcc7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":{"resolutions":["512","1K","2K","4K"],"aspect_ratios":["1:1","1:4","1:8","2:3","3:2","3:4","4:1","4:3","4:5","5:4","8:1","9:16","16:9","21:9"],"output_formats":null,"qualities":null,"backgrounds":null,"n":{"min":1,"max":1},"input_references":{"min":0,"max":14},"output_compression":null,"seed":null},"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":["cachedContent"],"capacity_tpm":null,"created_at":"2026-06-18T03:41:22.694Z","status":0}},{"slug":"google/gemini-3-pro-image","hf_slug":null,"updated_at":"2026-06-18T04:01:39.173Z","created_at":"2026-06-18T03:40:54.718Z","hf_updated_at":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","short_name":"Nano Banana Pro (Gemini 3 Pro Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-pro-image-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3-pro-image-20260528/10c0f842-826c-49e7-a00e-0eab9e11b14d/original-0.jpg","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3-pro-image-20260528/10c0f842-826c-49e7-a00e-0eab9e11b14d/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3-pro-image-20260528/10c0f842-826c-49e7-a00e-0eab9e11b14d/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"459bc165-dafa-4e03-9fd0-bdd22c19d516","name":"Google | google/gemini-3-pro-image-20260528","context_length":65536,"model":{"slug":"google/gemini-3-pro-image","hf_slug":null,"updated_at":"2026-06-18T04:01:39.173326+00:00","created_at":"2026-06-18T03:40:54.718018+00:00","hf_updated_at":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","short_name":"Nano Banana Pro (Gemini 3 Pro Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.","model_version_group_id":null,"context_length":65536,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-pro-image-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3-pro-image","model_variant_permaslug":"google/gemini-3-pro-image-20260528","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3-pro-image","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.000002","gemini:reasoning_tokens":"0.000012","gemini:web_search_calls":"0.014","gemini:cache_read_tokens":"0.0000002","gemini:completion_tokens":"0.000012","gemini:audio_input_tokens":"0.000002","gemini:image_input_tokens":"0.000002","gemini:image_output_tokens":"0.00012","gemini:cache_read_audio_tokens":"0.0000002","gemini:cache_write_storage_hours":"0.0000045"},"pricing_version_id":"39973585-32c8-4647-948b-1670da89fca9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":{"resolutions":["1K","2K"],"aspect_ratios":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"],"output_formats":null,"qualities":null,"backgrounds":null,"n":{"min":1,"max":1},"input_references":{"min":0,"max":14},"output_compression":null,"seed":null},"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":["cachedContent"],"capacity_tpm":null,"created_at":"2026-06-18T03:41:21.398Z","status":0}},{"slug":"cohere/north-mini-code","hf_slug":"CohereLabs/North-Mini-Code-1.0","updated_at":"2026-06-17T21:48:58.762Z","created_at":"2026-06-17T19:15:48.285Z","hf_updated_at":null,"name":"Cohere: North Mini Code (free)","short_name":"North Mini Code (free)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.\n\nIt offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/north-mini-code-20260617","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supported_reasoning_efforts":[],"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supported_reasoning_efforts":[],"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"d3a18412-b833-40de-bc07-c4ba9a1dea53","name":"Cohere | cohere/north-mini-code-20260617:free","context_length":256000,"model":{"slug":"cohere/north-mini-code","hf_slug":"CohereLabs/North-Mini-Code-1.0","updated_at":"2026-06-17T21:48:58.762553+00:00","created_at":"2026-06-17T19:15:48.285192+00:00","hf_updated_at":null,"name":"Cohere: North Mini Code","short_name":"North Mini Code","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.\n\nIt offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/north-mini-code-20260617","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supported_reasoning_efforts":[],"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supported_reasoning_efforts":[],"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"cohere/north-mini-code:free","model_variant_permaslug":"cohere/north-mini-code-20260617:free","adapter_name":"CohereV2Adapter","provider_name":"Cohere","provider_info":{"name":"Cohere","displayName":"Cohere","slug":"cohere","baseUrl":"https://api.cohere.com/v2","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"CohereV2Adapter","statusPageUrl":"https://status.cohere.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Cohere.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Cohere","provider_slug":"cohere","provider_model_id":"north-mini-code-1-0-xl","quantization":"unknown","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","tools","tool_choice"],"excluded_parameters":["structured_outputs","response_format"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0","openai:cached_prompt_tokens":"0"},"pricing_version_id":"debbb664-7fa7-403f-81d9-9b1d66360d64","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":15,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-17T19:15:55.040Z","status":0}},{"slug":"z-ai/glm-5.2","hf_slug":"zai-org/GLM-5.2","updated_at":"2026-06-18T11:28:43.458Z","created_at":"2026-06-16T17:45:30.803Z","hf_updated_at":null,"name":"Z.ai: GLM 5.2 (free)","short_name":"GLM 5.2 (free)","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\n\nReasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.2-20260616","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"036a9487-617f-45a2-b0e1-bc5e48a20284","name":"Decart | z-ai/glm-5.2-20260616:free","context_length":256000,"model":{"slug":"z-ai/glm-5.2","hf_slug":"zai-org/GLM-5.2","updated_at":"2026-06-18T11:28:43.458771+00:00","created_at":"2026-06-16T17:45:30.803+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5.2","short_name":"GLM 5.2","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\n\nReasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.2-20260616","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5.2:free","model_variant_permaslug":"z-ai/glm-5.2-20260616:free","adapter_name":"VLLMOpenAIAdapter","provider_name":"Decart","provider_info":{"name":"Decart","displayName":"Decart","slug":"decart","baseUrl":"https://api.cogito.decart.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cogito.decart.ai/legal/terms","privacyPolicyURL":"https://cogito.decart.ai/legal/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VLLMOpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://cogito.decart.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Decart","provider_slug":"decart/fp4","provider_model_id":"z-ai/glm-5.2-ultra-fast-free","quantization":"fp4","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":256000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cogito.decart.ai/legal/terms","privacyPolicyURL":"https://cogito.decart.ai/legal/privacy"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"877a74f4-0977-4434-a192-f9c254b8d282","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-16T20:56:33.318Z","status":0}},{"slug":"z-ai/glm-5.2","hf_slug":"zai-org/GLM-5.2","updated_at":"2026-06-18T11:28:43.458Z","created_at":"2026-06-16T17:45:30.803Z","hf_updated_at":null,"name":"Z.ai: GLM 5.2","short_name":"GLM 5.2","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\n\nReasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.2-20260616","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"515ff417-d0f5-4455-9f58-b5a82be6d842","name":"Baidu | z-ai/glm-5.2-20260616","context_length":1048576,"model":{"slug":"z-ai/glm-5.2","hf_slug":"zai-org/GLM-5.2","updated_at":"2026-06-18T11:28:43.458771+00:00","created_at":"2026-06-16T17:45:30.803+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5.2","short_name":"GLM 5.2","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\n\nReasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.2-20260616","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5.2","model_variant_permaslug":"z-ai/glm-5.2-20260616","adapter_name":"BaiduAdapter","provider_name":"Baidu","provider_info":{"name":"Baidu","displayName":"Baidu Qianfan","slug":"baidu","baseUrl":"https://api.baiduqianfan.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"BaiduAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://intl.cloud.baidu.com/en&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Baidu Qianfan","provider_slug":"baidu/fp8","provider_model_id":"glm-5.2","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en"},"pricing":{"prompt":"0.00000049","completion":"0.00000154","input_cache_read":"0.000000091","discount":0.65,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000049","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000154","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000091","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000049","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000154","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000091","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000014","openai:completion_tokens":"0.0000044","openai:cached_prompt_tokens":"0.00000026"},"pricing_version_id":"0e9d0c51-4559-4b43-ab6e-754f29bfb53f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":112300000,"created_at":"2026-06-18T12:20:54.242Z","status":0}},{"slug":"z-ai/glm-5.2","hf_slug":"zai-org/GLM-5.2","updated_at":"2026-06-18T11:28:43.458Z","created_at":"2026-06-16T17:45:30.803Z","hf_updated_at":null,"name":"Z.ai: GLM 5.2 (batch)","short_name":"GLM 5.2 (batch)","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\n\nReasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","model_version_group_id":null,"context_length":1048575,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.2-20260616","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"8c3b2c7b-440c-43fb-bea8-8d6ecc09edae","name":"Together | z-ai/glm-5.2-20260616:batch","context_length":1048575,"model":{"slug":"z-ai/glm-5.2","hf_slug":"zai-org/GLM-5.2","updated_at":"2026-06-18T11:28:43.458771+00:00","created_at":"2026-06-16T17:45:30.803+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5.2","short_name":"GLM 5.2","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\n\nReasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.2-20260616","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5.2:batch","model_variant_permaslug":"z-ai/glm-5.2-20260616:batch","adapter_name":"TogetherBatchAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherBatchAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"zai-org/GLM-5.2","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000014","openai:completion_tokens":"0.0000044","openai:cached_prompt_tokens":"0.00000026"},"pricing_version_id":"ff24202a-7b19-4573-b58c-b8eec487715c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-27T21:36:50.977Z","status":0}},{"slug":"openrouter/fusion","hf_slug":null,"updated_at":"2026-06-15T16:55:39.603Z","created_at":"2026-06-13T17:27:27.163Z","hf_updated_at":null,"name":"OpenRouter: Fusion","short_name":"Fusion","author":"openrouter","author_display_name":"OpenRouter","author_icon_uri":null,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a judge model synthesizes their responses into a structured analysis — consensus, contradictions, partial coverage, unique insights, and blind spots — and writes the final answer from it.\n\nBy default the panel is the `Quality` preset; switch to `Budget` for cheaper members, or override the panel and judge entirely with the fusion plugin's `analysis_models` and `model` fields. Reach for Fusion when a single model isn't enough — research, expert critique, or anywhere the cost of being wrong outweighs a few extra completions.\n\nBecause Fusion runs every panel member plus a judge call, your request is priced as the sum of those underlying completions rather than a single model. To see which models ran, visit [Activity](/activity).\n\nNote: Context limits are dependent on which models you select.\n\nLearn more in our [docs](/docs/guides/features/plugins/fusion). For another way to route, see the [Auto Router](/openrouter/auto).","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openrouter/fusion","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":null},{"slug":"moonshotai/kimi-k2.7-code","hf_slug":"moonshotai/Kimi-K2.7-Code","updated_at":"2026-06-13T13:58:56.538Z","created_at":"2026-06-12T12:12:41.358Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.7 Code","short_name":"Kimi K2.7 Code","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.7-code-20260612","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"7371d3a6-b4b2-4175-9efa-7f75319aa509","name":"Inceptron | moonshotai/kimi-k2.7-code-20260612","context_length":262144,"model":{"slug":"moonshotai/kimi-k2.7-code","hf_slug":"moonshotai/Kimi-K2.7-Code","updated_at":"2026-06-13T13:58:56.538067+00:00","created_at":"2026-06-12T12:12:41.358288+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.7 Code","short_name":"Kimi K2.7 Code","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.7-code-20260612","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2.7-code","model_variant_permaslug":"moonshotai/kimi-k2.7-code-20260612","adapter_name":"InceptronAdapter","provider_name":"Inceptron","provider_info":{"name":"Inceptron","displayName":"Inceptron","slug":"inceptron","baseUrl":"https://api.inceptron.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.inceptron.io/termsofservice","privacyPolicyURL":"https://www.inceptron.io/privacy","requiresUserIDs":false},"headquarters":"SE","datacenters":["FI"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"InceptronAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.inceptron.io&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Inceptron","provider_slug":"inceptron/int4","provider_model_id":"moonshotai/Kimi-K2.7-Code","quantization":"int4","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.inceptron.io/termsofservice","privacyPolicyURL":"https://www.inceptron.io/privacy"},"pricing":{"prompt":"0.00000067","completion":"0.0000034","input_cache_read":"0.00000019","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000067","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000034","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000019","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000067","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000034","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000019","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000067","openai:completion_tokens":"0.0000034","openai:cached_prompt_tokens":"0.00000019"},"pricing_version_id":"885c27ba-6238-411b-862b-4da28785e8ad","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-22T12:50:54.773Z","status":0}},{"slug":"moonshotai/kimi-k2.7-code","hf_slug":"moonshotai/Kimi-K2.7-Code","updated_at":"2026-06-13T13:58:56.538Z","created_at":"2026-06-12T12:12:41.358Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.7 Code (batch)","short_name":"Kimi K2.7 Code (batch)","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.7-code-20260612","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a68f2c24-36d7-4cab-8381-3b0e94e6f8bb","name":"Together | moonshotai/kimi-k2.7-code-20260612:batch","context_length":262144,"model":{"slug":"moonshotai/kimi-k2.7-code","hf_slug":"moonshotai/Kimi-K2.7-Code","updated_at":"2026-06-13T13:58:56.538067+00:00","created_at":"2026-06-12T12:12:41.358288+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.7 Code","short_name":"Kimi K2.7 Code","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.7-code-20260612","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2.7-code:batch","model_variant_permaslug":"moonshotai/kimi-k2.7-code-20260612:batch","adapter_name":"TogetherBatchAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherBatchAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"moonshotai/Kimi-K2.7-Code","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000019","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000019","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000095","openai:completion_tokens":"0.000004","openai:cached_prompt_tokens":"0.00000019"},"pricing_version_id":"e90eeb0c-65eb-4a14-8cdc-4bdef9fba8e7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-27T21:36:52.548Z","status":0}},{"slug":"~anthropic/claude-fable-latest","hf_slug":null,"updated_at":"2026-07-01T19:41:22.647Z","created_at":"2026-06-09T18:32:24.621Z","hf_updated_at":null,"name":"Anthropic: Claude Fable Latest","short_name":"Claude Fable Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Claude Fable family.","model_version_group_id":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. [Learn more](https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-fable-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/claude-on-aws","google-vertex/global","anthropic","azure","amazon-bedrock/us","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~anthropic/claude-fable-latest","name":"Amazon Bedrock | anthropic/claude-5-fable-20260609","context_length":1000000,"model":{"slug":"~anthropic/claude-fable-latest","hf_slug":null,"updated_at":"2026-07-01T19:41:22.647Z","created_at":"2026-06-09T18:32:24.621Z","hf_updated_at":null,"name":"Anthropic: Claude Fable Latest","short_name":"Claude Fable Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Claude Fable family.","model_version_group_id":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. [Learn more](https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-fable-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/claude-on-aws","google-vertex/global","anthropic","azure","amazon-bedrock/us","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~anthropic/claude-fable-latest","model_variant_permaslug":"~anthropic/claude-fable-latest","adapter_name":"InternalStreamAmazonBedrockInvokeAnthropicAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Amazon Bedrock","provider_slug":"amazon-bedrock","provider_model_id":"global.anthropic.claude-fable-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs","max_completion_tokens"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000020","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000020","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":"10e-6","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"1e-6","anthropic:completion_tokens":"50e-6","anthropic:cache_write_1h_tokens":"0.000020","anthropic:cache_write_5m_tokens":"12.5e-6"},"pricing_version_id":"b2f5daa9-f291-4df5-b4d7-a1d4eabea917","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":150,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-09T12:19:22.884Z","status":0}},{"slug":"anthropic/claude-fable-5","hf_slug":null,"updated_at":"2026-07-23T15:56:34.223Z","created_at":"2026-06-09T12:18:35.266Z","hf_updated_at":null,"name":"Anthropic: Claude Fable 5 (batch)","short_name":"Claude Fable 5 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","model_version_group_id":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. [Learn more](https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models)\n\nAzure, Google Vertex, and Amazon Bedrock endpoints are BYOK-only while we work on enabling public access.","promotion_message":null,"routing_error_message":"Claude Fable 5 is not available. Learn more: https://www.anthropic.com/news/fable-mythos-access","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-5-fable-20260609","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/claude-on-aws","google-vertex/global","anthropic","azure","amazon-bedrock/us","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"7e4185f2-5a38-48ae-805d-ff954a2aa881","name":"Anthropic | anthropic/claude-5-fable-20260609:batch","context_length":1000000,"model":{"slug":"anthropic/claude-fable-5","hf_slug":null,"updated_at":"2026-07-23T15:56:34.223067+00:00","created_at":"2026-06-09T12:18:35.26618+00:00","hf_updated_at":null,"name":"Anthropic: Claude Fable 5","short_name":"Claude Fable 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","model_version_group_id":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. [Learn more](https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models)\n\nAzure, Google Vertex, and Amazon Bedrock endpoints are BYOK-only while we work on enabling public access.","promotion_message":null,"routing_error_message":"Claude Fable 5 is not available. Learn more: https://www.anthropic.com/news/fable-mythos-access","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-5-fable-20260609","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/claude-on-aws","google-vertex/global","anthropic","azure","amazon-bedrock/us","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-fable-5:batch","model_variant_permaslug":"anthropic/claude-5-fable-20260609:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-fable-5","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000625","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000010","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000625","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000010","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.000005","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"5e-7","anthropic:completion_tokens":"0.000025","anthropic:cache_write_1h_tokens":"0.000010","anthropic:cache_write_5m_tokens":"0.00000625"},"pricing_version_id":"ae0bfb07-8f7d-43be-a633-0546fe4df0fd","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_web_fetch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:18:48.587Z","status":0}},{"slug":"anthropic/claude-fable-5","hf_slug":null,"updated_at":"2026-07-23T15:56:34.223Z","created_at":"2026-06-09T12:18:35.266Z","hf_updated_at":null,"name":"Anthropic: Claude Fable 5","short_name":"Claude Fable 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","model_version_group_id":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. [Learn more](https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models)\n\nAzure, Google Vertex, and Amazon Bedrock endpoints are BYOK-only while we work on enabling public access.","promotion_message":null,"routing_error_message":"Claude Fable 5 is not available. Learn more: https://www.anthropic.com/news/fable-mythos-access","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-5-fable-20260609","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/claude-on-aws","google-vertex/global","anthropic","azure","amazon-bedrock/us","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"52afa9b6-8499-4575-9932-f67190705711","name":"Amazon Bedrock | anthropic/claude-5-fable-20260609","context_length":1000000,"model":{"slug":"anthropic/claude-fable-5","hf_slug":null,"updated_at":"2026-07-23T15:56:34.223067+00:00","created_at":"2026-06-09T12:18:35.26618+00:00","hf_updated_at":null,"name":"Anthropic: Claude Fable 5","short_name":"Claude Fable 5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","model_version_group_id":"353b3db8-3c5a-49af-a3a8-fd0be9d36006","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. [Learn more](https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models)\n\nAzure, Google Vertex, and Amazon Bedrock endpoints are BYOK-only while we work on enabling public access.","promotion_message":null,"routing_error_message":"Claude Fable 5 is not available. Learn more: https://www.anthropic.com/news/fable-mythos-access","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-5-fable-20260609","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/claude-on-aws","google-vertex/global","anthropic","azure","amazon-bedrock/us","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-fable-5","model_variant_permaslug":"anthropic/claude-5-fable-20260609","adapter_name":"InternalStreamAmazonBedrockInvokeAnthropicAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Amazon Bedrock","provider_slug":"amazon-bedrock","provider_model_id":"global.anthropic.claude-fable-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000020","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000020","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":"10e-6","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"1e-6","anthropic:completion_tokens":"50e-6","anthropic:cache_write_1h_tokens":"0.000020","anthropic:cache_write_5m_tokens":"12.5e-6"},"pricing_version_id":"b2f5daa9-f291-4df5-b4d7-a1d4eabea917","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":150,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-09T12:19:22.884Z","status":0}},{"slug":"nex-agi/nex-n2-pro","hf_slug":"nex-agi/Nex-N2-Pro","updated_at":"2026-06-08T17:58:09.809Z","created_at":"2026-06-08T16:45:40.435Z","hf_updated_at":null,"name":"Nex AGI: Nex-N2-Pro","short_name":"Nex-N2-Pro","author":"nex-agi","author_display_name":"nex-agi","author_icon_uri":null,"description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces text output, and supports reasoning, function calling, and structured outputs. It is designed for coding, tool use, deep research, and long-horizon agentic workflows, unifying planning, code implementation, debugging, and iteration into a single execution loop.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nex-agi/nex-n2-pro","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"cd63e693-ab16-4d13-a92f-60c998be2ada","name":"Nex AGI | nex-agi/nex-n2-pro","context_length":262144,"model":{"slug":"nex-agi/nex-n2-pro","hf_slug":"nex-agi/Nex-N2-Pro","updated_at":"2026-06-08T17:58:09.809084+00:00","created_at":"2026-06-08T16:45:40.435244+00:00","hf_updated_at":null,"name":"Nex AGI: Nex-N2-Pro","short_name":"Nex-N2-Pro","author":"nex-agi","author_display_name":"nex-agi","author_icon_uri":null,"description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces text output, and supports reasoning, function calling, and structured outputs. It is designed for coding, tool use, deep research, and long-horizon agentic workflows, unifying planning, code implementation, debugging, and iteration into a single execution loop.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nex-agi/nex-n2-pro","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nex-agi/nex-n2-pro","model_variant_permaslug":"nex-agi/nex-n2-pro","adapter_name":"NexAGIAdapter","provider_name":"Nex AGI","provider_info":{"name":"Nex AGI","displayName":"Nex AGI","slug":"nex-agi","baseUrl":"https://api.nex-agi.cn/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"privacyPolicyURL":"https://api.nex-agi.cn/privacy-policy","requiresUserIDs":false},"headquarters":"CN","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"NexAGIAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nex.sii.edu.cn/en/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Nex AGI","provider_slug":"nex-agi/fp8","provider_model_id":"nex-agi/Nex-N2-Pro","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","top_p","top_k","temperature","max_tokens","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"privacyPolicyURL":"https://api.nex-agi.cn/privacy-policy"},"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.000000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000025","openai:completion_tokens":"0.000001","openai:cached_prompt_tokens":"0.000000025"},"pricing_version_id":"6b1ea2e8-4ae9-4186-ae2e-2a576ea434aa","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-08T16:47:37.088Z","status":0}},{"slug":"nvidia/nemotron-3.5-content-safety","hf_slug":"nvidia/Nemotron-3.5-Content-Safety","updated_at":"2026-06-04T14:19:12.864Z","created_at":"2026-06-04T14:04:24.276Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","short_name":"Nemotron 3.5 Content Safety (free)","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens.\n\nIt is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"Please do not upload any confidential information. You may upload images, which we and our service providers will use for the sole purpose of providing you with this demo experience. Your use is logged for security purposes and anonymous session data may be used to improve NVIDIA products and services, including network performance metrics, AI-generated outputs, and audio transcriptions. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By uploading the file, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3.5-content-safety-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"e1bc6262-4e47-42c0-9b9b-00236a52a01a","name":"Nvidia | nvidia/nemotron-3.5-content-safety-20260604:free","context_length":128000,"model":{"slug":"nvidia/nemotron-3.5-content-safety","hf_slug":"nvidia/Nemotron-3.5-Content-Safety","updated_at":"2026-06-04T14:19:12.864088+00:00","created_at":"2026-06-04T14:04:24.276954+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3.5 Content Safety","short_name":"Nemotron 3.5 Content Safety","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens.\n\nIt is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"Please do not upload any confidential information. You may upload images, which we and our service providers will use for the sole purpose of providing you with this demo experience. Your use is logged for security purposes and anonymous session data may be used to improve NVIDIA products and services, including network performance metrics, AI-generated outputs, and audio transcriptions. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By uploading the file, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3.5-content-safety-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3.5-content-safety:free","model_variant_permaslug":"nvidia/nemotron-3.5-content-safety-20260604:free","adapter_name":"NvidiaAdapter","provider_name":"Nvidia","provider_info":{"name":"Nvidia","displayName":"NVIDIA","slug":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"NvidiaAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.nvidia.com/en-us/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NVIDIA","provider_slug":"nvidia","provider_model_id":"nvidia/nemotron-3.5-content-safety","quantization":"unknown","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"dec1f6c0-33fd-40fe-b34c-77d9da0282a1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["chat_template_kwargs"],"capacity_tpm":null,"created_at":"2026-06-04T14:04:43.776Z","status":0}},{"slug":"nvidia/nemotron-3-ultra-550b-a55b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","updated_at":"2026-06-04T13:45:46.170Z","created_at":"2026-06-04T05:33:28.534Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Ultra (free)","short_name":"Nemotron 3 Ultra (free)","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\n\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"72416acd-887a-4940-9ccc-1f22d9e17dbc","name":"Nvidia | nvidia/nemotron-3-ultra-550b-a55b-20260604:free","context_length":1000000,"model":{"slug":"nvidia/nemotron-3-ultra-550b-a55b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","updated_at":"2026-06-04T13:45:46.170424+00:00","created_at":"2026-06-04T05:33:28.534306+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Ultra","short_name":"Nemotron 3 Ultra","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\n\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-ultra-550b-a55b:free","model_variant_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604:free","adapter_name":"NvidiaAdapter","provider_name":"Nvidia","provider_info":{"name":"Nvidia","displayName":"NVIDIA","slug":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"NvidiaAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.nvidia.com/en-us/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NVIDIA","provider_slug":"nvidia","provider_model_id":"private/nvidia/nemotron-3-ultra-550b-a55b","quantization":"unknown","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"7f169f05-a176-4ddc-a3ce-74fc98badc77","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["reasoning_budget","chat_template_kwargs"],"capacity_tpm":null,"created_at":"2026-06-04T05:33:35.709Z","status":0}},{"slug":"nvidia/nemotron-3-ultra-550b-a55b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","updated_at":"2026-06-04T13:45:46.170Z","created_at":"2026-06-04T05:33:28.534Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Ultra","short_name":"Nemotron 3 Ultra","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\n\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":512288,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"7d4f9061-1fd5-46d6-b439-e85b0b9fcd87","name":"DeepInfra | nvidia/nemotron-3-ultra-550b-a55b-20260604","context_length":262144,"model":{"slug":"nvidia/nemotron-3-ultra-550b-a55b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","updated_at":"2026-06-04T13:45:46.170424+00:00","created_at":"2026-06-04T05:33:28.534306+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Ultra","short_name":"Nemotron 3 Ultra","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\n\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-ultra-550b-a55b","model_variant_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000005","completion":"0.0000022","input_cache_read":"0.0000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000005","openai:completion_tokens":"0.0000022","openai:cached_prompt_tokens":"0.0000001"},"pricing_version_id":"37c6599e-769f-4110-a2de-f1ceeec0f75c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-04T15:12:31.621Z","status":0}},{"slug":"nvidia/nemotron-3-ultra-550b-a55b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","updated_at":"2026-06-04T13:45:46.170Z","created_at":"2026-06-04T05:33:28.534Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Ultra (batch)","short_name":"Nemotron 3 Ultra (batch)","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\n\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":512288,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"cf597c66-b18d-43e7-be0f-77415cc08b22","name":"Together | nvidia/nemotron-3-ultra-550b-a55b-20260604:batch","context_length":512288,"model":{"slug":"nvidia/nemotron-3-ultra-550b-a55b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","updated_at":"2026-06-04T13:45:46.170424+00:00","created_at":"2026-06-04T05:33:28.534306+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Ultra","short_name":"Nemotron 3 Ultra","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\n\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["medium","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-ultra-550b-a55b:batch","model_variant_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604:batch","adapter_name":"TogetherBatchAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherBatchAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"nvidia/nemotron-3-ultra-550b-a55b","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tool_choice","tools","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000036","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000036","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000006","openai:completion_tokens":"0.0000036","openai:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"1cf690cd-cd28-4b39-888a-f05453d9f23f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-27T21:36:51.822Z","status":0}},{"slug":"qwen/qwen3.7-plus","hf_slug":null,"updated_at":"2026-06-03T13:07:32.544Z","created_at":"2026-06-03T13:03:03.046Z","hf_updated_at":null,"name":"Qwen: Qwen3.7 Plus","short_name":"Qwen3.7 Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.7-plus-20260602","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b77fd6ef-e2e0-4e92-96e1-8ffbf62d9792","name":"Alibaba | qwen/qwen3.7-plus-20260602","context_length":1000000,"model":{"slug":"qwen/qwen3.7-plus","hf_slug":null,"updated_at":"2026-06-03T13:07:32.544704+00:00","created_at":"2026-06-03T13:03:03.046422+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.7 Plus","short_name":"Qwen3.7 Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.7-plus-20260602","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.7-plus","model_variant_permaslug":"qwen/qwen3.7-plus-20260602","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.7-plus","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000032","completion":"0.00000128","input_cache_read":"0.000000064","input_cache_write":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000096","completion":"0.00000384","input_cache_read":"0.000000192","input_cache_write":"0.0000012"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000032","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000032"},{"sku_label":">256K","price":"0.00000096"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000128","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000128"},{"sku_label":">256K","price":"0.00000384"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000064","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000064"},{"sku_label":">256K","price":"0.000000192"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000004"},{"sku_label":">256K","price":"0.0000012"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000032","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000032"},{"sku_label":">256K","price":"0.000000096"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000032","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000032"},{"sku_label":">256K","price":"0.00000096"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000128","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000128"},{"sku_label":">256K","price":"0.00000384"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000064","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000064"},{"sku_label":">256K","price":"0.000000192"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000004"},{"sku_label":">256K","price":"0.0000012"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000032","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000032"},{"sku_label":">256K","price":"0.000000096"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000032","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.00000128","alibaba:prompt_tokens_tier2":"0.00000096","alibaba:cached_prompt_tokens":"0.000000064","alibaba:cache_creation_tokens":"0.0000004","alibaba:completion_tokens_tier2":"0.00000384","alibaba:cached_prompt_tokens_tier2":"0.000000192","alibaba:cache_creation_tokens_tier2":"0.0000012","alibaba:explicit_cached_prompt_tokens":"0.000000032","alibaba:explicit_cached_prompt_tokens_tier2":"0.000000096"},"pricing_version_id":"2f607790-36ac-424a-a7fa-bd7326dccd42","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-03T13:04:14.356Z","status":0}},{"slug":"minimax/minimax-m3","hf_slug":"MiniMaxAI/Minimax-M3","updated_at":"2026-06-15T15:00:03.787Z","created_at":"2026-05-31T16:36:14.509Z","hf_updated_at":null,"name":"MiniMax: MiniMax M3","short_name":"MiniMax M3","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\n\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m3-20260531","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b4c27216-5aed-4eac-ac2e-e3109cc778e7","name":"CoreWeave | minimax/minimax-m3-20260531","context_length":262144,"model":{"slug":"minimax/minimax-m3","hf_slug":"MiniMaxAI/Minimax-M3","updated_at":"2026-06-15T15:00:03.787178+00:00","created_at":"2026-05-31T16:36:14.509973+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M3","short_name":"MiniMax M3","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\n\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m3-20260531","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m3","model_variant_permaslug":"minimax/minimax-m3-20260531","adapter_name":"WandbAdapter","provider_name":"CoreWeave","provider_info":{"name":"CoreWeave","displayName":"CoreWeave","slug":"coreweave","baseUrl":"https://api.inference.wandb.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"WandbAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/CoreWeave.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"CoreWeave","provider_slug":"coreweave/fp4","provider_model_id":"MiniMaxAI/MiniMax-M3","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy"},"pricing":{"prompt":"0.00000023","completion":"0.00000096","input_cache_read":"0.00000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000023","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000096","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000023","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000096","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000023","openai:completion_tokens":"0.00000096","openai:cached_prompt_tokens":"0.00000005"},"pricing_version_id":"216e82b8-25a2-44cb-aa85-7a8805b868fd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-24T16:46:48.095Z","status":0}},{"slug":"minimax/minimax-m3","hf_slug":"MiniMaxAI/Minimax-M3","updated_at":"2026-06-15T15:00:03.787Z","created_at":"2026-05-31T16:36:14.509Z","hf_updated_at":null,"name":"MiniMax: MiniMax M3 (batch)","short_name":"MiniMax M3 (batch)","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\n\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution. ","model_version_group_id":null,"context_length":524288,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m3-20260531","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"f9fca75b-49e6-4ec7-b425-8611563d56d2","name":"Together | minimax/minimax-m3-20260531:batch","context_length":524288,"model":{"slug":"minimax/minimax-m3","hf_slug":"MiniMaxAI/Minimax-M3","updated_at":"2026-06-15T15:00:03.787178+00:00","created_at":"2026-05-31T16:36:14.509973+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M3","short_name":"MiniMax M3","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\n\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m3-20260531","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m3:batch","model_variant_permaslug":"minimax/minimax-m3-20260531:batch","adapter_name":"TogetherBatchAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherBatchAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"MiniMaxAI/MiniMax-M3","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000012","openai:cached_prompt_tokens":"0.00000006"},"pricing_version_id":"2ec171c4-011e-4a01-bad9-4947089f5edf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-27T15:01:26.074Z","status":0}},{"slug":"stepfun/step-3.7-flash","hf_slug":"stepfun-ai/Step-3.7-Flash","updated_at":"2026-06-12T16:33:16.030Z","created_at":"2026-05-28T16:17:49.000Z","hf_updated_at":null,"name":"StepFun: Step 3.7 Flash","short_name":"Step 3.7 Flash","author":"stepfun","author_display_name":"stepfun","author_icon_uri":null,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.\n\nDesigned for coding, agentic workflows, structured outputs, and long-context productivity tasks.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"stepfun/step-3.7-flash-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"1e380b07-8052-4bd4-bd89-f20790fb0996","name":"StepFun | stepfun/step-3.7-flash-20260528","context_length":256000,"model":{"slug":"stepfun/step-3.7-flash","hf_slug":"stepfun-ai/Step-3.7-Flash","updated_at":"2026-06-12T16:33:16.030679+00:00","created_at":"2026-05-28T16:17:49.000506+00:00","hf_updated_at":null,"name":"StepFun: Step 3.7 Flash","short_name":"Step 3.7 Flash","author":"stepfun","author_display_name":"stepfun","author_icon_uri":null,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.\n\nDesigned for coding, agentic workflows, structured outputs, and long-context productivity tasks.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"stepfun/step-3.7-flash-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"stepfun/step-3.7-flash","model_variant_permaslug":"stepfun/step-3.7-flash-20260528","adapter_name":"StepFunAdapter","provider_name":"StepFun","provider_info":{"name":"StepFun","displayName":"StepFun","slug":"stepfun","baseUrl":"https://api.stepfun.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"StepFunAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://platform.stepfun.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"StepFun","provider_slug":"stepfun/fp8","provider_model_id":"step-3.7-flash","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":256000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","top_p","stop","frequency_penalty","logprobs","top_logprobs","response_format","structured_outputs","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false},"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000020","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000115","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000020","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000115","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000020","openai:completion_tokens":"0.00000115","openai:cached_prompt_tokens":"0.00000004"},"pricing_version_id":"e614667a-918f-48e4-81bc-7e8fc7230282","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-28T16:17:54.234Z","status":0}},{"slug":"anthropic/claude-opus-4.8-fast","hf_slug":null,"updated_at":"2026-07-23T16:02:41.108Z","created_at":"2026-05-27T20:28:23.711Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.8 (Fast)","short_name":"Claude Opus 4.8 (Fast)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.8-opus-fast-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["anthropic"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"07b9c653-6817-4555-9013-1039f33e17e8","name":"Anthropic | anthropic/claude-4.8-opus-fast-20260528","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.8-fast","hf_slug":null,"updated_at":"2026-07-23T16:02:41.108149+00:00","created_at":"2026-05-27T20:28:23.711152+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.8 (Fast)","short_name":"Claude Opus 4.8 (Fast)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.8-opus-fast-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["anthropic"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.8-fast","model_variant_permaslug":"anthropic/claude-4.8-opus-fast-20260528","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-8","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"20e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"12.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"20e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"10e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"1e-6","anthropic:completion_tokens":"50e-6","anthropic:cache_write_1h_tokens":"20e-6","anthropic:cache_write_5m_tokens":"12.5e-6"},"pricing_version_id":"4f84efe0-60bb-469e-9f7c-a5180d2b2eca","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-27T20:28:33.145Z","status":0}},{"slug":"anthropic/claude-opus-4.8","hf_slug":null,"updated_at":"2026-08-18T00:46:21.385Z","created_at":"2026-05-27T18:04:51.937Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.8 (batch)","short_name":"Claude Opus 4.8 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.8-opus-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/us","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a3359b46-c907-4df2-9eb7-09b892b3ad7a","name":"Anthropic | anthropic/claude-4.8-opus-20260528:batch","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.8","hf_slug":null,"updated_at":"2026-08-18T00:46:21.385811+00:00","created_at":"2026-05-27T18:04:51.937403+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.8","short_name":"Claude Opus 4.8","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.8-opus-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/us","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.8:batch","model_variant_permaslug":"anthropic/claude-4.8-opus-20260528:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-8","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000025","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"2.5e-7","anthropic:completion_tokens":"0.0000125","anthropic:cache_write_1h_tokens":"0.000005","anthropic:cache_write_5m_tokens":"0.000003125"},"pricing_version_id":"6b404447-1c94-45b2-98f2-d40b433b8d49","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_web_fetch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:09:32.184Z","status":0}},{"slug":"anthropic/claude-opus-4.8","hf_slug":null,"updated_at":"2026-08-18T00:46:21.385Z","created_at":"2026-05-27T18:04:51.937Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.8","short_name":"Claude Opus 4.8","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.8-opus-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/us","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"37ca59bb-cb63-4806-a46e-7ad51de3ec2f","name":"Google | anthropic/claude-4.8-opus-20260528","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.8","hf_slug":null,"updated_at":"2026-08-18T00:46:21.385811+00:00","created_at":"2026-05-27T18:04:51.937403+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.8","short_name":"Claude Opus 4.8","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.8-opus-20260528","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/us","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.8","model_variant_permaslug":"anthropic/claude-4.8-opus-20260528","adapter_name":"InternalStreamGoogleVertexAnthropicAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"claude-opus-4-8","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":"5e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":".5e-6","anthropic:completion_tokens":"25e-6","anthropic:cache_write_1h_tokens":"10e-6","anthropic:cache_write_5m_tokens":"6.25e-6"},"pricing_version_id":"4dbd4f48-523b-4b31-8e24-7a9740111768","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-27T18:05:11.020Z","status":0}},{"slug":"qwen/qwen3.7-max","hf_slug":null,"updated_at":"2026-05-21T15:32:36.118Z","created_at":"2026-05-21T15:21:01.891Z","hf_updated_at":null,"name":"Qwen: Qwen3.7 Max","short_name":"Qwen3.7 Max","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.7-max-20260520","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"6d30fdc6-f2a7-4bdf-b6ba-32353496d723","name":"Alibaba | qwen/qwen3.7-max-20260520","context_length":1000000,"model":{"slug":"qwen/qwen3.7-max","hf_slug":null,"updated_at":"2026-05-21T15:32:36.11802+00:00","created_at":"2026-05-21T15:21:01.89103+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.7 Max","short_name":"Qwen3.7 Max","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.7-max-20260520","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.7-max","model_variant_permaslug":"qwen/qwen3.7-max-20260520","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.7-max","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000001475","completion":"0.000004425","input_cache_read":"0.000000295","input_cache_write":"0.00000184375","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001475","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004425","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000295","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000184375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000001475","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001475","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004425","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000295","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000184375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000001475","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000001475","alibaba:completion_tokens":"0.000004425","alibaba:cached_prompt_tokens":"0.000000295","alibaba:cache_creation_tokens":"0.00000184375","alibaba:explicit_cached_prompt_tokens":"0.0000001475"},"pricing_version_id":"4d5bd9fd-bdb8-4f90-9283-42b877d484a5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-21T15:21:02.024Z","status":0}},{"slug":"x-ai/grok-build-0.1","hf_slug":null,"updated_at":"2026-08-04T17:55:02.494Z","created_at":"2026-05-20T17:28:43.274Z","hf_updated_at":null,"name":"SpaceXAI: Grok Build 0.1","short_name":"Grok Build 0.1","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers SpaceXAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-build-0.1-20260520","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"2d3cdd47-cfc2-4372-96bb-82980f6a032d","name":"xAI | x-ai/grok-build-0.1-20260520","context_length":256000,"model":{"slug":"x-ai/grok-build-0.1","hf_slug":null,"updated_at":"2026-08-04T17:55:02.494177+00:00","created_at":"2026-05-20T17:28:43.274+00:00","hf_updated_at":null,"name":"SpaceXAI: Grok Build 0.1","short_name":"Grok Build 0.1","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers SpaceXAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-build-0.1-20260520","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"x-ai/grok-build-0.1","model_variant_permaslug":"x-ai/grok-build-0.1-20260520","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI","provider_slug":"xai","provider_model_id":"grok-build-0.1","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":["reasoning_effort"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000002","input_cache_read":"0.0000002","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000004","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001"},{"sku_label":">200K","price":"2e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"4e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":"0.4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001"},{"sku_label":">200K","price":"2e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"4e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":"0.4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"0.000001","xai_responses:completion_tokens":"0.000002","xai_responses:cached_prompt_tokens":"0.0000002","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"2e-6","xai_responses:completion_tokens_high_context":"4e-6","xai_responses:cached_prompt_tokens_high_context":"0.4e-6"},"pricing_version_id":"81a37e48-f55c-4f5c-ab80-531a396beb96","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T12:18:34.092Z","status":0}},{"slug":"google/gemini-3.5-flash","hf_slug":null,"updated_at":"2026-05-19T18:53:37.316Z","created_at":"2026-05-19T12:30:00.426Z","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash (batch)","short_name":"Gemini 3.5 Flash (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\n\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-20260519","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"50c771c0-4130-4692-ae67-799703c8b22a","name":"Google | google/gemini-3.5-flash-20260519:batch","context_length":1048576,"model":{"slug":"google/gemini-3.5-flash","hf_slug":null,"updated_at":"2026-05-19T18:53:37.316706+00:00","created_at":"2026-05-19T12:30:00.426471+00:00","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash","short_name":"Gemini 3.5 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\n\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-20260519","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.5-flash:batch","model_variant_permaslug":"google/gemini-3.5-flash-20260519:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.5-flash","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075","audio":"0.0000015","input_audio_cache":"0.00000015","input_cache_read":"0.000000075","web_search":"0.014","internal_reasoning":"0.0000045","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":7.5e-7,"gemini:reasoning_tokens":0.0000045,"gemini:web_search_calls":"0.014","gemini:cache_read_tokens":7.5e-8,"gemini:completion_tokens":0.0000045,"gemini:text_input_tokens":7.5e-7,"gemini:audio_input_tokens":0.0000015,"gemini:image_input_tokens":7.5e-7,"gemini:video_input_tokens":7.5e-7,"gemini:cache_read_text_tokens":7.5e-8,"gemini:cache_read_audio_tokens":1.5e-7,"gemini:cache_read_image_tokens":7.5e-8,"gemini:cache_read_video_tokens":7.5e-8,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"6fe9ace7-1c7a-4295-bbc8-f6ee2c175096","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:12:03.699Z","status":0}},{"slug":"google/gemini-3.5-flash","hf_slug":null,"updated_at":"2026-05-19T18:53:37.316Z","created_at":"2026-05-19T12:30:00.426Z","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash","short_name":"Gemini 3.5 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\n\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-20260519","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"bd50061c-e1d8-469e-96b1-d322e77378f8","name":"Google AI Studio | google/gemini-3.5-flash-20260519","context_length":1048576,"model":{"slug":"google/gemini-3.5-flash","hf_slug":null,"updated_at":"2026-05-19T18:53:37.316706+00:00","created_at":"2026-05-19T12:30:00.426471+00:00","hf_updated_at":null,"name":"Google: Gemini 3.5 Flash","short_name":"Gemini 3.5 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\n\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.5-flash-20260519","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.5-flash","model_variant_permaslug":"google/gemini-3.5-flash-20260519","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.5-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","audio":"0.000003","input_audio_cache":"0.0000003","input_cache_read":"0.00000015","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.000009","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"9e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"9e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"1.5e-6","gemini:reasoning_tokens":"9e-6","gemini:cache_read_tokens":"0.15e-6","gemini:completion_tokens":"9e-6","gemini:text_input_tokens":"1.5e-6","gemini:audio_input_tokens":"3e-6","gemini:image_input_tokens":"1.5e-6","gemini:video_input_tokens":"1.5e-6","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.15e-6","gemini:cache_read_audio_tokens":"0.3e-6","gemini:cache_read_image_tokens":"0.15e-6","gemini:cache_read_video_tokens":"0.15e-6","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"1e-6","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"709b817c-5dd4-4d9c-9fe4-18febbe71d38","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":450,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-19T12:34:59.368Z","status":0}},{"slug":"anthropic/claude-opus-4.7-fast","hf_slug":null,"updated_at":"2026-07-23T15:52:41.749Z","created_at":"2026-05-12T19:10:11.422Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.7 (Fast)","short_name":"Claude Opus 4.7 (Fast)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.7-opus-fast-20260512","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["anthropic"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a5353e36-c5f8-42fa-8bcf-ecee9eebd2b7","name":"Anthropic | anthropic/claude-4.7-opus-fast-20260512","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.7-fast","hf_slug":null,"updated_at":"2026-07-23T15:52:41.749749+00:00","created_at":"2026-05-12T19:10:11.422+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.7 (Fast)","short_name":"Claude Opus 4.7 (Fast)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.7-opus-fast-20260512","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["anthropic"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.7-fast","model_variant_permaslug":"anthropic/claude-4.7-opus-fast-20260512","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-7","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00003","completion":"0.00015","input_cache_read":"0.000003","input_cache_write":"0.0000375","input_cache_write_1h":"0.00006","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"150e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"37.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"60e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"150e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"37.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"60e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:web_search":"0.01","anthropic:input_tokens":"0.00003","anthropic:output_tokens":"0.00015","anthropic:prompt_tokens":"30e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"3e-6","anthropic:completion_tokens":"150e-6","anthropic:cache_write_1h_tokens":"60e-6","anthropic:cache_write_5m_tokens":"37.5e-6","anthropic:cache_read_input_tokens":"0.000003","anthropic:cache_creation_input_tokens":"0.0000375"},"pricing_version_id":"b60d7a7e-ed1a-4174-af91-63039b3490d5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-11T23:30:00.954Z","status":0}},{"slug":"perceptron/perceptron-mk1","hf_slug":null,"updated_at":"2026-05-12T15:12:35.375Z","created_at":"2026-05-12T14:43:49.920Z","hf_updated_at":null,"name":"Perceptron: Perceptron Mk1","short_name":"Perceptron Mk1","author":"perceptron","author_display_name":"perceptron","author_icon_uri":null,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation.\n\nReasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the `annotation_format` parameter (pass `\"point\"`, `\"box\"`, or `\"polygon\"` for spatial localization on images, or `\"clip\"` (start/end timestamps) for temporal segments in video). Without `annotation_format`, the model returns natural-language text only.","model_version_group_id":null,"context_length":32768,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perceptron/perceptron-mk1-20260512","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"92521bd2-ad85-4d32-bc48-34528189a0de","name":"Perceptron | perceptron/perceptron-mk1-20260512","context_length":32768,"model":{"slug":"perceptron/perceptron-mk1","hf_slug":null,"updated_at":"2026-05-12T15:12:35.375088+00:00","created_at":"2026-05-12T14:43:49.92+00:00","hf_updated_at":null,"name":"Perceptron: Perceptron Mk1","short_name":"Perceptron Mk1","author":"perceptron","author_display_name":"perceptron","author_icon_uri":null,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation.\n\nReasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the `annotation_format` parameter (pass `\"point\"`, `\"box\"`, or `\"polygon\"` for spatial localization on images, or `\"clip\"` (start/end timestamps) for temporal segments in video). Without `annotation_format`, the model returns natural-language text only.","model_version_group_id":null,"context_length":32768,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perceptron/perceptron-mk1-20260512","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"perceptron/perceptron-mk1","model_variant_permaslug":"perceptron/perceptron-mk1-20260512","adapter_name":"PerceptronAdapter","provider_name":"Perceptron","provider_info":{"name":"Perceptron","displayName":"Perceptron","slug":"perceptron","baseUrl":"https://api.perceptron.inc/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perceptron.inc/terms-of-use","privacyPolicyURL":"https://www.perceptron.inc/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"PerceptronAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.perceptron.inc&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Perceptron","provider_slug":"perceptron","provider_model_id":"perceptron-mk1","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perceptron.inc/terms-of-use","privacyPolicyURL":"https://www.perceptron.inc/privacy-policy"},"pricing":{"prompt":"0.00000015","completion":"0.0000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000015","openai:completion_tokens":"0.0000015"},"pricing_version_id":"917cebf9-78bc-443c-b078-7df54e2ce7cd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-05T20:04:56.075Z","status":0}},{"slug":"google/gemini-3.1-flash-lite","hf_slug":null,"updated_at":"2026-05-07T16:01:49.211Z","created_at":"2026-05-07T15:47:08.228Z","hf_updated_at":null,"name":"Google: Gemini 3.1 Flash Lite (batch)","short_name":"Gemini 3.1 Flash Lite (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\n\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-20260507","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"d7f2978b-4764-4477-a660-bbf8b355cfca","name":"Google | google/gemini-3.1-flash-lite-20260507:batch","context_length":1048576,"model":{"slug":"google/gemini-3.1-flash-lite","hf_slug":null,"updated_at":"2026-05-07T16:01:49.211829+00:00","created_at":"2026-05-07T15:47:08.228084+00:00","hf_updated_at":null,"name":"Google: Gemini 3.1 Flash Lite","short_name":"Gemini 3.1 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\n\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-20260507","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-flash-lite:batch","model_variant_permaslug":"google/gemini-3.1-flash-lite-20260507:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.1-flash-lite","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","audio":"0.00000025","input_audio_cache":"0.000000025","input_cache_read":"0.0000000125","web_search":"0.014","internal_reasoning":"0.00000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"2.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"2.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":1.25e-7,"gemini:reasoning_tokens":7.5e-7,"gemini:web_search_calls":"0.014","gemini:cache_read_tokens":1.25e-8,"gemini:completion_tokens":7.5e-7,"gemini:text_input_tokens":1.25e-7,"gemini:audio_input_tokens":2.5e-7,"gemini:image_input_tokens":1.25e-7,"gemini:video_input_tokens":1.25e-7,"gemini:cache_read_text_tokens":1.25e-8,"gemini:cache_read_audio_tokens":2.5e-8,"gemini:cache_read_image_tokens":1.25e-8,"gemini:cache_read_video_tokens":1.25e-8,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"98eb2004-07a1-491d-b617-3f3be35dc348","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:12:00.994Z","status":0}},{"slug":"google/gemini-3.1-flash-lite","hf_slug":null,"updated_at":"2026-05-07T16:01:49.211Z","created_at":"2026-05-07T15:47:08.228Z","hf_updated_at":null,"name":"Google: Gemini 3.1 Flash Lite","short_name":"Gemini 3.1 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\n\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-20260507","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"0d6ee1b8-2f68-491f-9707-4febcfa3a6c4","name":"Google | google/gemini-3.1-flash-lite-20260507","context_length":1048576,"model":{"slug":"google/gemini-3.1-flash-lite","hf_slug":null,"updated_at":"2026-05-07T16:01:49.211829+00:00","created_at":"2026-05-07T15:47:08.228084+00:00","hf_updated_at":null,"name":"Google: Gemini 3.1 Flash Lite","short_name":"Gemini 3.1 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\n\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-20260507","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-flash-lite","model_variant_permaslug":"google/gemini-3.1-flash-lite-20260507","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.1-flash-lite","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","input_cache_read":"0.000000025","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.0000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.025e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.05e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.025e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.05e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.25e-6","gemini:reasoning_tokens":"1.5e-6","gemini:cache_read_tokens":"0.025e-6","gemini:completion_tokens":"1.5e-6","gemini:text_input_tokens":"0.25e-6","gemini:audio_input_tokens":"0.5e-6","gemini:image_input_tokens":"0.25e-6","gemini:video_input_tokens":"0.25e-6","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.025e-6","gemini:cache_read_audio_tokens":"0.05e-6","gemini:cache_read_image_tokens":"0.025e-6","gemini:cache_read_video_tokens":"0.025e-6","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"1e-6","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"35d843f3-1aa1-4a22-afe0-02edf7ddadea","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":300,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-07T15:47:17.114Z","status":0}},{"slug":"openai/gpt-chat-latest","hf_slug":null,"updated_at":"2026-05-05T18:01:50.845Z","created_at":"2026-05-05T16:56:52.607Z","hf_updated_at":null,"name":"OpenAI: GPT Chat Latest","short_name":"GPT Chat Latest","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates in the future, they are routed behind this slug automatically.\n\nFor more info, see: https://developers.openai.com/api/docs/models/chat-latest","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-chat-latest-20260505","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"144906de-89e6-4ba4-a986-640af2562cfa","name":"OpenAI | openai/gpt-chat-latest-20260505","context_length":400000,"model":{"slug":"openai/gpt-chat-latest","hf_slug":null,"updated_at":"2026-05-05T18:01:50.845513+00:00","created_at":"2026-05-05T16:56:52.607777+00:00","hf_updated_at":null,"name":"OpenAI: GPT Chat Latest","short_name":"GPT Chat Latest","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates in the future, they are routed behind this slug automatically.\n\nFor more info, see: https://developers.openai.com/api/docs/models/chat-latest","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-chat-latest-20260505","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-chat-latest","model_variant_permaslug":"openai/gpt-chat-latest-20260505","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"chat-latest","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["top_p","temperature"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:input_tokens":"0.00000175","openai_responses:output_tokens":"0.000014","openai_responses:prompt_tokens":"5e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"30e-6","openai_responses:web_search_results":"0.01","openai_responses:cached_input_tokens":"0.000000175","openai_responses:cached_prompt_tokens":"0.5e-6"},"pricing_version_id":"36e500d4-11aa-42d8-ae5b-c3dda8d42daf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-05T16:57:04.931Z","status":0}},{"slug":"x-ai/grok-4.3","hf_slug":null,"updated_at":"2026-08-04T17:55:06.013Z","created_at":"2026-04-30T23:30:21.141Z","hf_updated_at":null,"name":"SpaceXAI: Grok 4.3","short_name":"Grok 4.3","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.\n\nIt supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.3-20260430","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","none"],"default_reasoning_effort":"low","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","none"],"default_reasoning_effort":"low","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"5110cba8-da2e-4c85-be65-837bdfbedafe","name":"xAI | x-ai/grok-4.3-20260430","context_length":1000000,"model":{"slug":"x-ai/grok-4.3","hf_slug":null,"updated_at":"2026-08-04T17:55:06.013767+00:00","created_at":"2026-04-30T23:30:21.141+00:00","hf_updated_at":null,"name":"SpaceXAI: Grok 4.3","short_name":"Grok 4.3","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.\n\nIt supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","model_version_group_id":"bb483e52-2699-4b22-8fff-d0a2cb828cd7","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.3-20260430","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","none"],"default_reasoning_effort":"low","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","none"],"default_reasoning_effort":"low","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"x-ai/grok-4.3","model_variant_permaslug":"x-ai/grok-4.3-20260430","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai/zdr","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI (ZDR)","provider_slug":"xai/zdr","provider_model_id":"grok-4.3","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":["reasoning_effort"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"2.5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000025"},{"sku_label":">200K","price":"5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":".4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"2.5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000025"},{"sku_label":">200K","price":"5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":".4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"0.00000125","xai_responses:x_search_calls":"0.005","xai_responses:web_search_calls":"0.005","xai_responses:completion_tokens":"0.0000025","xai_responses:cached_prompt_tokens":"0.0000002","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"2.5e-6","xai_responses:completion_tokens_high_context":"5e-6","xai_responses:usage_guidelines_violation_fee":"0.05","xai_responses:cached_prompt_tokens_high_context":".4e-6"},"pricing_version_id":"e78ff105-62ae-4fa9-b3d0-86f6e8868c36","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-25T20:45:02.606Z","status":0}},{"slug":"ibm-granite/granite-4.1-8b","hf_slug":"ibm-granite/granite-4.1-8b","updated_at":"2026-04-30T19:24:42.875Z","created_at":"2026-04-30T19:24:31.868Z","hf_updated_at":null,"name":"IBM: Granite 4.1 8B","short_name":"Granite 4.1 8B","author":"ibm-granite","author_display_name":"ibm-granite","author_icon_uri":null,"description":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks including tool calling, retrieval-augmented generation (RAG), code generation with fill-in-the-middle support, text summarization, classification, and extraction.\n\nThe model handles 12 languages (English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese) and implements OpenAI-compatible tool calling. Released under the Apache 2.0 license.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"ibm-granite/granite-4.1-8b-20260429","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"text","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"c7587631-66c2-46d5-a5c9-b50cb6d230dc","name":"CoreWeave | ibm-granite/granite-4.1-8b-20260429","context_length":131072,"model":{"slug":"ibm-granite/granite-4.1-8b","hf_slug":"ibm-granite/granite-4.1-8b","updated_at":"2026-04-30T19:24:42.875536+00:00","created_at":"2026-04-30T19:24:31.868+00:00","hf_updated_at":null,"name":"IBM: Granite 4.1 8B","short_name":"Granite 4.1 8B","author":"ibm-granite","author_display_name":"ibm-granite","author_icon_uri":null,"description":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks including tool calling, retrieval-augmented generation (RAG), code generation with fill-in-the-middle support, text summarization, classification, and extraction.\n\nThe model handles 12 languages (English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese) and implements OpenAI-compatible tool calling. Released under the Apache 2.0 license.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"ibm-granite/granite-4.1-8b-20260429","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"text","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"ibm-granite/granite-4.1-8b","model_variant_permaslug":"ibm-granite/granite-4.1-8b-20260429","adapter_name":"WandbAdapter","provider_name":"CoreWeave","provider_info":{"name":"CoreWeave","displayName":"CoreWeave","slug":"coreweave","baseUrl":"https://api.inference.wandb.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"WandbAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/CoreWeave.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"CoreWeave","provider_slug":"coreweave/bf16","provider_model_id":"ibm-granite/granite-4.1-8b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy"},"pricing":{"prompt":"0.00000005","completion":"0.0000001","input_cache_read":"0.00000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000005","openai:completion_tokens":"0.0000001","openai:cached_prompt_tokens":"0.00000005"},"pricing_version_id":"07fa0fc6-fad4-4a06-8a06-fa3b0506c042","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T21:06:49.385Z","status":0}},{"slug":"mistralai/mistral-medium-3-5","hf_slug":null,"updated_at":"2026-05-14T22:39:36.220Z","created_at":"2026-04-30T17:33:59.822Z","hf_updated_at":null,"name":"Mistral: Mistral Medium 3.5","short_name":"Mistral Medium 3.5","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-medium-3.5-20260430","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"38ef23a9-5cb3-46fa-85ec-7aed174f04eb","name":"Mistral | mistralai/mistral-medium-3.5-20260430","context_length":262144,"model":{"slug":"mistralai/mistral-medium-3-5","hf_slug":null,"updated_at":"2026-05-14T22:39:36.220554+00:00","created_at":"2026-04-30T17:33:59.822783+00:00","hf_updated_at":null,"name":"Mistral: Mistral Medium 3.5","short_name":"Mistral Medium 3.5","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-medium-3.5-20260430","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","none"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-medium-3-5","model_variant_permaslug":"mistralai/mistral-medium-3.5-20260430","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"mistral-medium-3-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000015","completion":"0.0000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.0000015","mistral:completion_tokens":"0.0000075"},"pricing_version_id":"fe774ecd-3c11-4af8-88c1-ebc841bf3df3","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-30T17:34:04.562Z","status":0}},{"slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","hf_slug":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","updated_at":"2026-06-17T15:56:59.768Z","created_at":"2026-04-28T16:18:15.164Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","short_name":"Nemotron 3 Nano Omni (free)","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.\n\nBuilt on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"36402cf4-40a3-4188-b964-5625d8052cc0","name":"Nvidia | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428:free","context_length":256000,"model":{"slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","hf_slug":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","updated_at":"2026-06-17T15:56:59.768569+00:00","created_at":"2026-04-28T16:18:15.164+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Nano Omni","short_name":"Nemotron 3 Nano Omni","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.\n\nBuilt on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_max_tokens":true,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","model_variant_permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428:free","adapter_name":"NvidiaAdapter","provider_name":"Nvidia","provider_info":{"name":"Nvidia","displayName":"NVIDIA","slug":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"NvidiaAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.nvidia.com/en-us/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NVIDIA","provider_slug":"nvidia","provider_model_id":"private/nvidia/nemotron-3-nano-omni-reasoning-30b-a3b","quantization":"unknown","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"414b6754-ab51-4f0c-bf5c-3db26d6e788e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"disable_free_endpoint_limits":false,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":false,"literal_required":false,"type_function":false}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["reasoning_budget","chat_template_kwargs"],"capacity_tpm":null,"created_at":"2026-04-27T16:35:21.655Z","status":0}},{"slug":"~anthropic/claude-haiku-latest","hf_slug":null,"updated_at":"2026-05-05T04:43:05.067Z","created_at":"2026-04-27T19:34:52.584Z","hf_updated_at":null,"name":"Anthropic Claude Haiku Latest","short_name":"Anthropic Claude Haiku Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Anthropic Claude Haiku family.","model_version_group_id":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-haiku-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/global","google-vertex","anthropic","google-vertex/europe","amazon-bedrock"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~anthropic/claude-haiku-latest","name":"Anthropic | anthropic/claude-4.5-haiku-20251001","context_length":200000,"model":{"slug":"~anthropic/claude-haiku-latest","hf_slug":null,"updated_at":"2026-05-05T04:43:05.067Z","created_at":"2026-04-27T19:34:52.584Z","hf_updated_at":null,"name":"Anthropic Claude Haiku Latest","short_name":"Anthropic Claude Haiku Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Anthropic Claude Haiku family.","model_version_group_id":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-haiku-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/global","google-vertex","anthropic","google-vertex/europe","amazon-bedrock"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~anthropic/claude-haiku-latest","model_variant_permaslug":"~anthropic/claude-haiku-latest","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-haiku-4-5-20251001","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format","max_completion_tokens"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":0.000001,"anthropic:web_search_calls":0.01,"anthropic:cache_read_tokens":1e-7,"anthropic:completion_tokens":0.000005,"anthropic:cache_write_1h_tokens":0.000002,"anthropic:cache_write_5m_tokens":0.00000125},"pricing_version_id":"37ac63dd-eb6a-47b4-96ea-c8ed46256597","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":125,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-14T19:38:10.102Z","status":0}},{"slug":"~openai/gpt-mini-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:34:31.606Z","hf_updated_at":null,"name":"OpenAI GPT Mini Latest","short_name":"OpenAI GPT Mini Latest","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model always redirects to the latest model in the OpenAI GPT Mini family.","model_version_group_id":"ff27acaa-273d-45ee-be59-d9667cd68b4f","context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~openai/gpt-mini-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~openai/gpt-mini-latest","name":"Azure | openai/gpt-5.4-mini-20260317","context_length":400000,"model":{"slug":"~openai/gpt-mini-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:34:31.606Z","hf_updated_at":null,"name":"OpenAI GPT Mini Latest","short_name":"OpenAI GPT Mini Latest","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model always redirects to the latest model in the OpenAI GPT Mini family.","model_version_group_id":"ff27acaa-273d-45ee-be59-d9667cd68b4f","context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~openai/gpt-mini-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~openai/gpt-mini-latest","model_variant_permaslug":"~openai/gpt-mini-latest","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.4-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice","max_tokens"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000075","completion":"0.0000045","input_cache_read":"0.000000075","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.75e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.075e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.75e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.075e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"0.75e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"4.5e-6","openai_responses:cached_prompt_tokens":"0.075e-6"},"pricing_version_id":"63988824-363a-4715-9462-89de743b8eab","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_resolutions":null,"supported_aspect_ratios":null,"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-16T18:01:59.363Z","status":0}},{"slug":"~google/gemini-pro-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:34:11.587Z","hf_updated_at":null,"name":"Google Gemini Pro Latest","short_name":"Google Gemini Pro Latest","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"This model always redirects to the latest model in the Google Gemini Pro family.","model_version_group_id":"efd991b0-c32d-4220-8a39-10b0ae06b094","context_length":1048576,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~google/gemini-pro-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~google/gemini-pro-latest","name":"Google AI Studio | google/gemini-3.1-pro-preview-20260219","context_length":1048576,"model":{"slug":"~google/gemini-pro-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:34:11.587Z","hf_updated_at":null,"name":"Google Gemini Pro Latest","short_name":"Google Gemini Pro Latest","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"This model always redirects to the latest model in the Google Gemini Pro family.","model_version_group_id":"efd991b0-c32d-4220-8a39-10b0ae06b094","context_length":1048576,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~google/gemini-pro-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~google/gemini-pro-latest","model_variant_permaslug":"~google/gemini-pro-latest","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.1-pro-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000012"},{"sku_label":">200K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000012"},{"sku_label":">200K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.000002","gemini:reasoning_tokens":"0.000012","gemini:cache_read_tokens":"2e-7","gemini:completion_tokens":"0.000012","gemini:text_input_tokens":"0.000002","gemini:audio_input_tokens":"0.000002","gemini:image_input_tokens":"0.000002","gemini:video_input_tokens":"0.000002","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"2e-7","gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":"2e-7","gemini:cache_read_image_tokens":"2e-7","gemini:cache_read_video_tokens":"2e-7","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"0.0000045","gemini:prompt_tokens_high_context":"0.000004","gemini:reasoning_tokens_high_context":"0.000018","gemini:cache_read_tokens_high_context":"4e-7","gemini:completion_tokens_high_context":"0.000018","gemini:cache_read_text_tokens_high_context":"4e-7","gemini:cache_read_audio_tokens_high_context":"4e-7","gemini:cache_read_image_tokens_high_context":"4e-7","gemini:cache_read_video_tokens_high_context":"4e-7","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"0312e85d-eece-4c6f-8c8e-49087e1a1899","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":300,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-10T00:42:42.296Z","status":0}},{"slug":"~moonshotai/kimi-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:33:48.140Z","hf_updated_at":null,"name":"MoonshotAI Kimi Latest","short_name":"MoonshotAI Kimi Latest","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"This model always redirects to the latest model in the MoonshotAI Kimi family.","model_version_group_id":"4c6ad0bc-8b01-4b5f-8466-129136e36ef7","context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~moonshotai/kimi-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~moonshotai/kimi-latest","name":"Sail Research | moonshotai/kimi-k3-20260715","context_length":974842,"model":{"slug":"~moonshotai/kimi-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:33:48.140Z","hf_updated_at":null,"name":"MoonshotAI Kimi Latest","short_name":"MoonshotAI Kimi Latest","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"This model always redirects to the latest model in the MoonshotAI Kimi family.","model_version_group_id":"4c6ad0bc-8b01-4b5f-8466-129136e36ef7","context_length":1048576,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~moonshotai/kimi-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","high","max"],"default_reasoning_effort":"max","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~moonshotai/kimi-latest","model_variant_permaslug":"~moonshotai/kimi-latest","adapter_name":"SailResearchAdapter","provider_name":"Sail Research","provider_info":{"name":"Sail Research","displayName":"Sail Research","slug":"sail-research","baseUrl":"https://api.sailresearch.com/partner/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.sailresearch.com/terms","privacyPolicyURL":"https://www.sailresearch.com/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"SailResearchAdapter","statusPageUrl":"https://status.sailresearch.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.sailresearch.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Sail Research","provider_slug":"sail-research/fp4","provider_model_id":"moonshotai/Kimi-K3","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":974842,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","min_p","repetition_penalty","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.sailresearch.com/terms","privacyPolicyURL":"https://www.sailresearch.com/privacy"},"pricing":{"prompt":"0.0000026","completion":"0.000013","input_cache_read":"0.00000029","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000026","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000029","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000026","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000029","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000026","openai:completion_tokens":"0.000013","openai:cached_prompt_tokens":"0.00000029"},"pricing_version_id":"1fda5b4f-bffd-4eac-a045-75429ba92867","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":false,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":false,"supports_base64_video_input":false,"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":2100000,"created_at":"2026-08-06T23:52:02.825Z","status":0}},{"slug":"~google/gemini-flash-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:33:18.348Z","hf_updated_at":null,"name":"Google Gemini Flash Latest","short_name":"Google Gemini Flash Latest","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"This model always redirects to the latest model in the Google Gemini Flash family.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~google/gemini-flash-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/global"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":300,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~google/gemini-flash-latest","name":"Google | google/gemini-3.7-flash-20260813","context_length":1048576,"model":{"slug":"~google/gemini-flash-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:33:18.348Z","hf_updated_at":null,"name":"Google Gemini Flash Latest","short_name":"Google Gemini Flash Latest","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"This model always redirects to the latest model in the Google Gemini Flash family.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~google/gemini-flash-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","low","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/global"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":300,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~google/gemini-flash-latest","model_variant_permaslug":"~google/gemini-flash-latest","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.7-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","temperature","top_p"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","audio":"0.000000375","input_audio_cache":"0.0000000375","input_cache_read":"0.0000000375","input_cache_write":"0.000000020833333333333335","web_search":"0.014","internal_reasoning":"0.000001875","discount":0.75,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000020833333333333335","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000020833333333333335","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"gemini:prompt_tokens":"0.0000015","gemini:reasoning_tokens":"0.0000075","gemini:web_search_calls":"0.014","gemini:cache_read_tokens":"0.00000015","gemini:completion_tokens":"0.0000075","gemini:text_input_tokens":"0.0000015","gemini:audio_input_tokens":"0.0000015","gemini:image_input_tokens":"0.0000015","gemini:video_input_tokens":"0.0000015","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.00000015","gemini:cache_read_audio_tokens":"0.00000015","gemini:cache_read_image_tokens":"0.00000015","gemini:cache_read_video_tokens":"0.00000015","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"0.000001","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"6657c55f-e921-43ff-b361-742728707831","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-12T14:13:50.546Z","status":0}},{"slug":"~anthropic/claude-sonnet-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:32:48.042Z","hf_updated_at":null,"name":"Anthropic Claude Sonnet Latest","short_name":"Anthropic Claude Sonnet Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-sonnet-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","azure/global","anthropic","amazon-bedrock/us-east-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~anthropic/claude-sonnet-latest","name":"Anthropic | anthropic/claude-sonnet-5-20260630","context_length":1000000,"model":{"slug":"~anthropic/claude-sonnet-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:32:48.042Z","hf_updated_at":null,"name":"Anthropic Claude Sonnet Latest","short_name":"Anthropic Claude Sonnet Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-sonnet-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","max","xhigh"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","azure/global","anthropic","amazon-bedrock/us-east-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~anthropic/claude-sonnet-latest","model_variant_permaslug":"~anthropic/claude-sonnet-latest","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-sonnet-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity","max_completion_tokens"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"2e-6","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":".2e-6","anthropic:completion_tokens":"10e-6","anthropic:cache_write_1h_tokens":"4e-6","anthropic:cache_write_5m_tokens":"2.5e-6"},"pricing_version_id":"1efcb581-a9a3-4500-a466-f7e855f95d96","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-29T20:28:52.700Z","status":0}},{"slug":"~openai/gpt-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:32:14.498Z","hf_updated_at":null,"name":"OpenAI GPT Latest","short_name":"OpenAI GPT Latest","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model always redirects to the latest model in the OpenAI GPT family.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~openai/gpt-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~openai/gpt-latest","name":"OpenAI | openai/gpt-5.6-sol-20260709","context_length":1050000,"model":{"slug":"~openai/gpt-latest","hf_slug":null,"updated_at":null,"created_at":"2026-04-27T19:32:14.498Z","hf_updated_at":null,"name":"OpenAI GPT Latest","short_name":"OpenAI GPT Latest","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model always redirects to the latest model in the OpenAI GPT family.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"~openai/gpt-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh","max"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2026-02-16T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~openai/gpt-latest","model_variant_permaslug":"~openai/gpt-latest","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.6-sol","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","max_completion_tokens"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0.5,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00001"},{"sku_label":">272K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.000002"},{"sku_label":">272K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.00001"},{"sku_label":">272K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000002"},{"sku_label":">272K","price":"0.0000004"}]},{"kind":"token","sku_label":"Cache Write","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.0000025"},{"sku_label":">272K","price":"0.000005"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true,"isDiscountExempt":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000004","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.00002","openai_responses:cache_write_tokens":"0.000005","openai_responses:cached_prompt_tokens":"0.0000004","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"0.000008","openai_responses:completion_tokens_high_context":"0.00003","openai_responses:cache_write_tokens_high_context":"0.00001","openai_responses:cached_prompt_tokens_high_context":"0.0000008"},"pricing_version_id":"18f0d69c-c23d-4deb-9254-75118a94371b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T19:30:02.541Z","status":0}},{"slug":"qwen/qwen3.5-plus-20260420","hf_slug":null,"updated_at":"2026-04-27T04:21:21.854Z","created_at":"2026-04-27T03:42:48.608Z","hf_updated_at":null,"name":"Qwen: Qwen3.5 Plus 2026-04-20","short_name":"Qwen3.5 Plus 2026-04-20","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This is an updated version of Qwen3.5 Plus with tiered pricing above 256K tokens.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-plus-20260420","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc","name":"Alibaba | qwen/qwen3.5-plus-20260420","context_length":1000000,"model":{"slug":"qwen/qwen3.5-plus-20260420","hf_slug":null,"updated_at":"2026-04-27T04:21:21.854424+00:00","created_at":"2026-04-27T03:42:48.608256+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5 Plus 2026-04-20","short_name":"Qwen3.5 Plus 2026-04-20","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This is an updated version of Qwen3.5 Plus with tiered pricing above 256K tokens.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-plus-20260420","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-plus-20260420","model_variant_permaslug":"qwen/qwen3.5-plus-20260420","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.5-plus-2026-04-20","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.0000003","completion":"0.0000018","input_cache_write":"0.000000375","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000375","completion":"0.00000225","input_cache_write":"0.00000046875"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000003"},{"sku_label":">256K","price":"0.000000375"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000018","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000018"},{"sku_label":">256K","price":"0.00000225"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000375"},{"sku_label":">256K","price":"0.00000046875"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000003"},{"sku_label":">256K","price":"0.0000000375"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000003"},{"sku_label":">256K","price":"0.000000375"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000018","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000018"},{"sku_label":">256K","price":"0.00000225"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000375"},{"sku_label":">256K","price":"0.00000046875"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000003"},{"sku_label":">256K","price":"0.0000000375"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.0000003","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.0000018","alibaba:prompt_tokens_tier2":"0.000000375","alibaba:cache_creation_tokens":"0.000000375","alibaba:completion_tokens_tier2":"0.00000225","alibaba:cache_creation_tokens_tier2":"0.00000046875","alibaba:explicit_cached_prompt_tokens":"0.00000003","alibaba:explicit_cached_prompt_tokens_tier2":"0.0000000375"},"pricing_version_id":"2460b33f-df37-42fa-bc9a-bf8a126e49f9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_base64_video_input":true,"supports_video_urls":true,"reasoning_return_mechanism":"reasoning","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-27T03:43:17.046Z","status":0}},{"slug":"qwen/qwen3.6-flash","hf_slug":null,"updated_at":"2026-04-27T04:21:18.979Z","created_at":"2026-04-27T03:42:42.075Z","hf_updated_at":null,"name":"Qwen: Qwen3.6 Flash","short_name":"Qwen3.6 Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in above 256K tokens. Prompt caching is supported, with both explicit cache read and cache creation pricing.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2435bec9-c808-4f27-9fc8-12f3460d7b66","name":"Alibaba | qwen/qwen3.6-flash","context_length":1000000,"model":{"slug":"qwen/qwen3.6-flash","hf_slug":null,"updated_at":"2026-04-27T04:21:18.97943+00:00","created_at":"2026-04-27T03:42:42.075562+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.6 Flash","short_name":"Qwen3.6 Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in above 256K tokens. Prompt caching is supported, with both explicit cache read and cache creation pricing.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.6-flash","model_variant_permaslug":"qwen/qwen3.6-flash","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.6-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.0000001875","completion":"0.000001125","input_cache_write":"0.000000234375","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000075","completion":"0.000003","input_cache_write":"0.0000009375"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000001875"},{"sku_label":">256K","price":"0.00000075"}]},{"kind":"token","sku_label":"Output Price","price":"0.000001125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000001125"},{"sku_label":">256K","price":"0.000003"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000234375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000234375"},{"sku_label":">256K","price":"0.0000009375"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.00000001875","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000001875"},{"sku_label":">256K","price":"0.000000075"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001875","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000001875"},{"sku_label":">256K","price":"0.00000075"}]},{"kind":"token","sku_label":"Output Price","price":"0.000001125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000001125"},{"sku_label":">256K","price":"0.000003"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000234375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000234375"},{"sku_label":">256K","price":"0.0000009375"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.00000001875","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000001875"},{"sku_label":">256K","price":"0.000000075"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.0000001875","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.000001125","alibaba:prompt_tokens_tier2":"0.00000075","alibaba:cache_creation_tokens":"0.000000234375","alibaba:completion_tokens_tier2":"0.000003","alibaba:cache_creation_tokens_tier2":"0.0000009375","alibaba:explicit_cached_prompt_tokens":"0.00000001875","alibaba:explicit_cached_prompt_tokens_tier2":"0.000000075"},"pricing_version_id":"d30666fc-0f0f-4b45-af2b-80bea8d83985","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"reasoning_return_mechanism":"reasoning","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-27T03:43:10.738Z","status":0}},{"slug":"qwen/qwen3.6-35b-a3b","hf_slug":"Qwen/Qwen3.6-35B-A3B","updated_at":"2026-04-27T03:32:48.372Z","created_at":"2026-04-27T03:24:15.340Z","hf_updated_at":null,"name":"Qwen: Qwen3.6 35B A3B","short_name":"Qwen3.6 35B A3B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-35b-a3b-20260415","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"babd4746-9e93-4855-8578-4b40539a5f4a","name":"Darkbloom | qwen/qwen3.6-35b-a3b-20260415","context_length":262144,"model":{"slug":"qwen/qwen3.6-35b-a3b","hf_slug":"Qwen/Qwen3.6-35B-A3B","updated_at":"2026-04-27T03:32:48.372228+00:00","created_at":"2026-04-27T03:24:15.340327+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.6 35B A3B","short_name":"Qwen3.6 35B A3B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-35b-a3b-20260415","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.6-35b-a3b","model_variant_permaslug":"qwen/qwen3.6-35b-a3b-20260415","adapter_name":"DarkbloomAdapter","provider_name":"Darkbloom","provider_info":{"name":"Darkbloom","displayName":"Darkbloom","slug":"darkbloom","baseUrl":"https://api.darkbloom.dev/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.darkbloom.dev/terms.html","privacyPolicyURL":"https://www.darkbloom.dev/privacy.html","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"DarkbloomAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"/images/icons/Darkbloom.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Darkbloom","provider_slug":"darkbloom/fp4","provider_model_id":"qwen3.6-35b-a3b-vl-mtp-mxfp8","quantization":"fp4","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.darkbloom.dev/terms.html","privacyPolicyURL":"https://www.darkbloom.dev/privacy.html"},"pricing":{"prompt":"0.00000007","completion":"0.0000007","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000007","openai:completion_tokens":"0.0000007"},"pricing_version_id":"86eaedc8-01ce-418a-adfc-49b24406a8b9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":false,"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-14T20:52:18.212Z","status":-2}},{"slug":"qwen/qwen3.6-max-preview","hf_slug":null,"updated_at":"2026-04-27T03:35:43.820Z","created_at":"2026-04-27T03:24:02.092Z","hf_updated_at":null,"name":"Qwen: Qwen3.6 Max Preview","short_name":"Qwen3.6 Max Preview","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning traces across multi-turn conversations and supports structured output and function calling. Access is available exclusively through the Alibaba Cloud Model Studio and Qwen Studio APIs; no open weights are provided.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-max-preview-20260420","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787","name":"Alibaba | qwen/qwen3.6-max-preview-20260420","context_length":262144,"model":{"slug":"qwen/qwen3.6-max-preview","hf_slug":null,"updated_at":"2026-04-27T03:35:43.820538+00:00","created_at":"2026-04-27T03:24:02.092229+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.6 Max Preview","short_name":"Qwen3.6 Max Preview","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning traces across multi-turn conversations and supports structured output and function calling. Access is available exclusively through the Alibaba Cloud Model Studio and Qwen Studio APIs; no open weights are provided.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-max-preview-20260420","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.6-max-preview","model_variant_permaslug":"qwen/qwen3.6-max-preview-20260420","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.6-max-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":229376,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000001027","completion":"0.000006162","input_cache_write":"0.00000128375","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.00000158","completion":"0.00000948","input_cache_write":"0.000001975"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001027","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000001027"},{"sku_label":">128K","price":"0.00000158"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006162","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000006162"},{"sku_label":">128K","price":"0.00000948"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000128375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.00000128375"},{"sku_label":">128K","price":"0.000001975"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000001027","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000001027"},{"sku_label":">128K","price":"0.000000158"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001027","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000001027"},{"sku_label":">128K","price":"0.00000158"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006162","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000006162"},{"sku_label":">128K","price":"0.00000948"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000128375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.00000128375"},{"sku_label":">128K","price":"0.000001975"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000001027","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000001027"},{"sku_label":">128K","price":"0.000000158"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.000001027","alibaba:tier2_threshold":"128000","alibaba:completion_tokens":"0.000006162","alibaba:prompt_tokens_tier2":"0.00000158","alibaba:cache_creation_tokens":"0.00000128375","alibaba:completion_tokens_tier2":"0.00000948","alibaba:cache_creation_tokens_tier2":"0.000001975","alibaba:explicit_cached_prompt_tokens":"0.0000001027","alibaba:explicit_cached_prompt_tokens_tier2":"0.000000158"},"pricing_version_id":"85c0c330-bec9-43c1-9e6d-5339b9359908","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-27T03:24:26.286Z","status":0}},{"slug":"qwen/qwen3.6-27b","hf_slug":"Qwen/Qwen3.6-27B","updated_at":"2026-04-27T03:32:47.263Z","created_at":"2026-04-27T01:57:44.058Z","hf_updated_at":null,"name":"Qwen: Qwen3.6 27B","short_name":"Qwen3.6 27B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs — and supports a 262,144-token context window.\n\nThe model is designed for agentic coding and reasoning tasks, with particular strength in repository-level code comprehension, front-end development workflows, and multi-step problem solving. It includes a built-in thinking mode for extended reasoning and preserves thinking context across conversation history. Qwen3.6 27B supports 201 languages and dialects and is released under the Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-27b-20260422","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"328bee10-7e34-44f8-a7cc-c33c8f8775ed","name":"Chutes | qwen/qwen3.6-27b-20260422","context_length":262144,"model":{"slug":"qwen/qwen3.6-27b","hf_slug":"Qwen/Qwen3.6-27B","updated_at":"2026-04-27T03:32:47.263211+00:00","created_at":"2026-04-27T01:57:44.058014+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.6 27B","short_name":"Qwen3.6 27B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs — and supports a 262,144-token context window.\n\nThe model is designed for agentic coding and reasoning tasks, with particular strength in repository-level code comprehension, front-end development workflows, and multi-step problem solving. It includes a built-in thinking mode for extended reasoning and preserves thinking context across conversation history. Qwen3.6 27B supports 201 languages and dialects and is released under the Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-27b-20260422","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.6-27b","model_variant_permaslug":"qwen/qwen3.6-27b-20260422","adapter_name":"ChutesAdapter","provider_name":"Chutes","provider_info":{"name":"Chutes","displayName":"Chutes","slug":"chutes","baseUrl":"https://llm.chutes.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://chutes.ai/tos","privacyPolicyURL":"https://chutes.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ChutesAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://chutes.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Chutes","provider_slug":"chutes/fp8","provider_model_id":"Qwen/Qwen3.6-27B-TEE","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://chutes.ai/tos","privacyPolicyURL":"https://chutes.ai/privacy"},"pricing":{"prompt":"0.0000003","completion":"0.000002","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.000002","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"baca7b32-e1bf-410f-baac-3e7b5e491d20","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-27T02:11:01.546Z","status":0}},{"slug":"openai/gpt-5.5-pro","hf_slug":"","updated_at":"2026-05-05T18:03:31.506Z","created_at":"2026-04-24T17:31:36.719Z","hf_updated_at":null,"name":"OpenAI: GPT-5.5 Pro (batch)","short_name":"GPT-5.5 Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-pro-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"7e09d95d-31e8-4479-8db5-583154679138","name":"OpenAI | openai/gpt-5.5-pro-20260423:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.5-pro","hf_slug":"","updated_at":"2026-05-05T18:03:31.506397+00:00","created_at":"2026-04-24T17:31:36.719+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.5 Pro","short_name":"GPT-5.5 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-pro-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.5-pro:batch","model_variant_permaslug":"openai/gpt-5.5-pro-20260423:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.5-pro-2026-04-23","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000015","completion":"0.00009","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00003","completion":"0.000135"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.500000e-5"},{"sku_label":">272K","price":"3.000000e-5"}]},{"kind":"token","sku_label":"Output Price","price":"9.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"9.000000e-5"},{"sku_label":">272K","price":"1.350000e-4"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.500000e-5"},{"sku_label":">272K","price":"3.000000e-5"}]},{"kind":"token","sku_label":"Output Price","price":"9.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"9.000000e-5"},{"sku_label":">272K","price":"1.350000e-4"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.500000e-5","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"9.000000e-5","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"3.000000e-5","openai_responses:completion_tokens_high_context":"1.350000e-4"},"pricing_version_id":"33349434-8266-457a-b462-9b1b8d8809f8","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:25.860Z","status":0}},{"slug":"openai/gpt-5.5-pro","hf_slug":"","updated_at":"2026-05-05T18:03:31.506Z","created_at":"2026-04-24T17:31:36.719Z","hf_updated_at":null,"name":"OpenAI: GPT-5.5 Pro","short_name":"GPT-5.5 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-pro-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"947d13c4-fbd4-48d6-8bf3-c923edab343e","name":"OpenAI | openai/gpt-5.5-pro-20260423","context_length":1050000,"model":{"slug":"openai/gpt-5.5-pro","hf_slug":"","updated_at":"2026-05-05T18:03:31.506397+00:00","created_at":"2026-04-24T17:31:36.719+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.5 Pro","short_name":"GPT-5.5 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","model_version_group_id":null,"context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-pro-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.5-pro","model_variant_permaslug":"openai/gpt-5.5-pro-20260423","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.5-pro-2026-04-23","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"60e-6"}]},{"kind":"token","sku_label":"Output Price","price":"180e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"180e-6"},{"sku_label":">272K","price":"270e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"60e-6"}]},{"kind":"token","sku_label":"Output Price","price":"180e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"180e-6"},{"sku_label":">272K","price":"270e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"30e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"180e-6","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"60e-6","openai_responses:completion_tokens_high_context":"270e-6"},"pricing_version_id":"fd1c8b34-8d7a-4fb4-b2b6-5befa624e435","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-23T13:08:13.100Z","status":0}},{"slug":"openai/gpt-5.5","hf_slug":"","updated_at":"2026-05-05T18:03:21.886Z","created_at":"2026-04-24T17:31:33.253Z","hf_updated_at":null,"name":"OpenAI: GPT-5.5","short_name":"GPT-5.5","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"42da77cc-cd0e-43a4-923a-3b742f7b124d","name":"Azure | openai/gpt-5.5-20260423","context_length":1050000,"model":{"slug":"openai/gpt-5.5","hf_slug":"","updated_at":"2026-05-05T18:03:21.886661+00:00","created_at":"2026-04-24T17:31:33.253+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.5","short_name":"GPT-5.5","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.5","model_variant_permaslug":"openai/gpt-5.5-20260423","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"5e-6"},{"sku_label":">272K","price":"10e-6"}]},{"kind":"token","sku_label":"Output Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"45e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.50e-6"},{"sku_label":">272K","price":"1e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"5e-6"},{"sku_label":">272K","price":"10e-6"}]},{"kind":"token","sku_label":"Output Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"45e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.50e-6"},{"sku_label":">272K","price":"1e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"5e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"30e-6","openai_responses:cached_prompt_tokens":"0.50e-6","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"10e-6","openai_responses:completion_tokens_high_context":"45e-6","openai_responses:cached_prompt_tokens_high_context":"1e-6"},"pricing_version_id":"adf37ec6-b610-4793-9f1b-b51f33b394d0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-23T13:17:36.926Z","status":0}},{"slug":"openai/gpt-5.5","hf_slug":"","updated_at":"2026-05-05T18:03:21.886Z","created_at":"2026-04-24T17:31:33.253Z","hf_updated_at":null,"name":"OpenAI: GPT-5.5 (batch)","short_name":"GPT-5.5 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"34bd7c03-d5bf-4981-93d8-0f8bd0423045","name":"OpenAI | openai/gpt-5.5-20260423:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.5","hf_slug":"","updated_at":"2026-05-05T18:03:21.886661+00:00","created_at":"2026-04-24T17:31:33.253+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.5","short_name":"GPT-5.5","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","model_version_group_id":"c59971be-c6bc-4199-9192-95e9dc48cb9e","context_length":1050000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.5-20260423","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-12-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.5:batch","model_variant_permaslug":"openai/gpt-5.5-20260423:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.5-2026-04-23","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.000015","input_cache_read":"0.00000025","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"0.0000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.500000e-6"},{"sku_label":">272K","price":"5.000000e-6"}]},{"kind":"token","sku_label":"Output Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.500000e-5"},{"sku_label":">272K","price":"2.250000e-5"}]},{"kind":"token","sku_label":"Cache Read","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.500000e-7"},{"sku_label":">272K","price":"5.000000e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.500000e-6"},{"sku_label":">272K","price":"5.000000e-6"}]},{"kind":"token","sku_label":"Output Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.500000e-5"},{"sku_label":">272K","price":"2.250000e-5"}]},{"kind":"token","sku_label":"Cache Read","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.500000e-7"},{"sku_label":">272K","price":"5.000000e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"2.500000e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"1.500000e-5","openai_responses:cached_prompt_tokens":"2.500000e-7","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2.5","openai_responses:prompt_tokens_high_context":"5.000000e-6","openai_responses:completion_tokens_high_context":"2.250000e-5","openai_responses:cached_prompt_tokens_high_context":"5.000000e-7"},"pricing_version_id":"48b5c9cb-1110-4379-8037-ab39078a22a5","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:55.440Z","status":0}},{"slug":"deepseek/deepseek-v4-pro","hf_slug":"deepseek-ai/DeepSeek-V4-Pro","updated_at":"2026-08-16T16:49:27.205Z","created_at":"2026-04-24T03:17:59.654Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Pro 0423","short_name":"DeepSeek V4 Pro 0423","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.\n\nBuilt on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-pro-20260423","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["xhigh","high"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["xhigh","high"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"48f7c1a9-3b0c-4f31-a55b-4650d37e35f3","name":"Baidu | deepseek/deepseek-v4-pro-20260423","context_length":1048576,"model":{"slug":"deepseek/deepseek-v4-pro","hf_slug":"deepseek-ai/DeepSeek-V4-Pro","updated_at":"2026-08-16T16:49:27.205586+00:00","created_at":"2026-04-24T03:17:59.654909+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Pro 0423","short_name":"DeepSeek V4 Pro 0423","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.\n\nBuilt on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-pro-20260423","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["xhigh","high"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["xhigh","high"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v4-pro","model_variant_permaslug":"deepseek/deepseek-v4-pro-20260423","adapter_name":"BaiduAdapter","provider_name":"Baidu","provider_info":{"name":"Baidu","displayName":"Baidu Qianfan","slug":"baidu","baseUrl":"https://api.baiduqianfan.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"BaiduAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://intl.cloud.baidu.com/en&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Baidu Qianfan","provider_slug":"baidu/fp8","provider_model_id":"deepseek-v4-pro","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":393216,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["max_completion_tokens"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en"},"pricing":{"prompt":"0.000000507","completion":"0.000001014","input_cache_read":"0.000000042","discount":0.7,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000507","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000042","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000507","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000042","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000169","openai:completion_tokens":"0.00000338","openai:cached_prompt_tokens":"0.00000014"},"pricing_version_id":"a60e16b6-e596-4a60-b617-255d342fd943","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":215160000,"created_at":"2026-04-29T11:41:27.715Z","status":0}},{"slug":"deepseek/deepseek-v4-flash","hf_slug":"deepseek-ai/DeepSeek-V4-Flash","updated_at":"2026-08-03T19:53:54.226Z","created_at":"2026-04-24T03:17:46.710Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Flash 0423","short_name":"DeepSeek V4 Flash 0423","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.\n\nThe model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.","model_version_group_id":"82f5b893-9a91-488e-b71d-77410fdf15d6","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-flash-20260423","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"fa22fe84-7ea9-49b0-a8eb-4d87ede9de31","name":"Baidu | deepseek/deepseek-v4-flash-20260423","context_length":1048576,"model":{"slug":"deepseek/deepseek-v4-flash","hf_slug":"deepseek-ai/DeepSeek-V4-Flash","updated_at":"2026-08-03T19:53:54.226401+00:00","created_at":"2026-04-24T03:17:46.710737+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V4 Flash 0423","short_name":"DeepSeek V4 Flash 0423","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.\n\nThe model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.","model_version_group_id":"82f5b893-9a91-488e-b71d-77410fdf15d6","context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v4-flash-20260423","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","xhigh"],"default_reasoning_effort":"high","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v4-flash","model_variant_permaslug":"deepseek/deepseek-v4-flash-20260423","adapter_name":"BaiduAdapter","provider_name":"Baidu","provider_info":{"name":"Baidu","displayName":"Baidu Qianfan","slug":"baidu","baseUrl":"https://api.baiduqianfan.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"BaiduAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://intl.cloud.baidu.com/en&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Baidu Qianfan","provider_slug":"baidu/fp8","provider_model_id":"deepseek-v4-flash","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["max_completion_tokens"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en"},"pricing":{"prompt":"0.0000000546","completion":"0.0000001092","input_cache_read":"0.00000001092","discount":0.61,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000000546","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001092","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001092","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000000546","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001092","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001092","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000014","openai:completion_tokens":"0.00000028","openai:cached_prompt_tokens":"0.000000028"},"pricing_version_id":"705a8343-d43b-4fe1-b4d8-06aa7b2313dd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":515860000,"created_at":"2026-05-11T09:35:35.608Z","status":0}},{"slug":"tencent/hy3-preview","hf_slug":"tencent/Hy3-preview","updated_at":"2026-05-08T22:41:20.907Z","created_at":"2026-04-22T17:15:50.112Z","hf_updated_at":null,"name":"Tencent: Hy3 preview","short_name":"Hy3 preview","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering strong code generation and reliable performance across multi-step, real-world workflows.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":"Hy3 preview is no longer available as a free model. It has transitioned to a paid model. Continue using it here: https://openrouter.ai/tencent/hy3-preview","required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy3-preview-20260421","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"e062ae6d-577e-4d12-8232-8eabc472c4ec","name":"GMICloud | tencent/hy3-preview-20260421","context_length":262144,"model":{"slug":"tencent/hy3-preview","hf_slug":"tencent/Hy3-preview","updated_at":"2026-05-08T22:41:20.907368+00:00","created_at":"2026-04-22T17:15:50.112+00:00","hf_updated_at":null,"name":"Tencent: Hy3 preview","short_name":"Hy3 preview","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering strong code generation and reliable performance across multi-step, real-world workflows.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":"Hy3 preview is no longer available as a free model. It has transitioned to a paid model. Continue using it here: https://openrouter.ai/tencent/hy3-preview","required_attestation_types":[],"is_private":false,"permaslug":"tencent/hy3-preview-20260421","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","high"],"default_reasoning_effort":"high","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"tencent/hy3-preview","model_variant_permaslug":"tencent/hy3-preview-20260421","adapter_name":"GMICloudAdapter","provider_name":"GMICloud","provider_info":{"name":"GMICloud","displayName":"GMICloud","slug":"gmicloud","baseUrl":"https://api.gmi-serving.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"GMICloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://gmicloud.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"GMICloud","provider_slug":"gmicloud/bf16","provider_model_id":"tencent/hy3-preview","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy"},"pricing":{"prompt":"0.00000018","completion":"0.0000006","input_cache_read":"0.00000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000018","openai:completion_tokens":"0.0000006","openai:cached_prompt_tokens":"0.00000006","openai_extended:long_context_threshold":"16384","openai_extended:long_context_threshold_2":"32768","openai_extended:long_context_prompt_tokens":"0.00000024","openai_extended:long_context_prompt_tokens_2":"0.0000003","openai_extended:long_context_completion_tokens":"0.00000096","openai_extended:long_context_completion_tokens_2":"0.0000012","openai_extended:long_context_cached_prompt_tokens":"0.00000009","openai_extended:long_context_cached_prompt_tokens_2":"0.00000012"},"pricing_version_id":"de8090aa-fa6e-4a85-90d1-7fc4527f3d52","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-11T19:51:27.269Z","status":0}},{"slug":"xiaomi/mimo-v2.5-pro","hf_slug":"XiaomiMiMo/MiMo-V2.5-Pro","updated_at":"2026-04-30T14:15:16.695Z","created_at":"2026-04-22T16:11:13.016Z","hf_updated_at":null,"name":"Xiaomi: MiMo-V2.5-Pro","short_name":"MiMo-V2.5-Pro","author":"xiaomi","author_display_name":"Xiaomi","author_icon_uri":null,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"xiaomi/mimo-v2.5-pro-20260422","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"362a7650-63ed-41d8-b74e-1886ad31b3d9","name":"GMICloud | xiaomi/mimo-v2.5-pro-20260422","context_length":1050000,"model":{"slug":"xiaomi/mimo-v2.5-pro","hf_slug":"XiaomiMiMo/MiMo-V2.5-Pro","updated_at":"2026-04-30T14:15:16.695941+00:00","created_at":"2026-04-22T16:11:13.016+00:00","hf_updated_at":null,"name":"Xiaomi: MiMo-V2.5-Pro","short_name":"MiMo-V2.5-Pro","author":"xiaomi","author_display_name":"Xiaomi","author_icon_uri":null,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"xiaomi/mimo-v2.5-pro-20260422","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"xiaomi/mimo-v2.5-pro","model_variant_permaslug":"xiaomi/mimo-v2.5-pro-20260422","adapter_name":"GMICloudAdapter","provider_name":"GMICloud","provider_info":{"name":"GMICloud","displayName":"GMICloud","slug":"gmicloud","baseUrl":"https://api.gmi-serving.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"GMICloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://gmicloud.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"GMICloud","provider_slug":"gmicloud/bf16","provider_model_id":"XiaomiMiMo/MiMo-V2.5-Pro","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format"],"excluded_parameters":["tools","tool_choice"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy"},"pricing":{"prompt":"0.0000003045","completion":"0.000000609","input_cache_read":"0.0000000028","discount":0.3,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000609","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000028","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000609","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000028","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000435","openai:completion_tokens":"0.00000087","openai:cached_prompt_tokens":"0.000000004"},"pricing_version_id":"270b8d66-2665-4de5-aa2a-670625b5a003","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":false,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-06T20:21:58.311Z","status":0}},{"slug":"xiaomi/mimo-v2.5","hf_slug":"XiaomiMiMo/MiMo-V2.5","updated_at":"2026-04-30T14:15:23.148Z","created_at":"2026-04-22T16:11:09.307Z","hf_updated_at":null,"name":"Xiaomi: MiMo-V2.5","short_name":"MiMo-V2.5","author":"xiaomi","author_display_name":"Xiaomi","author_icon_uri":null,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"xiaomi/mimo-v2.5-20260422","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"fb34a890-eaa9-428e-8fc4-4ad0fdcba2ff","name":"GMICloud | xiaomi/mimo-v2.5-20260422","context_length":1050000,"model":{"slug":"xiaomi/mimo-v2.5","hf_slug":"XiaomiMiMo/MiMo-V2.5","updated_at":"2026-04-30T14:15:23.148861+00:00","created_at":"2026-04-22T16:11:09.307+00:00","hf_updated_at":null,"name":"Xiaomi: MiMo-V2.5","short_name":"MiMo-V2.5","author":"xiaomi","author_display_name":"Xiaomi","author_icon_uri":null,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"xiaomi/mimo-v2.5-20260422","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"xiaomi/mimo-v2.5","model_variant_permaslug":"xiaomi/mimo-v2.5-20260422","adapter_name":"GMICloudAdapter","provider_name":"GMICloud","provider_info":{"name":"GMICloud","displayName":"GMICloud","slug":"gmicloud","baseUrl":"https://api.gmi-serving.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"GMICloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://gmicloud.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"GMICloud","provider_slug":"gmicloud/fp8","provider_model_id":"XiaomiMiMo/MiMo-V2.5","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice"],"excluded_parameters":["response_format"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy"},"pricing":{"prompt":"0.000000119","completion":"0.000000238","input_cache_read":"0.00000000255","discount":0.15,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000119","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000238","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000000255","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000119","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000238","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000000255","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000014","openai:completion_tokens":"0.00000028","openai:cached_prompt_tokens":"0.000000003"},"pricing_version_id":"17dcc4d0-4781-4e7a-8072-fb2fb4b58220","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_video_urls":false,"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-06T20:07:20.204Z","status":0}},{"slug":"openai/gpt-5.4-image-2","hf_slug":"","updated_at":"2026-04-21T23:24:05.941Z","created_at":"2026-04-21T18:52:08.583Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Image 2","short_name":"GPT-5.4 Image 2","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and visual generation within the same interaction.","model_version_group_id":null,"context_length":272000,"input_modalities":["image","text","file"],"output_modalities":["image","text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-image-2-20260421","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5.4-image-2-20260421/b3a54e22-0d35-4269-b3df-cee5ec2af28f/original-0.png","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5.4-image-2-20260421/b3a54e22-0d35-4269-b3df-cee5ec2af28f/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5.4-image-2-20260421/b3a54e22-0d35-4269-b3df-cee5ec2af28f/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5acf5b3b-66dd-4ee8-8db2-2eed7d795b17","name":"OpenAI | openai/gpt-5.4-image-2-20260421","context_length":272000,"model":{"slug":"openai/gpt-5.4-image-2","hf_slug":"","updated_at":"2026-04-21T23:24:05.941674+00:00","created_at":"2026-04-21T18:52:08.583899+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Image 2","short_name":"GPT-5.4 Image 2","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and visual generation within the same interaction.","model_version_group_id":null,"context_length":272000,"input_modalities":["image","text","file"],"output_modalities":["image","text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-image-2-20260421","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-image-2","model_variant_permaslug":"openai/gpt-5.4-image-2-20260421","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-2026-03-05","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000008","completion":"0.000015","image_output":"0.00003","input_cache_read":"0.000002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"8e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"8e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"8e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"15e-6","openai_responses:image_output_tokens":"30e-6","openai_responses:cached_prompt_tokens":"2e-6"},"pricing_version_id":"eb9112bb-7ccf-4ac9-9853-8659cf2b8b07","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":{"resolutions":null,"aspect_ratios":["1:1","3:2","2:3","4:3","3:4","16:9","9:16","21:9","auto"],"output_formats":null,"qualities":["auto","low","medium","high"],"backgrounds":["auto","opaque"],"n":{"min":1,"max":10},"input_references":{"min":0,"max":16},"output_compression":{"min":0,"max":100},"seed":null},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["moderation"],"capacity_tpm":null,"created_at":"2026-04-21T19:05:37.429Z","status":0}},{"slug":"~anthropic/claude-opus-latest","hf_slug":"","updated_at":"2026-05-05T04:43:04.577Z","created_at":"2026-04-21T18:16:01.446Z","hf_updated_at":null,"name":"Anthropic: Claude Opus Latest","short_name":"Claude Opus Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Claude Opus family.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-opus-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"tilde-latest-~anthropic/claude-opus-latest","name":"Claude Platform on AWS | anthropic/claude-opus-5-20260723","context_length":1000000,"model":{"slug":"~anthropic/claude-opus-latest","hf_slug":"","updated_at":"2026-05-05T04:43:04.577Z","created_at":"2026-04-21T18:16:01.446Z","hf_updated_at":null,"name":"Anthropic: Claude Opus Latest","short_name":"Claude Opus Latest","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"This model always redirects to the latest model in the Claude Opus family.","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"~anthropic/claude-opus-latest","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"~anthropic/claude-opus-latest","model_variant_permaslug":"~anthropic/claude-opus-latest","adapter_name":"ClaudeOnAwsAdapter","provider_name":"Claude Platform on AWS","provider_info":{"name":"Claude Platform on AWS","displayName":"Claude Platform on AWS","slug":"claude-on-aws","baseUrl":"https://aws-external-anthropic.us-east-1.api.aws/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"ClaudeOnAwsAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":false,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Claude Platform on AWS","provider_slug":"claude-on-aws","provider_model_id":"claude-opus-5","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity","temperature","max_completion_tokens"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"5e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":".5e-6","anthropic:completion_tokens":"25e-6","anthropic:cache_write_1h_tokens":"10e-6","anthropic:cache_write_5m_tokens":"6.25e-6"},"pricing_version_id":"e9e376f5-5c81-4454-88b8-1063473daef1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":250,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_web_fetch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-25T19:49:17.571Z","status":0}},{"slug":"openrouter/pareto-code","hf_slug":"","updated_at":"2026-05-09T18:00:04.121Z","created_at":"2026-04-21T05:05:00.602Z","hf_updated_at":null,"name":"Pareto Code Router","short_name":"Pareto Code Router","author":"openrouter","author_display_name":"OpenRouter","author_icon_uri":null,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how strong a coder you need; higher scores select stronger (and typically more expensive) models. If you omit min_coding_score, the router defaults to the High tier.\n\nSelecting Nitro from the variant dropdown ranks the models in your tier by measured throughput and routes each request to the fastest one, so you trade some model variety for lower latency.\n\nRead the [Pareto Router docs](https://openrouter.ai/docs/guides/routing/routers/pareto-router) for the full selection logic, fallback behavior, and how to customize routing. For another way to route, see the [Auto Router](/openrouter/auto).","model_version_group_id":null,"context_length":2000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openrouter/pareto-code","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":null},{"slug":"moonshotai/kimi-k2.6","hf_slug":"moonshotai/Kimi-K2.6","updated_at":"2026-07-16T18:44:02.934Z","created_at":"2026-04-20T15:36:42.832Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.6","short_name":"Kimi K2.6","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.","model_version_group_id":"4c6ad0bc-8b01-4b5f-8466-129136e36ef7","context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.6-20260420","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"78cbd7eb-84cd-46ea-8347-0578e3415f83","name":"Baidu | moonshotai/kimi-k2.6-20260420","context_length":262144,"model":{"slug":"moonshotai/kimi-k2.6","hf_slug":"moonshotai/Kimi-K2.6","updated_at":"2026-07-16T18:44:02.934284+00:00","created_at":"2026-04-20T15:36:42.832584+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.6","short_name":"Kimi K2.6","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.","model_version_group_id":"4c6ad0bc-8b01-4b5f-8466-129136e36ef7","context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.6-20260420","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2.6","model_variant_permaslug":"moonshotai/kimi-k2.6-20260420","adapter_name":"BaiduAdapter","provider_name":"Baidu","provider_info":{"name":"Baidu","displayName":"Baidu Qianfan","slug":"baidu","baseUrl":"https://api.baiduqianfan.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"BaiduAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://intl.cloud.baidu.com/en&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Baidu Qianfan","provider_slug":"baidu/fp4","provider_model_id":"kimi-k2.6","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en"},"pricing":{"prompt":"0.0000005415","completion":"0.00000228","input_cache_read":"0.0000000912","discount":0.43,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005415","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000228","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000912","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005415","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000228","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000912","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000095","openai:completion_tokens":"0.000004","openai:cached_prompt_tokens":"0.00000016"},"pricing_version_id":"74266252-a1bb-42ce-9716-876ccd8a057a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":25490000,"created_at":"2026-05-21T14:24:00.671Z","status":0}},{"slug":"anthropic/claude-opus-4.7","hf_slug":null,"updated_at":"2026-08-18T00:45:33.828Z","created_at":"2026-04-16T14:51:40.905Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.7 (batch)","short_name":"Claude Opus 4.7 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/evaluate-and-optimize/model-migrations/claude-4-7)\n","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.7-opus-20260416","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b8b72169-c315-4f28-b134-06a2497d9395","name":"Anthropic | anthropic/claude-4.7-opus-20260416:batch","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.7","hf_slug":null,"updated_at":"2026-08-18T00:45:33.828983+00:00","created_at":"2026-04-16T14:51:40.905+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.7","short_name":"Claude Opus 4.7","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/evaluate-and-optimize/model-migrations/claude-4-7)\n","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.7-opus-20260416","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.7:batch","model_variant_permaslug":"anthropic/claude-4.7-opus-20260416:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-7","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000025","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"2.5e-7","anthropic:completion_tokens":"0.0000125","anthropic:cache_write_1h_tokens":"0.000005","anthropic:cache_write_5m_tokens":"0.000003125"},"pricing_version_id":"37db2afe-1066-44c8-abfe-58d9c3c56b4e","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_web_fetch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:09:34.372Z","status":0}},{"slug":"anthropic/claude-opus-4.7","hf_slug":null,"updated_at":"2026-08-18T00:45:33.828Z","created_at":"2026-04-16T14:51:40.905Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.7","short_name":"Claude Opus 4.7","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/evaluate-and-optimize/model-migrations/claude-4-7)\n","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.7-opus-20260416","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"0fa65117-00d9-4835-808d-9b68041d9ce4","name":"Amazon Bedrock | anthropic/claude-4.7-opus-20260416","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.7","hf_slug":null,"updated_at":"2026-08-18T00:45:33.828983+00:00","created_at":"2026-04-16T14:51:40.905+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.7","short_name":"Claude Opus 4.7","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/evaluate-and-optimize/model-migrations/claude-4-7)\n","model_version_group_id":"b98cca06-1cff-4829-90c2-ef03ddfefb7d","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.7-opus-20260416","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","amazon-bedrock/eu-west-1","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.7","model_variant_permaslug":"anthropic/claude-4.7-opus-20260416","adapter_name":"InternalStreamAmazonBedrockInvokeAnthropicAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock (Global)","slug":"amazon-bedrock/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Amazon Bedrock (Global)","provider_slug":"amazon-bedrock/global","provider_model_id":"global.anthropic.claude-opus-4-7","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","structured_outputs"],"excluded_parameters":["temperature","top_p","top_k"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":"5e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":".5e-6","anthropic:completion_tokens":"25e-6","anthropic:cache_write_1h_tokens":"10e-6","anthropic:cache_write_5m_tokens":"6.25e-6"},"pricing_version_id":"2fdff15f-6743-40ee-8ca7-82b599d51c34","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-15T18:20:57.584Z","status":0}},{"slug":"z-ai/glm-5.1","hf_slug":"zai-org/GLM-5.1","updated_at":"2026-04-07T17:39:47.767Z","created_at":"2026-04-07T16:07:05.031Z","hf_updated_at":null,"name":"Z.ai: GLM 5.1","short_name":"GLM 5.1","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.1-20260406","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"44b42eb7-1926-4e06-99ce-29b6f710b86f","name":"Baidu | z-ai/glm-5.1-20260406","context_length":202752,"model":{"slug":"z-ai/glm-5.1","hf_slug":"zai-org/GLM-5.1","updated_at":"2026-04-07T17:39:47.767489+00:00","created_at":"2026-04-07T16:07:05.031+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5.1","short_name":"GLM 5.1","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.","model_version_group_id":null,"context_length":202752,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5.1-20260406","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5.1","model_variant_permaslug":"z-ai/glm-5.1-20260406","adapter_name":"BaiduAdapter","provider_name":"Baidu","provider_info":{"name":"Baidu","displayName":"Baidu Qianfan","slug":"baidu","baseUrl":"https://api.baiduqianfan.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"BaiduAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://intl.cloud.baidu.com/en&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Baidu Qianfan","provider_slug":"baidu/fp8","provider_model_id":"glm-5.1","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","privacyPolicyURL":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en"},"pricing":{"prompt":"0.000000896","completion":"0.000002816","input_cache_read":"0.0000001664","discount":0.36,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000896","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002816","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001664","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000896","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002816","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001664","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000014","openai:completion_tokens":"0.0000044","openai:cached_prompt_tokens":"0.00000026"},"pricing_version_id":"d03336e2-a101-42c5-823e-f15e37b2d0d7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":6600000,"created_at":"2026-05-14T14:06:29.585Z","status":0}},{"slug":"google/gemma-4-26b-a4b-it","hf_slug":"google/gemma-4-26B-A4B-it","updated_at":"2026-04-03T17:24:33.755Z","created_at":"2026-04-03T14:53:09.504Z","hf_updated_at":null,"name":"Google: Gemma 4 26B A4B  (free)","short_name":"Gemma 4 26B A4B  (free)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-26b-a4b-it-20260403","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9d057a54-dce2-49d5-af13-f063a029b2ef","name":"Google AI Studio | google/gemma-4-26b-a4b-it-20260403:free","context_length":262144,"model":{"slug":"google/gemma-4-26b-a4b-it","hf_slug":"google/gemma-4-26B-A4B-it","updated_at":"2026-04-03T17:24:33.755104+00:00","created_at":"2026-04-03T14:53:09.504543+00:00","hf_updated_at":null,"name":"Google: Gemma 4 26B A4B ","short_name":"Gemma 4 26B A4B ","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-26b-a4b-it-20260403","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-4-26b-a4b-it:free","model_variant_permaslug":"google/gemma-4-26b-a4b-it-20260403:free","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemma-4-26b-a4b-it","quantization":"unknown","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":"0","gemini:reasoning_tokens":"0","gemini:completion_tokens":"0","gemini:text_input_tokens":"0","gemini:audio_input_tokens":"0","gemini:image_input_tokens":"0","gemini:video_input_tokens":"0","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"6d9c64b3-cb14-4b66-a47e-4734e0def761","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-03T14:56:24.512Z","status":0}},{"slug":"google/gemma-4-26b-a4b-it","hf_slug":"google/gemma-4-26B-A4B-it","updated_at":"2026-04-03T17:24:33.755Z","created_at":"2026-04-03T14:53:09.504Z","hf_updated_at":null,"name":"Google: Gemma 4 26B A4B ","short_name":"Gemma 4 26B A4B ","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-26b-a4b-it-20260403","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0e9b72a2-e1eb-45bd-adc5-81f0f31e185f","name":"Darkbloom | google/gemma-4-26b-a4b-it-20260403","context_length":131072,"model":{"slug":"google/gemma-4-26b-a4b-it","hf_slug":"google/gemma-4-26B-A4B-it","updated_at":"2026-04-03T17:24:33.755104+00:00","created_at":"2026-04-03T14:53:09.504543+00:00","hf_updated_at":null,"name":"Google: Gemma 4 26B A4B ","short_name":"Gemma 4 26B A4B ","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-26b-a4b-it-20260403","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-4-26b-a4b-it","model_variant_permaslug":"google/gemma-4-26b-a4b-it-20260403","adapter_name":"DarkbloomAdapter","provider_name":"Darkbloom","provider_info":{"name":"Darkbloom","displayName":"Darkbloom","slug":"darkbloom","baseUrl":"https://api.darkbloom.dev/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.darkbloom.dev/terms.html","privacyPolicyURL":"https://www.darkbloom.dev/privacy.html","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"DarkbloomAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"/images/icons/Darkbloom.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Darkbloom","provider_slug":"darkbloom","provider_model_id":"gemma-4-26b-a4b-it","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.darkbloom.dev/terms.html","privacyPolicyURL":"https://www.darkbloom.dev/privacy.html"},"pricing":{"prompt":"0.000000042","completion":"0.00000022","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000042","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000042","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000042","openai:completion_tokens":"0.00000022"},"pricing_version_id":"233ffb0d-68d3-4809-a709-e7bee09723bf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-17T02:17:07.792Z","status":0}},{"slug":"google/gemma-4-31b-it","hf_slug":"google/gemma-4-31B-it","updated_at":"2026-04-03T11:33:51.350Z","created_at":"2026-04-02T16:48:06.471Z","hf_updated_at":null,"name":"Google: Gemma 4 31B (free)","short_name":"Gemma 4 31B (free)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-31b-it-20260402","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"65b19119-a8d5-427b-9cbd-03329ef0d939","name":"Google AI Studio | google/gemma-4-31b-it-20260402:free","context_length":262144,"model":{"slug":"google/gemma-4-31b-it","hf_slug":"google/gemma-4-31B-it","updated_at":"2026-04-03T11:33:51.350841+00:00","created_at":"2026-04-02T16:48:06.471117+00:00","hf_updated_at":null,"name":"Google: Gemma 4 31B","short_name":"Gemma 4 31B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-31b-it-20260402","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-4-31b-it:free","model_variant_permaslug":"google/gemma-4-31b-it-20260402:free","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemma-4-31b-it","quantization":"unknown","variant":"free","is_free":true,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":"0","gemini:reasoning_tokens":"0","gemini:completion_tokens":"0","gemini:text_input_tokens":"0","gemini:audio_input_tokens":"0","gemini:image_input_tokens":"0","gemini:video_input_tokens":"0","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"a43dd9b5-f97b-443b-ab36-66c88f2cfa2b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-02T17:18:05.239Z","status":0}},{"slug":"google/gemma-4-31b-it","hf_slug":"google/gemma-4-31B-it","updated_at":"2026-04-03T11:33:51.350Z","created_at":"2026-04-02T16:48:06.471Z","hf_updated_at":null,"name":"Google: Gemma 4 31B","short_name":"Gemma 4 31B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-31b-it-20260402","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6498d998-23ad-4dc5-b98f-9dee5a48d290","name":"OpenInference | google/gemma-4-31b-it-20260402","context_length":262144,"model":{"slug":"google/gemma-4-31b-it","hf_slug":"google/gemma-4-31B-it","updated_at":"2026-04-03T11:33:51.350841+00:00","created_at":"2026-04-02T16:48:06.471117+00:00","hf_updated_at":null,"name":"Google: Gemma 4 31B","short_name":"Gemma 4 31B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemma","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-4-31b-it-20260402","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-4-31b-it","model_variant_permaslug":"google/gemma-4-31b-it-20260402","adapter_name":"OpenInferenceAdapter","provider_name":"OpenInference","provider_info":{"name":"OpenInference","displayName":"OpenInference","slug":"open-inference","baseUrl":"https://api.openinference.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.openinference.ai/terms","privacyPolicyURL":"https://www.openinference.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"OpenInferenceAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://openinference.xyz/&size=256","className":"invert dark:invert-0"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenInference","provider_slug":"open-inference/bf16","provider_model_id":"google/gemma-4-31B-it","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","stop","seed","response_format","tools","tool_choice","structured_outputs","top_p","frequency_penalty","presence_penalty"],"excluded_parameters":["logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.openinference.ai/terms","privacyPolicyURL":"https://www.openinference.ai/privacy"},"pricing":{"prompt":"0.00000008","completion":"0.00000035","input_cache_read":"0.00000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000008","openai:completion_tokens":"0.00000035","openai:cached_prompt_tokens":"0.00000001"},"pricing_version_id":"15dc591e-90e3-4ee2-b771-fcc7820fff4a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":60,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_base64_video_input":false,"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-13T20:47:44.087Z","status":0}},{"slug":"qwen/qwen3.6-plus","hf_slug":"","updated_at":"2026-04-27T03:32:21.206Z","created_at":"2026-04-02T12:39:17.573Z","hf_updated_at":null,"name":"Qwen: Qwen3.6 Plus","short_name":"Qwen3.6 Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verified. It represents a substantial leap in both pure-text and multimodal capabilities, performing at the level of leading state-of-the-art models.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free model has been deprecated. Transition to qwen/qwen3.6-plus for continued paid access.","required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-plus-04-02","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2102b4bc-ef48-4aab-964c-33e043b3f3f2","name":"Alibaba | qwen/qwen3.6-plus-04-02","context_length":1000000,"model":{"slug":"qwen/qwen3.6-plus","hf_slug":"","updated_at":"2026-04-27T03:32:21.206851+00:00","created_at":"2026-04-02T12:39:17.573323+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.6 Plus","short_name":"Qwen3.6 Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verified. It represents a substantial leap in both pure-text and multimodal capabilities, performing at the level of leading state-of-the-art models.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free model has been deprecated. Transition to qwen/qwen3.6-plus for continued paid access.","required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.6-plus-04-02","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.6-plus","model_variant_permaslug":"qwen/qwen3.6-plus-04-02","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.6-plus","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000325","completion":"0.00000195","input_cache_write":"0.00000040625","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.0000013","completion":"0.0000039","input_cache_write":"0.000001625"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000325"},{"sku_label":">256K","price":"0.0000013"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000195","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000195"},{"sku_label":">256K","price":"0.0000039"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000040625","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000040625"},{"sku_label":">256K","price":"0.000001625"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000000325"},{"sku_label":">256K","price":"0.00000013"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000325"},{"sku_label":">256K","price":"0.0000013"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000195","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000195"},{"sku_label":">256K","price":"0.0000039"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000040625","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000040625"},{"sku_label":">256K","price":"0.000001625"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.0000000325"},{"sku_label":">256K","price":"0.00000013"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.000000325","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.00000195","alibaba:prompt_tokens_tier2":"0.0000013","alibaba:cache_creation_tokens":"0.00000040625","alibaba:completion_tokens_tier2":"0.0000039","alibaba:cache_creation_tokens_tier2":"0.000001625","alibaba:explicit_cached_prompt_tokens":"0.0000000325","alibaba:explicit_cached_prompt_tokens_tier2":"0.00000013"},"pricing_version_id":"bb3e66bd-9536-4ba3-b7f3-8e143b8e98f6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_base64_video_input":true,"supports_video_urls":true,"disable_free_endpoint_limits":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":{},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-07T15:01:17.939Z","status":0}},{"slug":"z-ai/glm-5v-turbo","hf_slug":"","updated_at":"2026-04-01T17:00:01.920Z","created_at":"2026-04-01T16:37:38.290Z","hf_updated_at":null,"name":"Z.ai: GLM 5V Turbo","short_name":"GLM 5V Turbo","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.","model_version_group_id":null,"context_length":202752,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5v-turbo-20260401","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a3b0220b-6a75-47bd-aa99-70f955e5b84d","name":"Z.AI | z-ai/glm-5v-turbo-20260401","context_length":202752,"model":{"slug":"z-ai/glm-5v-turbo","hf_slug":"","updated_at":"2026-04-01T17:00:01.920442+00:00","created_at":"2026-04-01T16:37:38.290675+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5V Turbo","short_name":"GLM 5V Turbo","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.","model_version_group_id":null,"context_length":202752,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5v-turbo-20260401","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5v-turbo","model_variant_permaslug":"z-ai/glm-5v-turbo-20260401","adapter_name":"ZAIAdapter","provider_name":"Z.AI","provider_info":{"name":"Z.AI","displayName":"Z.ai","slug":"z-ai","baseUrl":"https://api.z.ai/api/paas/v4","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"ZAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://z.ai/model-api&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Z.ai","provider_slug":"z-ai/fp8","provider_model_id":"glm-5v-turbo","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","top_k"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy"},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.24e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.24e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"1.2e-6","openai:completion_tokens":"4e-6","openai:cached_prompt_tokens":"0.24e-6"},"pricing_version_id":"77c3ca02-1f16-4cd2-b042-0573fe1721b4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":{},"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2098-12-31T16:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-01T16:42:35.583Z","status":0}},{"slug":"arcee-ai/trinity-large-thinking","hf_slug":"arcee-ai/Trinity-Large-Thinking","updated_at":"2026-05-11T18:55:13.279Z","created_at":"2026-04-01T15:45:18.036Z","hf_updated_at":null,"name":"Arcee AI: Trinity Large Thinking","short_name":"Trinity Large Thinking","author":"arcee-ai","author_display_name":"arcee-ai","author_icon_uri":null,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7\n\nThis model is optimized for agentic workflows and performs best when reasoning is preserved (aka interleaved thinking). Learn how to preserve reasoning in our docs: https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"arcee-ai/trinity-large-thinking","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":0.8,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"c6203380-90d0-4ded-be03-0fbcf3aad22c","name":"Parasail | arcee-ai/trinity-large-thinking","context_length":262144,"model":{"slug":"arcee-ai/trinity-large-thinking","hf_slug":"arcee-ai/Trinity-Large-Thinking","updated_at":"2026-05-11T18:55:13.279609+00:00","created_at":"2026-04-01T15:45:18.036+00:00","hf_updated_at":null,"name":"Arcee AI: Trinity Large Thinking","short_name":"Trinity Large Thinking","author":"arcee-ai","author_display_name":"arcee-ai","author_icon_uri":null,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7\n\nThis model is optimized for agentic workflows and performs best when reasoning is preserved (aka interleaved thinking). Learn how to preserve reasoning in our docs: https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"arcee-ai/trinity-large-thinking","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":0.8,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"arcee-ai/trinity-large-thinking","model_variant_permaslug":"arcee-ai/trinity-large-thinking","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/fp4","provider_model_id":"parasail-trinity-large-thinking","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000022","completion":"0.00000085","input_cache_read":"0.00000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000022","openai:completion_tokens":"0.00000085","openai:cached_prompt_tokens":"0.00000006"},"pricing_version_id":"84172733-37d2-4357-945b-cb3f9465e381","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-20T11:46:06.762Z","status":0}},{"slug":"x-ai/grok-4.20-multi-agent","hf_slug":"","updated_at":"2026-08-04T17:55:06.870Z","created_at":"2026-03-31T17:45:58.343Z","hf_updated_at":null,"name":"SpaceXAI: Grok 4.20 Multi-Agent","short_name":"Grok 4.20 Multi-Agent","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.\n\nReasoning effort behavior:\n- low / medium: 4 agents\n- high / xhigh: 16 agents","model_version_group_id":null,"context_length":2000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.20-multi-agent-20260309","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-09-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"5f5b5f6c-e80d-4b77-9c06-d1cb35452bab","name":"xAI | x-ai/grok-4.20-multi-agent-20260309","context_length":2000000,"model":{"slug":"x-ai/grok-4.20-multi-agent","hf_slug":"","updated_at":"2026-08-04T17:55:06.870168+00:00","created_at":"2026-03-31T17:45:58.343536+00:00","hf_updated_at":null,"name":"SpaceXAI: Grok 4.20 Multi-Agent","short_name":"Grok 4.20 Multi-Agent","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.\n\nReasoning effort behavior:\n- low / medium: 4 agents\n- high / xhigh: 16 agents","model_version_group_id":null,"context_length":2000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.20-multi-agent-20260309","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":false,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-09-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"x-ai/grok-4.20-multi-agent","model_variant_permaslug":"x-ai/grok-4.20-multi-agent-20260309","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai/zdr","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI (ZDR)","provider_slug":"xai/zdr","provider_model_id":"grok-4.20-multi-agent-0309","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"2.5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000025"},{"sku_label":">200K","price":"5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":"0.4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"2.5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000025"},{"sku_label":">200K","price":"5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":"0.4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"0.00000125","xai_responses:x_search_calls":"0.005","xai_responses:web_search_calls":"0.005","xai_responses:completion_tokens":"0.0000025","xai_responses:cached_prompt_tokens":"0.0000002","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"2.5e-6","xai_responses:completion_tokens_high_context":"5e-6","xai_responses:usage_guidelines_violation_fee":"0.05","xai_responses:cached_prompt_tokens_high_context":"0.4e-6"},"pricing_version_id":"76369f87-6edd-450b-b2f7-e12a58f8bbaf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-25T20:45:03.812Z","status":0}},{"slug":"x-ai/grok-4.20","hf_slug":"","updated_at":"2026-08-04T17:55:07.777Z","created_at":"2026-03-31T17:43:39.677Z","hf_updated_at":null,"name":"SpaceXAI: Grok 4.20","short_name":"Grok 4.20","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)","model_version_group_id":null,"context_length":2000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.20-20260309","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-09-01T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b17f55ac-e8fa-47ef-9e2e-5081c2124c7d","name":"xAI | x-ai/grok-4.20-20260309","context_length":2000000,"model":{"slug":"x-ai/grok-4.20","hf_slug":"","updated_at":"2026-08-04T17:55:07.777951+00:00","created_at":"2026-03-31T17:43:39.677744+00:00","hf_updated_at":null,"name":"SpaceXAI: Grok 4.20","short_name":"Grok 4.20","author":"x-ai","author_display_name":"SpaceXAI","author_icon_uri":null,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)","model_version_group_id":null,"context_length":2000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Grok","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"x-ai/grok-4.20-20260309","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["xai","xai/zdr"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-09-01T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"x-ai/grok-4.20","model_variant_permaslug":"x-ai/grok-4.20-20260309","adapter_name":"XAIResponsesAdapter","provider_name":"xAI","provider_info":{"name":"xAI","displayName":"SpaceXAI","slug":"xai/zdr","baseUrl":"https://api.x.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"XAIResponsesAdapter","statusPageUrl":"https://status.x.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://x.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"xai_responses"},"provider_display_name":"SpaceXAI (ZDR)","provider_slug":"xai/zdr","provider_model_id":"grok-4.20-0309-non-reasoning","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"excluded_parameters":["reasoning_effort"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://x.ai/legal/terms-of-service-enterprise","privacyPolicyURL":"https://x.ai/legal/privacy-policy","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"2.5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000025"},{"sku_label":">200K","price":"5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":"0.4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"2.5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000025"},{"sku_label":">200K","price":"5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000002"},{"sku_label":">200K","price":"0.4e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"xai_responses:prompt_tokens":"0.00000125","xai_responses:x_search_calls":"0.005","xai_responses:web_search_calls":"0.005","xai_responses:completion_tokens":"0.0000025","xai_responses:cached_prompt_tokens":"0.0000002","xai_responses:high_context_threshold":"200000","xai_responses:priority_tier_multiplier":"2","xai_responses:prompt_tokens_high_context":"2.5e-6","xai_responses:completion_tokens_high_context":"5e-6","xai_responses:usage_guidelines_violation_fee":"0.05","xai_responses:cached_prompt_tokens_high_context":"0.4e-6"},"pricing_version_id":"4244936c-23e9-4d4c-a94e-bfda484a9489","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_file_input":false,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-25T20:45:03.316Z","status":0}},{"slug":"google/lyria-3-pro-preview","hf_slug":null,"updated_at":"2026-05-12T14:52:02.531Z","created_at":"2026-03-30T21:48:06.546Z","hf_updated_at":null,"name":"Google: Lyria 3 Pro Preview","short_name":"Lyria 3 Pro Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Pro can generate full-length songs with verses, choruses, bridges.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text","audio"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/lyria-3-pro-preview-20260330","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"82959141-f095-4f8f-92ce-f9b751be41e6","name":"Google AI Studio | google/lyria-3-pro-preview-20260330","context_length":1048576,"model":{"slug":"google/lyria-3-pro-preview","hf_slug":null,"updated_at":"2026-05-12T14:52:02.531375+00:00","created_at":"2026-03-30T21:48:06.546+00:00","hf_updated_at":null,"name":"Google: Lyria 3 Pro Preview","short_name":"Lyria 3 Pro Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Pro can generate full-length songs with verses, choruses, bridges.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text","audio"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/lyria-3-pro-preview-20260330","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/lyria-3-pro-preview","model_variant_permaslug":"google/lyria-3-pro-preview-20260330","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"google_lyria"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"lyria-3-pro-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"unit","sku_label":"Song Generation","price":"0.08","displayMultiplier":1,"unitLabel":"/song"}]},"display_pricing":[{"kind":"unit","sku_label":"Song Generation","price":"0.08","displayMultiplier":1,"unitLabel":"/song"}],"pricing_json":{"google_lyria:song_generation":"0.08"},"pricing_version_id":"6cfa748d-ab2e-45a7-a7cc-d2db0113e11e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":false,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-30T20:55:17.376Z","status":0}},{"slug":"google/lyria-3-clip-preview","hf_slug":null,"updated_at":"2026-03-30T21:47:56.013Z","created_at":"2026-03-30T21:47:35.284Z","hf_updated_at":null,"name":"Google: Lyria 3 Clip Preview","short_name":"Lyria 3 Clip Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Clip can generate short clips, loops, previews.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text","audio"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/lyria-3-clip-preview-20260330","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3aa2798e-0bbd-44f0-89a9-e949e169633d","name":"Google AI Studio | google/lyria-3-clip-preview-20260330","context_length":1048576,"model":{"slug":"google/lyria-3-clip-preview","hf_slug":null,"updated_at":"2026-03-30T21:47:56.013853+00:00","created_at":"2026-03-30T21:47:35.284+00:00","hf_updated_at":null,"name":"Google: Lyria 3 Clip Preview","short_name":"Lyria 3 Clip Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Clip can generate short clips, loops, previews.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text","audio"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/lyria-3-clip-preview-20260330","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/lyria-3-clip-preview","model_variant_permaslug":"google/lyria-3-clip-preview-20260330","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"google_lyria"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"lyria-3-clip-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"unit","sku_label":"Song Generation","price":"0.04","displayMultiplier":1,"unitLabel":"/song"}]},"display_pricing":[{"kind":"unit","sku_label":"Song Generation","price":"0.04","displayMultiplier":1,"unitLabel":"/song"}],"pricing_json":{"google_lyria:song_generation":"0.04"},"pricing_version_id":"97c7c832-dbb6-4959-a5fe-0a7eb95fabf0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":false,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-30T20:55:17.376Z","status":0}},{"slug":"kwaipilot/kat-coder-pro-v2","hf_slug":"","updated_at":"2026-03-28T00:29:44.320Z","created_at":"2026-03-27T22:08:30.640Z","hf_updated_at":null,"name":"Kwaipilot: KAT-Coder-Pro V2","short_name":"KAT-Coder-Pro V2","author":"kwaipilot","author_display_name":"kwaipilot","author_icon_uri":null,"description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions, with a focus on large-scale production environments, multi-system coordination, and seamless integration across modern software stacks, while also supporting web aesthetics generation to produce production-grade landing pages and presentation decks.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"kwaipilot/kat-coder-pro-v2-20260327","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"aa630b00-cc39-41e5-b1cd-de31a1b95d43","name":"StreamLake | kwaipilot/kat-coder-pro-v2-20260327","context_length":256000,"model":{"slug":"kwaipilot/kat-coder-pro-v2","hf_slug":"","updated_at":"2026-03-28T00:29:44.320758+00:00","created_at":"2026-03-27T22:08:30.640848+00:00","hf_updated_at":null,"name":"Kwaipilot: KAT-Coder-Pro V2","short_name":"KAT-Coder-Pro V2","author":"kwaipilot","author_display_name":"kwaipilot","author_icon_uri":null,"description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions, with a focus on large-scale production environments, multi-system coordination, and seamless integration across modern software stacks, while also supporting web aesthetics generation to produce production-grade landing pages and presentation decks.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"kwaipilot/kat-coder-pro-v2-20260327","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"kwaipilot/kat-coder-pro-v2","model_variant_permaslug":"kwaipilot/kat-coder-pro-v2-20260327","adapter_name":"StreamLakeAdapter","provider_name":"StreamLake","provider_info":{"name":"StreamLake","displayName":"StreamLake","slug":"streamlake","baseUrl":"https://vanchin.streamlake.ai/api/gateway/v1/endpoints","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"StreamLakeAdapter","statusPageUrl":"https://status.streamlake.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.streamlake.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"StreamLake","provider_slug":"streamlake","provider_model_id":"ep-zt08ah-1774648418751969715","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":80000,"max_tokens_per_image":null,"supported_parameters":["tool_choice","tools","max_tokens","temperature","top_p","stop","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54"},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000012","openai:cached_prompt_tokens":"0.00000006"},"pricing_version_id":"7cb7795f-108b-44ba-9a2b-085dc5592ccf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-27T22:28:32.328Z","status":0}},{"slug":"rekaai/reka-edge","hf_slug":"RekaAI/reka-edge-2603","updated_at":"2026-04-01T13:27:11.516Z","created_at":"2026-03-20T17:16:05.541Z","hf_updated_at":null,"name":"Reka Edge","short_name":"Reka Edge","author":"rekaai","author_display_name":"rekaai","author_icon_uri":null,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding, video analysis, object detection, and agentic tool-use.","model_version_group_id":null,"context_length":16384,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"rekaai/reka-edge-2603","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0cd3013f-24e9-467d-a617-6232877aedb9","name":"Reka | rekaai/reka-edge-2603","context_length":16384,"model":{"slug":"rekaai/reka-edge","hf_slug":"RekaAI/reka-edge-2603","updated_at":"2026-04-01T13:27:11.516648+00:00","created_at":"2026-03-20T17:16:05.541274+00:00","hf_updated_at":null,"name":"Reka Edge","short_name":"Reka Edge","author":"rekaai","author_display_name":"rekaai","author_icon_uri":null,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding, video analysis, object detection, and agentic tool-use.","model_version_group_id":null,"context_length":16384,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"rekaai/reka-edge-2603","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"rekaai/reka-edge","model_variant_permaslug":"rekaai/reka-edge-2603","adapter_name":"OpenAIAdapter","provider_name":"Reka","provider_info":{"name":"Reka","displayName":"Reka AI","slug":"reka","baseUrl":"https://api.reka.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://reka.ai/legal/terms-of-use","privacyPolicyURL":"https://reka.ai/legal/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://reka.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Reka AI","provider_slug":"reka/bf16","provider_model_id":"reka-edge-2603","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["tool_choice","tools","top_k","top_p","stop","seed","temperature","frequency_penalty","presence_penalty","max_tokens","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://reka.ai/legal/terms-of-use","privacyPolicyURL":"https://reka.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000001"},"pricing_version_id":"d3424fe3-da00-4704-9b13-bb4c0669017c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-20T17:38:08.282Z","status":0}},{"slug":"minimax/minimax-m2.7","hf_slug":"MiniMaxAI/MiniMax-M2.7","updated_at":"2026-03-18T13:14:17.052Z","created_at":"2026-03-18T12:24:57.176Z","hf_updated_at":null,"name":"MiniMax: MiniMax M2.7","short_name":"MiniMax M2.7","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\n\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2.7-20260318","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"00366232-455a-441e-906a-4da12292f801","name":"Mara | minimax/minimax-m2.7-20260318","context_length":196608,"model":{"slug":"minimax/minimax-m2.7","hf_slug":"MiniMaxAI/MiniMax-M2.7","updated_at":"2026-03-18T13:14:17.052826+00:00","created_at":"2026-03-18T12:24:57.176001+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M2.7","short_name":"MiniMax M2.7","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\n\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2.7-20260318","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m2.7","model_variant_permaslug":"minimax/minimax-m2.7-20260318","adapter_name":"OpenAIAdapter","provider_name":"Mara","provider_info":{"name":"Mara","displayName":"MARA","slug":"mara","baseUrl":"https://api.cloud.mara.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.mara.com/mara-legals/ai-policies#cloud-toc","privacyPolicyURL":"https://www.mara.com/mara-legals/ai-policies#cloud-pp","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.mara.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"MARA","provider_slug":"mara","provider_model_id":"MiniMax-M2.7","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":196608,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.mara.com/mara-legals/ai-policies#cloud-toc","privacyPolicyURL":"https://www.mara.com/mara-legals/ai-policies#cloud-pp"},"pricing":{"prompt":"0.00000024","completion":"0.00000096","discount":0.6,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000024","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000096","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000024","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000096","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000006","openai:completion_tokens":"0.0000024"},"pricing_version_id":"969058ea-3e90-479d-ae04-e95c24048217","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-21T20:07:30.893Z","status":-2}},{"slug":"openai/gpt-5.4-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-03-17T11:49:47.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Nano (batch)","short_name":"GPT-5.4 Nano (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-nano-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"44ec9d1d-751b-4da6-a664-fa57248bca38","name":"OpenAI | openai/gpt-5.4-nano-20260317:batch","context_length":400000,"model":{"slug":"openai/gpt-5.4-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-03-17T11:49:47+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Nano","short_name":"GPT-5.4 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-nano-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-nano:batch","model_variant_permaslug":"openai/gpt-5.4-nano-20260317:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-nano-2026-03-17","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000001","completion":"0.000000625","input_cache_read":"0.00000001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.000000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.000000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.000000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"6.250000e-7","openai_responses:cached_prompt_tokens":"1.000000e-8","openai_responses:flex_tier_multiplier":"0.5"},"pricing_version_id":"8212d833-7827-42ae-9741-43ee44efbcf6","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:54.707Z","status":0}},{"slug":"openai/gpt-5.4-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-03-17T11:49:47.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Nano","short_name":"GPT-5.4 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-nano-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f","name":"OpenAI | openai/gpt-5.4-nano-20260317","context_length":400000,"model":{"slug":"openai/gpt-5.4-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-03-17T11:49:47+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Nano","short_name":"GPT-5.4 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-nano-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-nano","model_variant_permaslug":"openai/gpt-5.4-nano-20260317","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-nano-2026-03-17","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000002","completion":"0.00000125","input_cache_read":"0.00000002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.02e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.02e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.2e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"1.25e-6","openai_responses:cached_prompt_tokens":"0.02e-6","openai_responses:flex_tier_multiplier":"0.5"},"pricing_version_id":"657abaab-9065-4045-9afa-294309ade223","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-16T16:08:09.861Z","status":-2}},{"slug":"openai/gpt-5.4-mini","hf_slug":"","updated_at":"2026-04-27T19:36:47.189Z","created_at":"2026-03-17T11:49:38.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Mini (batch)","short_name":"GPT-5.4 Mini (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","model_version_group_id":"ff27acaa-273d-45ee-be59-d9667cd68b4f","context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-mini-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b6a2b660-f0f1-429e-9ff7-24c0d96f7570","name":"OpenAI | openai/gpt-5.4-mini-20260317:batch","context_length":400000,"model":{"slug":"openai/gpt-5.4-mini","hf_slug":"","updated_at":"2026-04-27T19:36:47.189148+00:00","created_at":"2026-03-17T11:49:38+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Mini","short_name":"GPT-5.4 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","model_version_group_id":"ff27acaa-273d-45ee-be59-d9667cd68b4f","context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-mini-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-mini:batch","model_variant_permaslug":"openai/gpt-5.4-mini-20260317:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-mini-2026-03-17","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000375","completion":"0.00000225","input_cache_read":"0.0000000375","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.250000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3.750000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.250000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3.750000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"3.750000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"2.250000e-6","openai_responses:cached_prompt_tokens":"3.750000e-8","openai_responses:flex_tier_multiplier":"0.5","openai_responses:priority_tier_multiplier":"2"},"pricing_version_id":"49cc59a5-e9d4-4bc8-9713-b8aa85b4dba6","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:53.997Z","status":0}},{"slug":"openai/gpt-5.4-mini","hf_slug":"","updated_at":"2026-04-27T19:36:47.189Z","created_at":"2026-03-17T11:49:38.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Mini","short_name":"GPT-5.4 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","model_version_group_id":"ff27acaa-273d-45ee-be59-d9667cd68b4f","context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-mini-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"689cfb85-f673-4da5-961a-4f4711cc7d88","name":"Azure | openai/gpt-5.4-mini-20260317","context_length":400000,"model":{"slug":"openai/gpt-5.4-mini","hf_slug":"","updated_at":"2026-04-27T19:36:47.189148+00:00","created_at":"2026-03-17T11:49:38+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Mini","short_name":"GPT-5.4 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","model_version_group_id":"ff27acaa-273d-45ee-be59-d9667cd68b4f","context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-mini-20260317","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","none","xhigh"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-08-31T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-mini","model_variant_permaslug":"openai/gpt-5.4-mini-20260317","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.4-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000075","completion":"0.0000045","input_cache_read":"0.000000075","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.75e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.075e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.75e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.075e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"0.75e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"4.5e-6","openai_responses:cached_prompt_tokens":"0.075e-6"},"pricing_version_id":"63988824-363a-4715-9462-89de743b8eab","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_resolutions":null,"supported_aspect_ratios":null,"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-16T18:01:59.363Z","status":0}},{"slug":"mistralai/mistral-small-2603","hf_slug":"mistralai/Mistral-Small-4-119B-2603","updated_at":"2026-03-17T11:49:18.493Z","created_at":"2026-03-16T21:14:45.935Z","hf_updated_at":null,"name":"Mistral: Mistral Small 4","short_name":"Mistral Small 4","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-2603","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","high"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","high"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7a90a100-ff71-4d05-bb5d-7e65632eddbf","name":"Mistral | mistralai/mistral-small-2603","context_length":262144,"model":{"slug":"mistralai/mistral-small-2603","hf_slug":"mistralai/Mistral-Small-4-119B-2603","updated_at":"2026-03-17T11:49:18.49398+00:00","created_at":"2026-03-16T21:14:45.935052+00:00","hf_updated_at":null,"name":"Mistral: Mistral Small 4","short_name":"Mistral Small 4","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-2603","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","high"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","high"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-small-2603","model_variant_permaslug":"mistralai/mistral-small-2603","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral/zdr","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral (ZDR)","provider_slug":"mistral/zdr","provider_model_id":"mistral-small-2603","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.00000015","mistral:completion_tokens":"0.0000006","mistral:cached_prompt_tokens":"0.000000015"},"pricing_version_id":"f1325a5c-8074-40ed-81d3-974a146bbb56","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T16:05:16.895Z","status":-5}},{"slug":"z-ai/glm-5-turbo","hf_slug":"","updated_at":"2026-03-15T14:55:14.787Z","created_at":"2026-03-15T14:06:13.880Z","hf_updated_at":null,"name":"Z.ai: GLM 5 Turbo","short_name":"GLM 5 Turbo","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.","model_version_group_id":null,"context_length":202752,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5-turbo-20260315","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9ce3b132-3a17-4fea-8092-0e8e519ed32b","name":"Z.AI | z-ai/glm-5-turbo-20260315","context_length":202752,"model":{"slug":"z-ai/glm-5-turbo","hf_slug":"","updated_at":"2026-03-15T14:55:14.787666+00:00","created_at":"2026-03-15T14:06:13.880167+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5 Turbo","short_name":"GLM 5 Turbo","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.","model_version_group_id":null,"context_length":202752,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5-turbo-20260315","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5-turbo","model_variant_permaslug":"z-ai/glm-5-turbo-20260315","adapter_name":"ZAIAdapter","provider_name":"Z.AI","provider_info":{"name":"Z.AI","displayName":"Z.ai","slug":"z-ai","baseUrl":"https://api.z.ai/api/paas/v4","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"ZAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://z.ai/model-api&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Z.ai","provider_slug":"z-ai","provider_model_id":"glm-5-turbo","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","top_k"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy"},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.24e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.2e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.24e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"1.2e-6","openai:completion_tokens":"4e-6","openai:cached_prompt_tokens":"0.24e-6"},"pricing_version_id":"e774fc74-80f0-454e-9179-76d90c69d197","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":{"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2098-12-31T16:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-15T14:08:16.021Z","status":0}},{"slug":"nvidia/nemotron-3-super-120b-a12b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","updated_at":"2026-07-16T20:38:47.536Z","created_at":"2026-03-11T16:07:19.000Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Super (free)","short_name":"Nemotron 3 Super (free)","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\n \nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\n \nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"970aecad-f13b-4ec3-9362-e1758aea3e56","name":"Nvidia | nvidia/nemotron-3-super-120b-a12b-20230311:free","context_length":262144,"model":{"slug":"nvidia/nemotron-3-super-120b-a12b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","updated_at":"2026-07-16T20:38:47.5364+00:00","created_at":"2026-03-11T16:07:19+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Super","short_name":"Nemotron 3 Super","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\n \nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\n \nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-super-120b-a12b:free","model_variant_permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311:free","adapter_name":"NvidiaAdapter","provider_name":"Nvidia","provider_info":{"name":"Nvidia","displayName":"NVIDIA","slug":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","dataPolicy":{"training":true,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"NvidiaAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.nvidia.com/en-us/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NVIDIA","provider_slug":"nvidia","provider_model_id":"private/nvidia/nemotron-3-super-120b-a12b","quantization":"unknown","variant":"free","is_free":true,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","seed","top_p","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":true,"trainingOpenRouter":true,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","privacyPolicyURL":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/"},"pricing":{"prompt":"0","completion":"0","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0","openai:completion_tokens":"0"},"pricing_version_id":"34aa3e1d-db04-4f14-99a3-548b00a381e0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":0,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"disable_free_endpoint_limits":false,"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-06T21:57:52.861Z","status":0}},{"slug":"nvidia/nemotron-3-super-120b-a12b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","updated_at":"2026-07-16T20:38:47.536Z","created_at":"2026-03-11T16:07:19.000Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Super","short_name":"Nemotron 3 Super","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\n \nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\n \nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b893e351-21c8-4215-8f36-c761298acf9e","name":"DeepInfra | nvidia/nemotron-3-super-120b-a12b-20230311","context_length":262144,"model":{"slug":"nvidia/nemotron-3-super-120b-a12b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","updated_at":"2026-07-16T20:38:47.5364+00:00","created_at":"2026-03-11T16:07:19+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Super","short_name":"Nemotron 3 Super","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\n \nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\n \nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium"],"default_reasoning_effort":"medium","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-super-120b-a12b","model_variant_permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.000000085","completion":"0.0000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000085","openai:completion_tokens":"0.0000004"},"pricing_version_id":"834040e7-1b02-4809-bd20-a20565bfd930","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-18T18:47:28.344Z","status":0}},{"slug":"bytedance-seed/seed-2.0-lite","hf_slug":null,"updated_at":"2026-03-12T16:39:47.420Z","created_at":"2026-03-10T15:40:31.000Z","hf_updated_at":null,"name":"ByteDance Seed: Seed-2.0-Lite","short_name":"Seed-2.0-Lite","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across text, vision, and tools. Engineered for high-frequency visual understanding and agentic workflows, it's an ideal choice for deployment at scale with minimal latency.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2.0-lite-20260309","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","minimal"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","minimal"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"bf1a3473-7a0a-46d3-aaa5-adb8f876a697","name":"Seed | bytedance-seed/seed-2.0-lite-20260309","context_length":262144,"model":{"slug":"bytedance-seed/seed-2.0-lite","hf_slug":null,"updated_at":"2026-03-12T16:39:47.420254+00:00","created_at":"2026-03-10T15:40:31+00:00","hf_updated_at":null,"name":"ByteDance Seed: Seed-2.0-Lite","short_name":"Seed-2.0-Lite","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across text, vision, and tools. Engineered for high-frequency visual understanding and agentic workflows, it's an ideal choice for deployment at scale with minimal latency.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2.0-lite-20260309","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","minimal"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","minimal"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance-seed/seed-2.0-lite","model_variant_permaslug":"bytedance-seed/seed-2.0-lite-20260309","adapter_name":"BytePlusAdapter","provider_name":"Seed","provider_info":{"name":"Seed","displayName":"Seed","slug":"seed","baseUrl":"https://ark.ap-southeast.bytepluses.com/api/v3","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"BytePlusAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256"},"sendClientIp":false,"pricingStrategy":"byteplus"},"provider_display_name":"Seed","provider_slug":"seed/fp8","provider_model_id":"ep-20260307011659-5tkmr","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","structured_outputs","tool_choice","tools","response_format","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy"},"pricing":{"prompt":"0.00000025","completion":"0.000002","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000005","completion":"0.000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.00000025"},{"sku_label":">128K","price":"0.0000005"}]},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000002"},{"sku_label":">128K","price":"0.000004"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.00000025"},{"sku_label":">128K","price":"0.0000005"}]},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000002"},{"sku_label":">128K","price":"0.000004"}]}],"pricing_json":{"byteplus:prompt_tokens":"0.00000025","byteplus:completion_tokens":"0.000002","byteplus:long_context_threshold":"128000","byteplus:prompt_tokens_long_context":"0.0000005","byteplus:completion_tokens_long_context":"0.000004"},"pricing_version_id":"e6d35cc5-5cbc-431a-8a69-82688939979e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-09T19:54:54.047Z","status":0}},{"slug":"qwen/qwen3.5-9b","hf_slug":"Qwen/Qwen3.5-9B","updated_at":"2026-03-10T14:28:45.091Z","created_at":"2026-03-10T14:19:56.963Z","hf_updated_at":null,"name":"Qwen: Qwen3.5-9B","short_name":"Qwen3.5-9B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-9b-20260310","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"073a2dde-9ebc-4ae0-840f-c84fc8f72247","name":"DeepInfra | qwen/qwen3.5-9b-20260310","context_length":262144,"model":{"slug":"qwen/qwen3.5-9b","hf_slug":"Qwen/Qwen3.5-9B","updated_at":"2026-03-10T14:28:45.09171+00:00","created_at":"2026-03-10T14:19:56.963435+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5-9B","short_name":"Qwen3.5-9B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-9b-20260310","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-9b","model_variant_permaslug":"qwen/qwen3.5-9b-20260310","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"Qwen/Qwen3.5-9B","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":81920,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000001","completion":"0.00000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.00000015"},"pricing_version_id":"c76b0072-0c06-4a42-893b-e30809825d98","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-26T07:05:54.801Z","status":0}},{"slug":"openai/gpt-5.4-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-03-05T18:12:46.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Pro (batch)","short_name":"GPT-5.4 Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-pro-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7977696f-44ea-4cc3-8e46-b303ecaf0814","name":"OpenAI | openai/gpt-5.4-pro-20260305:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.4-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-03-05T18:12:46+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Pro","short_name":"GPT-5.4 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-pro-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-pro:batch","model_variant_permaslug":"openai/gpt-5.4-pro-20260305:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-pro-2026-03-05","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000015","completion":"0.00009","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00003","completion":"0.000135"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.500000e-5"},{"sku_label":">272K","price":"3.000000e-5"}]},{"kind":"token","sku_label":"Output Price","price":"9.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"9.000000e-5"},{"sku_label":">272K","price":"1.350000e-4"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.500000e-5"},{"sku_label":">272K","price":"3.000000e-5"}]},{"kind":"token","sku_label":"Output Price","price":"9.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"9.000000e-5"},{"sku_label":">272K","price":"1.350000e-4"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.500000e-5","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"9.000000e-5","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"3.000000e-5","openai_responses:completion_tokens_high_context":"1.350000e-4"},"pricing_version_id":"e718ddde-0f9d-4720-9097-1912cf493fc1","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:24.898Z","status":0}},{"slug":"openai/gpt-5.4-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-03-05T18:12:46.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Pro","short_name":"GPT-5.4 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-pro-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"03502d26-37dd-432c-9d82-f48c0329b020","name":"Azure | openai/gpt-5.4-pro-20260305","context_length":1050000,"model":{"slug":"openai/gpt-5.4-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-03-05T18:12:46+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4 Pro","short_name":"GPT-5.4 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-pro-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4-pro","model_variant_permaslug":"openai/gpt-5.4-pro-20260305","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.4-pro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.00006","completion":"0.00027"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"60e-6"}]},{"kind":"token","sku_label":"Output Price","price":"180e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"180e-6"},{"sku_label":">272K","price":"270e-6"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"30e-6"},{"sku_label":">272K","price":"60e-6"}]},{"kind":"token","sku_label":"Output Price","price":"180e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"180e-6"},{"sku_label":">272K","price":"270e-6"}]}],"pricing_json":{"openai_responses:prompt_tokens":"30e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"180e-6","openai_responses:high_context_threshold":"272000","openai_responses:prompt_tokens_high_context":"60e-6","openai_responses:completion_tokens_high_context":"270e-6"},"pricing_version_id":"f8f57864-831f-497c-b93b-659d9f8f22d3","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-16T17:58:11.140Z","status":0}},{"slug":"openai/gpt-5.4","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-03-05T18:12:32.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4 (batch)","short_name":"GPT-5.4 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"beed36e2-016a-425b-b16a-fdcb5ad481c8","name":"OpenAI | openai/gpt-5.4-20260305:batch","context_length":1050000,"model":{"slug":"openai/gpt-5.4","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-03-05T18:12:32+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4","short_name":"GPT-5.4","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4:batch","model_variant_permaslug":"openai/gpt-5.4-20260305:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-2026-03-05","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.0000075","input_cache_read":"0.000000125","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000025","completion":"0.00001125","input_cache_read":"0.00000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.250000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.250000e-6"},{"sku_label":">272K","price":"2.500000e-6"}]},{"kind":"token","sku_label":"Output Price","price":"7.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"7.500000e-6"},{"sku_label":">272K","price":"1.125000e-5"}]},{"kind":"token","sku_label":"Cache Read","price":"1.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.250000e-7"},{"sku_label":">272K","price":"2.500000e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.250000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.250000e-6"},{"sku_label":">272K","price":"2.500000e-6"}]},{"kind":"token","sku_label":"Output Price","price":"7.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"7.500000e-6"},{"sku_label":">272K","price":"1.125000e-5"}]},{"kind":"token","sku_label":"Cache Read","price":"1.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"1.250000e-7"},{"sku_label":">272K","price":"2.500000e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.250000e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"7.500000e-6","openai_responses:cached_prompt_tokens":"1.250000e-7","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"2.500000e-6","openai_responses:completion_tokens_high_context":"1.125000e-5","openai_responses:cached_prompt_tokens_high_context":"2.500000e-7"},"pricing_version_id":"013538c4-3e7f-4806-a412-bd774591fbc6","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:53.196Z","status":0}},{"slug":"openai/gpt-5.4","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-03-05T18:12:32.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.4","short_name":"GPT-5.4","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9ff5625c-403f-4d7f-b895-58ac7295062c","name":"OpenAI | openai/gpt-5.4-20260305","context_length":1050000,"model":{"slug":"openai/gpt-5.4","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-03-05T18:12:32+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.4","short_name":"GPT-5.4","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","model_version_group_id":null,"context_length":1050000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.4-20260305","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.4","model_variant_permaslug":"openai/gpt-5.4-20260305","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.4-2026-03-05","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":922000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.000015","input_cache_read":"0.00000025","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"0.0000005"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.5e-6"},{"sku_label":">272K","price":"5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"15e-6"},{"sku_label":">272K","price":"22.5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.25e-6"},{"sku_label":">272K","price":"0.5e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"2.5e-6"},{"sku_label":">272K","price":"5e-6"}]},{"kind":"token","sku_label":"Output Price","price":"15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"15e-6"},{"sku_label":">272K","price":"22.5e-6"}]},{"kind":"token","sku_label":"Cache Read","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤272K","price":"0.25e-6"},{"sku_label":">272K","price":"0.5e-6"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"2.5e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"15e-6","openai_responses:cached_prompt_tokens":"0.25e-6","openai_responses:flex_tier_multiplier":"0.5","openai_responses:high_context_threshold":"272000","openai_responses:priority_tier_multiplier":"2","openai_responses:prompt_tokens_high_context":"5e-6","openai_responses:completion_tokens_high_context":"22.5e-6","openai_responses:cached_prompt_tokens_high_context":"0.5e-6"},"pricing_version_id":"5f9490cf-9ac9-4eda-bb46-958edf7b6f1e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":1600,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-03T14:51:36.911Z","status":0}},{"slug":"inception/mercury-2","hf_slug":null,"updated_at":"2026-03-05T16:01:22.794Z","created_at":"2026-03-04T14:57:55.767Z","hf_updated_at":null,"name":"Inception: Mercury 2","short_name":"Mercury 2","author":"inception","author_display_name":"inception","author_icon_uri":null,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).\nInstead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost. \nMercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the [blog post](https://www.inceptionlabs.ai/blog/introducing-mercury-2).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"inception/mercury-2-20260304","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":0.75,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c2a24e34-c306-4b4d-9e2f-b162c2d8bf0e","name":"Inception | inception/mercury-2-20260304","context_length":128000,"model":{"slug":"inception/mercury-2","hf_slug":null,"updated_at":"2026-03-05T16:01:22.794207+00:00","created_at":"2026-03-04T14:57:55.767129+00:00","hf_updated_at":null,"name":"Inception: Mercury 2","short_name":"Mercury 2","author":"inception","author_display_name":"inception","author_icon_uri":null,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).\nInstead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost. \nMercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the [blog post](https://www.inceptionlabs.ai/blog/introducing-mercury-2).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"inception/mercury-2-20260304","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"medium","default_reasoning_enabled":true},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":0.75,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"inception/mercury-2","model_variant_permaslug":"inception/mercury-2-20260304","adapter_name":"InceptionAdapter","provider_name":"Inception","provider_info":{"name":"Inception","displayName":"Inception","slug":"inception","baseUrl":"https://api.inceptionlabs.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.inceptionlabs.ai/terms","privacyPolicyURL":"https://www.inceptionlabs.ai/terms#privacy-policy","requiresUserIDs":false},"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"InceptionAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/Inception.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Inception","provider_slug":"inception","provider_model_id":"mercury-2","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":50000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","temperature","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.inceptionlabs.ai/terms","privacyPolicyURL":"https://www.inceptionlabs.ai/terms#privacy-policy"},"pricing":{"prompt":"0.00000025","completion":"0.00000075","input_cache_read":"0.000000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000025","openai:completion_tokens":"0.00000075","openai:cached_prompt_tokens":"0.000000025"},"pricing_version_id":"91c960ab-a2df-45f1-afe5-ada1d0c47607","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-04T14:57:56.222Z","status":0}},{"slug":"google/gemini-3.1-flash-lite-preview","hf_slug":"","updated_at":"2026-03-03T16:32:04.999Z","created_at":"2026-03-03T04:37:53.564Z","hf_updated_at":null,"name":"Google: Gemini 3.1 Flash Lite Preview","short_name":"Gemini 3.1 Flash Lite Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-preview-20260303","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e004ce39-eb0c-4474-93d5-55072e725970","name":"Google AI Studio | google/gemini-3.1-flash-lite-preview-20260303","context_length":1048576,"model":{"slug":"google/gemini-3.1-flash-lite-preview","hf_slug":"","updated_at":"2026-03-03T16:32:04.999376+00:00","created_at":"2026-03-03T04:37:53.564789+00:00","hf_updated_at":null,"name":"Google: Gemini 3.1 Flash Lite Preview","short_name":"Gemini 3.1 Flash Lite Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-lite-preview-20260303","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["medium","minimal","low","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-flash-lite-preview","model_variant_permaslug":"google/gemini-3.1-flash-lite-preview-20260303","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.1-flash-lite-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","input_cache_read":"0.000000025","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.0000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.025e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.05e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.025e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"0.05e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.25e-6","gemini:reasoning_tokens":"1.5e-6","gemini:cache_read_tokens":"0.025e-6","gemini:completion_tokens":"1.5e-6","gemini:text_input_tokens":"0.25e-6","gemini:audio_input_tokens":"0.5e-6","gemini:image_input_tokens":"0.25e-6","gemini:video_input_tokens":"0.25e-6","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"0.025e-6","gemini:cache_read_audio_tokens":"0.05e-6","gemini:cache_read_image_tokens":"0.025e-6","gemini:cache_read_video_tokens":"0.025e-6","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"1e-6","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"72060f24-f5a4-4dcb-86eb-19d6e9e0548a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":450,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-03T04:56:39.046Z","status":0}},{"slug":"bytedance-seed/seed-2.0-mini","hf_slug":"","updated_at":"2026-02-26T18:58:51.947Z","created_at":"2026-02-26T18:38:27.000Z","hf_updated_at":null,"name":"ByteDance Seed: Seed-2.0-Mini","short_name":"Seed-2.0-Mini","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding, and is optimized for lightweight tasks where cost and speed take priority.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2.0-mini-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","minimal","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","minimal","high"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9265aa87-9657-4d40-b9d7-2a70318e57d9","name":"Seed | bytedance-seed/seed-2.0-mini-20260224","context_length":262144,"model":{"slug":"bytedance-seed/seed-2.0-mini","hf_slug":"","updated_at":"2026-02-26T18:58:51.947888+00:00","created_at":"2026-02-26T18:38:27+00:00","hf_updated_at":null,"name":"ByteDance Seed: Seed-2.0-Mini","short_name":"Seed-2.0-Mini","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding, and is optimized for lightweight tasks where cost and speed take priority.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-2.0-mini-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","minimal","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","minimal","high"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance-seed/seed-2.0-mini","model_variant_permaslug":"bytedance-seed/seed-2.0-mini-20260224","adapter_name":"BytePlusAdapter","provider_name":"Seed","provider_info":{"name":"Seed","displayName":"Seed","slug":"seed","baseUrl":"https://ark.ap-southeast.bytepluses.com/api/v3","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"BytePlusAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256"},"sendClientIp":false,"pricingStrategy":"byteplus"},"provider_display_name":"Seed","provider_slug":"seed/fp8","provider_model_id":"ep-20260225003753-6xpj9","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000004","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000002","completion":"0.0000008"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000001"},{"sku_label":">128K","price":"0.0000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000004"},{"sku_label":">128K","price":"0.0000008"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000001"},{"sku_label":">128K","price":"0.0000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000004"},{"sku_label":">128K","price":"0.0000008"}]}],"pricing_json":{"byteplus:prompt_tokens":"0.0000001","byteplus:completion_tokens":"0.0000004","byteplus:long_context_threshold":"128000","byteplus:prompt_tokens_long_context":"0.0000002","byteplus:completion_tokens_long_context":"0.0000008"},"pricing_version_id":"30b61b58-7a2f-411d-b9e2-27b439ace262","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-25T19:02:41.598Z","status":0}},{"slug":"google/gemini-3.1-flash-image-preview","hf_slug":"","updated_at":"2026-03-04T14:13:20.174Z","created_at":"2026-02-26T15:25:58.367Z","hf_updated_at":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","short_name":"Nano Banana 2 (Gemini 3.1 Flash Image Preview)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)","model_version_group_id":null,"context_length":65536,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-image-preview-20260226","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-image-preview-20260226/ce91d0e2-9d8b-4242-bc3b-01a200506afb/original-0.jpg","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-image-preview-20260226/ce91d0e2-9d8b-4242-bc3b-01a200506afb/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3.1-flash-image-preview-20260226/ce91d0e2-9d8b-4242-bc3b-01a200506afb/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2d3e3ef1-e1fb-4515-b5c8-6f0779b0e7aa","name":"Google AI Studio | google/gemini-3.1-flash-image-preview-20260226","context_length":65536,"model":{"slug":"google/gemini-3.1-flash-image-preview","hf_slug":"","updated_at":"2026-03-04T14:13:20.174946+00:00","created_at":"2026-02-26T15:25:58.367817+00:00","hf_updated_at":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","short_name":"Nano Banana 2 (Gemini 3.1 Flash Image Preview)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-flash-image-preview-20260226","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","high"],"default_reasoning_effort":"minimal","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-flash-image-preview","model_variant_permaslug":"google/gemini-3.1-flash-image-preview-20260226","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.1-flash-image-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.0000005","completion":"0.000003","image_output":"0.00006","web_search":"0.014","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"60e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"60e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.5e-6","gemini:completion_tokens":"3e-6","gemini:image_output_tokens":"60e-6"},"pricing_version_id":"1b76edbc-e69d-4596-861e-03592926c49f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":80,"limit_rpd":3000,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":{"resolutions":["512","1K","2K","4K"],"aspect_ratios":["1:1","1:4","1:8","2:3","3:2","3:4","4:1","4:3","4:5","5:4","8:1","9:16","16:9","21:9"],"output_formats":null,"qualities":null,"backgrounds":null,"n":{"min":1,"max":1},"input_references":{"min":0,"max":14},"output_compression":null,"seed":null},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["cachedContent"],"capacity_tpm":null,"created_at":"2026-02-26T15:29:10.444Z","status":0}},{"slug":"qwen/qwen3.5-35b-a3b","hf_slug":"Qwen/Qwen3.5-35B-A3B","updated_at":"2026-03-20T20:29:28.981Z","created_at":"2026-02-25T21:10:22.000Z","hf_updated_at":null,"name":"Qwen: Qwen3.5-35B-A3B","short_name":"Qwen3.5-35B-A3B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-35b-a3b-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"098f81e1-07f9-4f7c-a006-65c81138ddea","name":"DeepInfra | qwen/qwen3.5-35b-a3b-20260224","context_length":262144,"model":{"slug":"qwen/qwen3.5-35b-a3b","hf_slug":"Qwen/Qwen3.5-35B-A3B","updated_at":"2026-03-20T20:29:28.981001+00:00","created_at":"2026-02-25T21:10:22+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5-35B-A3B","short_name":"Qwen3.5-35B-A3B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-35b-a3b-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-35b-a3b","model_variant_permaslug":"qwen/qwen3.5-35b-a3b-20260224","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Qwen/Qwen3.5-35B-A3B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":81920,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000014","completion":"0.000001","input_cache_read":"0.00000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000014","openai:completion_tokens":"0.000001","openai:cached_prompt_tokens":"0.00000005"},"pricing_version_id":"1514e3f6-0352-4534-b76b-2dec614f632d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-26T07:05:54.579Z","status":0}},{"slug":"qwen/qwen3.5-27b","hf_slug":"Qwen/Qwen3.5-27B","updated_at":"2026-03-20T20:29:35.954Z","created_at":"2026-02-25T21:10:10.000Z","hf_updated_at":null,"name":"Qwen: Qwen3.5-27B","short_name":"Qwen3.5-27B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-27b-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f3f88554-0c22-4d57-973b-0dec948808e8","name":"Alibaba | qwen/qwen3.5-27b-20260224","context_length":262144,"model":{"slug":"qwen/qwen3.5-27b","hf_slug":"Qwen/Qwen3.5-27B","updated_at":"2026-03-20T20:29:35.9548+00:00","created_at":"2026-02-25T21:10:10+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5-27B","short_name":"Qwen3.5-27B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-27b-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-27b","model_variant_permaslug":"qwen/qwen3.5-27b-20260224","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.5-27b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":258048,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000195","completion":"0.00000156","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000195","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000156","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000195","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000156","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000000195","alibaba:completion_tokens":"0.00000156"},"pricing_version_id":"62f07a71-6b4e-4f11-81a2-c6805b6ebfa9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-25T16:10:09.814Z","status":0}},{"slug":"qwen/qwen3.5-122b-a10b","hf_slug":"Qwen/Qwen3.5-122B-A10B","updated_at":"2026-03-20T20:29:51.113Z","created_at":"2026-02-25T21:09:49.000Z","hf_updated_at":null,"name":"Qwen: Qwen3.5-122B-A10B","short_name":"Qwen3.5-122B-A10B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-122b-a10b-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0a90a7cd-5063-4bcf-a228-e51ebb87feee","name":"SiliconFlow | qwen/qwen3.5-122b-a10b-20260224","context_length":262144,"model":{"slug":"qwen/qwen3.5-122b-a10b","hf_slug":"Qwen/Qwen3.5-122B-A10B","updated_at":"2026-03-20T20:29:51.113729+00:00","created_at":"2026-02-25T21:09:49+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5-122B-A10B","short_name":"Qwen3.5-122B-A10B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-122b-a10b-20260224","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-122b-a10b","model_variant_permaslug":"qwen/qwen3.5-122b-a10b-20260224","adapter_name":"SiliconFlowAdapter","provider_name":"SiliconFlow","provider_info":{"name":"SiliconFlow","displayName":"SiliconFlow","slug":"siliconflow","baseUrl":"https://api.siliconflow.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.siliconflow.com/en/legals/terms-of-service","privacyPolicyURL":"https://docs.siliconflow.com/en/legals/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"SiliconFlowAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/SiliconFlow.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"SiliconFlow","provider_slug":"siliconflow/fp8","provider_model_id":"Qwen/Qwen3.5-122B-A10B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.siliconflow.com/en/legals/terms-of-service","privacyPolicyURL":"https://docs.siliconflow.com/en/legals/privacy-policy"},"pricing":{"prompt":"0.00000026","completion":"0.00000208","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000208","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000208","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000026","openai:completion_tokens":"0.00000208"},"pricing_version_id":"5f0136a3-28ed-4e6c-804b-c2fcf142338b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-22T04:01:55.471Z","status":0}},{"slug":"qwen/qwen3.5-flash-02-23","hf_slug":null,"updated_at":"2026-02-25T21:09:36.451Z","created_at":"2026-02-25T21:09:36.000Z","hf_updated_at":null,"name":"Qwen: Qwen3.5-Flash","short_name":"Qwen3.5-Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-flash-20260224","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5f6b71b5-8672-4b27-8b2d-f674429f9e63","name":"Alibaba | qwen/qwen3.5-flash-20260224","context_length":1000000,"model":{"slug":"qwen/qwen3.5-flash-02-23","hf_slug":null,"updated_at":"2026-02-25T21:09:36.451208+00:00","created_at":"2026-02-25T21:09:36+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5-Flash","short_name":"Qwen3.5-Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-flash-20260224","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-flash-02-23","model_variant_permaslug":"qwen/qwen3.5-flash-20260224","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.5-flash-2026-02-23","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000065","completion":"0.00000026","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000065","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000065","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000000065","alibaba:completion_tokens":"0.00000026"},"pricing_version_id":"063d2c8b-b7ed-434d-8ed7-292fe9d07c53","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-24T16:42:43.659Z","status":0}},{"slug":"google/gemini-3.1-pro-preview-customtools","hf_slug":null,"updated_at":"2026-02-25T19:23:18.275Z","created_at":"2026-02-25T18:58:43.000Z","hf_updated_at":null,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","short_name":"Gemini 3.1 Pro Preview Custom Tools","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party or user-defined functions are available. This specialized preview endpoint significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows.\n\nIt retains the core strengths of Gemini 3.1 Pro, including multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-pro-preview-customtools-20260219","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3ccc4f6d-d337-43ed-9c40-bb43618ba0ca","name":"Google AI Studio | google/gemini-3.1-pro-preview-customtools-20260219","context_length":1048576,"model":{"slug":"google/gemini-3.1-pro-preview-customtools","hf_slug":null,"updated_at":"2026-02-25T19:23:18.275993+00:00","created_at":"2026-02-25T18:58:43+00:00","hf_updated_at":null,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","short_name":"Gemini 3.1 Pro Preview Custom Tools","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party or user-defined functions are available. This specialized preview endpoint significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows.\n\nIt retains the core strengths of Gemini 3.1 Pro, including multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance.","model_version_group_id":null,"context_length":1048756,"input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-pro-preview-customtools-20260219","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-pro-preview-customtools","model_variant_permaslug":"google/gemini-3.1-pro-preview-customtools-20260219","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.1-pro-preview-customtools","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000012"},{"sku_label":">200K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000012"},{"sku_label":">200K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]}],"pricing_json":{"gemini:prompt_tokens":"0.000002","gemini:reasoning_tokens":"0.000012","gemini:cache_read_tokens":"2e-7","gemini:completion_tokens":"0.000012","gemini:text_input_tokens":"0.000002","gemini:audio_input_tokens":"0.000002","gemini:image_input_tokens":"0.000002","gemini:video_input_tokens":"0.000002","gemini:cache_read_text_tokens":"2e-7","gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":"2e-7","gemini:cache_read_image_tokens":"2e-7","gemini:cache_read_video_tokens":"2e-7","gemini:cache_write_storage_hours":"0.0000045","gemini:prompt_tokens_high_context":"0.000004","gemini:reasoning_tokens_high_context":"0.000018","gemini:cache_read_tokens_high_context":"4e-7","gemini:completion_tokens_high_context":"0.000018","gemini:cache_read_text_tokens_high_context":"4e-7","gemini:cache_read_audio_tokens_high_context":"4e-7","gemini:cache_read_image_tokens_high_context":"4e-7","gemini:cache_read_video_tokens_high_context":"4e-7","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"8b9bb74b-8cfb-497d-bc6f-93c68796774f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":300,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-23T22:27:25.290Z","status":0}},{"slug":"openai/gpt-5.3-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-02-24T18:52:44.481Z","hf_updated_at":null,"name":"OpenAI: GPT-5.3-Codex","short_name":"GPT-5.3-Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.\n\nBeyond coding, GPT-5.3-Codex performs strongly on structured knowledge-work benchmarks such as GDPval, supporting tasks like document drafting, spreadsheet analysis, slide creation, and operational research across domains. It is trained with enhanced cybersecurity awareness, including vulnerability identification capabilities, and deployed with additional safeguards for high-risk use cases. Compared to prior Codex models, it is more token-efficient and approximately 25% faster, targeting professional end-to-end workflows that span reasoning, execution, and computer interaction.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.3-codex-20260224","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"75bb5ca0-7b08-4f1a-aca5-aa2bbf44d98e","name":"OpenAI | openai/gpt-5.3-codex-20260224","context_length":400000,"model":{"slug":"openai/gpt-5.3-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-02-24T18:52:44.481761+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.3-Codex","short_name":"GPT-5.3-Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.\n\nBeyond coding, GPT-5.3-Codex performs strongly on structured knowledge-work benchmarks such as GDPval, supporting tasks like document drafting, spreadsheet analysis, slide creation, and operational research across domains. It is trained with enhanced cybersecurity awareness, including vulnerability identification capabilities, and deployed with additional safeguards for high-risk use cases. Compared to prior Codex models, it is more token-efficient and approximately 25% faster, targeting professional end-to-end workflows that span reasoning, execution, and computer interaction.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.3-codex-20260224","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","low","medium","xhigh","none"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.3-codex","model_variant_permaslug":"openai/gpt-5.3-codex-20260224","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.3-codex","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.00000175","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"0.000014","openai_responses:cached_prompt_tokens":"1.75e-7","openai_responses:priority_tier_multiplier":"2"},"pricing_version_id":"7240aabb-c10e-4e30-b265-543379c247ab","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-24T18:54:05.100Z","status":0}},{"slug":"aion-labs/aion-2.0","hf_slug":null,"updated_at":"2026-02-24T19:34:10.842Z","created_at":"2026-02-23T21:15:06.199Z","hf_updated_at":null,"name":"AionLabs: Aion-2.0","short_name":"Aion-2.0","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging. It also handles mature and darker themes with more nuance and depth.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-2.0-20260223","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1e93b0bb-eb0f-49bc-8fda-947105413b86","name":"AionLabs | aion-labs/aion-2.0-20260223","context_length":131072,"model":{"slug":"aion-labs/aion-2.0","hf_slug":null,"updated_at":"2026-02-24T19:34:10.842018+00:00","created_at":"2026-02-23T21:15:06.199634+00:00","hf_updated_at":null,"name":"AionLabs: Aion-2.0","short_name":"Aion-2.0","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging. It also handles mature and darker themes with more nuance and depth.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-2.0-20260223","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"aion-labs/aion-2.0","model_variant_permaslug":"aion-labs/aion-2.0-20260223","adapter_name":"OpenAIAdapter","provider_name":"AionLabs","provider_info":{"name":"AionLabs","displayName":"AionLabs","slug":"aion-labs","baseUrl":"https://api.aionlabs.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/","requiresUserIDs":false},"headquarters":"IL","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.aionlabs.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"AionLabs","provider_slug":"aion-labs","provider_model_id":"aion-labs/aion-2.0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/"},"pricing":{"prompt":"0.0000008","completion":"0.0000016","input_cache_read":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000016","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000016","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000008","openai:completion_tokens":"0.0000016","openai:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"b00ff336-87a6-4982-833b-2e875e5a7e67","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-23T21:15:06.659Z","status":0}},{"slug":"google/gemini-3.1-pro-preview","hf_slug":"","updated_at":"2026-04-27T19:36:42.970Z","created_at":"2026-02-19T14:00:27.000Z","hf_updated_at":null,"name":"Google: Gemini 3.1 Pro Preview (batch)","short_name":"Gemini 3.1 Pro Preview (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.\n\nDesigned for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.","model_version_group_id":"efd991b0-c32d-4220-8a39-10b0ae06b094","context_length":1048576,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-pro-preview-20260219","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a7871437-0dd8-4ec7-8ddd-25ecf1383fdb","name":"Google | google/gemini-3.1-pro-preview-20260219:batch","context_length":1048576,"model":{"slug":"google/gemini-3.1-pro-preview","hf_slug":"","updated_at":"2026-04-27T19:36:42.970871+00:00","created_at":"2026-02-19T14:00:27+00:00","hf_updated_at":null,"name":"Google: Gemini 3.1 Pro Preview","short_name":"Gemini 3.1 Pro Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.\n\nDesigned for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.","model_version_group_id":"efd991b0-c32d-4220-8a39-10b0ae06b094","context_length":1048576,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-pro-preview-20260219","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-pro-preview:batch","model_variant_permaslug":"google/gemini-3.1-pro-preview-20260219:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3.1-pro-preview","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","audio":"0.000001","web_search":"0.014","internal_reasoning":"0.000006","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000002","completion":"0.000009","audio":"0.000002"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001"},{"sku_label":">200K","price":"0.000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000009"}]},{"kind":"token","sku_label":"Image Input","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001"},{"sku_label":">200K","price":"0.000002"}]},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001"},{"sku_label":">200K","price":"0.000002"}]},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000009"}]},{"kind":"token","sku_label":"Image Input","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001"},{"sku_label":">200K","price":"0.000002"}]},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":0.000001,"gemini:reasoning_tokens":0.000006,"gemini:web_search_calls":"0.014","gemini:completion_tokens":0.000006,"gemini:text_input_tokens":0.000001,"gemini:audio_input_tokens":0.000001,"gemini:image_input_tokens":0.000001,"gemini:video_input_tokens":0.000001,"gemini:long_context_threshold":"200000","gemini:prompt_tokens_high_context":0.000002,"gemini:reasoning_tokens_high_context":0.000009,"gemini:completion_tokens_high_context":0.000009,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"4da9bfc4-6996-4471-bca9-fc4c32c70e9f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:12:02.396Z","status":0}},{"slug":"google/gemini-3.1-pro-preview","hf_slug":"","updated_at":"2026-04-27T19:36:42.970Z","created_at":"2026-02-19T14:00:27.000Z","hf_updated_at":null,"name":"Google: Gemini 3.1 Pro Preview","short_name":"Gemini 3.1 Pro Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.\n\nDesigned for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.","model_version_group_id":"efd991b0-c32d-4220-8a39-10b0ae06b094","context_length":1048576,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-pro-preview-20260219","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"2abf5677-0826-45d9-8470-3d62c31d54a1","name":"Google AI Studio | google/gemini-3.1-pro-preview-20260219","context_length":1048576,"model":{"slug":"google/gemini-3.1-pro-preview","hf_slug":"","updated_at":"2026-04-27T19:36:42.970871+00:00","created_at":"2026-02-19T14:00:27+00:00","hf_updated_at":null,"name":"Google: Gemini 3.1 Pro Preview","short_name":"Gemini 3.1 Pro Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.\n\nDesigned for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.","model_version_group_id":"efd991b0-c32d-4220-8a39-10b0ae06b094","context_length":1048576,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3.1-pro-preview-20260219","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high","medium","low"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3.1-pro-preview","model_variant_permaslug":"google/gemini-3.1-pro-preview-20260219","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3.1-pro-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000004","completion":"0.000018","audio":"0.000004","input_audio_cache":"0.0000004","input_cache_read":"0.0000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000012"},{"sku_label":">200K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000012"},{"sku_label":">200K","price":"0.000018"}]},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000002"},{"sku_label":">200K","price":"0.000004"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"2e-7"},{"sku_label":">200K","price":"4e-7"}]},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":"0.000002","gemini:reasoning_tokens":"0.000012","gemini:cache_read_tokens":"2e-7","gemini:completion_tokens":"0.000012","gemini:text_input_tokens":"0.000002","gemini:audio_input_tokens":"0.000002","gemini:image_input_tokens":"0.000002","gemini:video_input_tokens":"0.000002","gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":"2e-7","gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":"2e-7","gemini:cache_read_image_tokens":"2e-7","gemini:cache_read_video_tokens":"2e-7","gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":"0.0000045","gemini:prompt_tokens_high_context":"0.000004","gemini:reasoning_tokens_high_context":"0.000018","gemini:cache_read_tokens_high_context":"4e-7","gemini:completion_tokens_high_context":"0.000018","gemini:cache_read_text_tokens_high_context":"4e-7","gemini:cache_read_audio_tokens_high_context":"4e-7","gemini:cache_read_image_tokens_high_context":"4e-7","gemini:cache_read_video_tokens_high_context":"4e-7","gemini:informational_cache_write_tokens_count":"0"},"pricing_version_id":"0312e85d-eece-4c6f-8c8e-49087e1a1899","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":300,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-10T00:42:42.296Z","status":0}},{"slug":"anthropic/claude-sonnet-4.6","hf_slug":"","updated_at":"2026-08-18T00:44:25.810Z","created_at":"2026-02-17T15:43:10.807Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.6 (batch)","short_name":"Claude Sonnet 4.6 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-sonnet-20260217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/us-east5","claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","azure/global","google-vertex/europe","amazon-bedrock/eu-west-1"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"fa199746-90d3-41af-a665-902840b98847","name":"Anthropic | anthropic/claude-4.6-sonnet-20260217:batch","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-4.6","hf_slug":"","updated_at":"2026-08-18T00:44:25.810947+00:00","created_at":"2026-02-17T15:43:10.807722+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.6","short_name":"Claude Sonnet 4.6","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-sonnet-20260217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/us-east5","claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","azure/global","google-vertex/europe","amazon-bedrock/eu-west-1"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-4.6:batch","model_variant_permaslug":"anthropic/claude-4.6-sonnet-20260217:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-sonnet-4-6","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000015","completion":"0.0000075","input_cache_read":"0.00000015","input_cache_write":"0.000001875","input_cache_write_1h":"0.000003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000015","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"0.00000015","anthropic:completion_tokens":"0.0000075","anthropic:cache_write_1h_tokens":"0.000003","anthropic:cache_write_5m_tokens":"0.000001875"},"pricing_version_id":"0ab3384a-04aa-49cd-b414-3e161a87e7a8","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-14T02:38:51.606Z","status":0}},{"slug":"anthropic/claude-sonnet-4.6","hf_slug":"","updated_at":"2026-08-18T00:44:25.810Z","created_at":"2026-02-17T15:43:10.807Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.6","short_name":"Claude Sonnet 4.6","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-sonnet-20260217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/us-east5","claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","azure/global","google-vertex/europe","amazon-bedrock/eu-west-1"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"3ad4538c-bdd2-4161-86d8-8350c2bb8efa","name":"Claude Platform on AWS | anthropic/claude-4.6-sonnet-20260217","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-4.6","hf_slug":"","updated_at":"2026-08-18T00:44:25.810947+00:00","created_at":"2026-02-17T15:43:10.807722+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.6","short_name":"Claude Sonnet 4.6","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","model_version_group_id":"abf62d9f-0b98-401f-a916-b5bd3c214712","context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-sonnet-20260217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","max"]},"chat_template_config":{}},"default_parameters":{},"default_order":["google-vertex/us-east5","claude-on-aws","amazon-bedrock/global","google-vertex/global","anthropic","azure/global","google-vertex/europe","amazon-bedrock/eu-west-1"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-4.6","model_variant_permaslug":"anthropic/claude-4.6-sonnet-20260217","adapter_name":"ClaudeOnAwsAdapter","provider_name":"Claude Platform on AWS","provider_info":{"name":"Claude Platform on AWS","displayName":"Claude Platform on AWS","slug":"claude-on-aws","baseUrl":"https://aws-external-anthropic.us-east-1.api.aws/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"ClaudeOnAwsAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":false,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Claude Platform on AWS","provider_slug":"claude-on-aws","provider_model_id":"claude-sonnet-4-6","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format","verbosity"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.000003","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"0.0000003","anthropic:completion_tokens":"0.000015","anthropic:cache_write_1h_tokens":"0.000006","anthropic:cache_write_5m_tokens":"0.00000375"},"pricing_version_id":"c8621512-37e9-4f35-8aa7-d9a271f3b988","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-17T23:36:38.519Z","status":0}},{"slug":"qwen/qwen3.5-plus-02-15","hf_slug":"","updated_at":"2026-02-16T08:39:05.789Z","created_at":"2026-02-16T08:10:16.477Z","hf_updated_at":null,"name":"Qwen: Qwen3.5 Plus 2026-02-15","short_name":"Qwen3.5 Plus 2026-02-15","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-plus-20260216","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"71e0f6c3-7815-4734-92d3-8a04f3b0ca91","name":"Alibaba | qwen/qwen3.5-plus-20260216","context_length":1000000,"model":{"slug":"qwen/qwen3.5-plus-02-15","hf_slug":"","updated_at":"2026-02-16T08:39:05.78904+00:00","created_at":"2026-02-16T08:10:16.477672+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5 Plus 2026-02-15","short_name":"Qwen3.5 Plus 2026-02-15","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-plus-20260216","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-plus-02-15","model_variant_permaslug":"qwen/qwen3.5-plus-20260216","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.5-plus-2026-02-15","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":983616,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000026","completion":"0.00000156","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000325","completion":"0.00000195"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.000000325"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000156","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000156"},{"sku_label":">256K","price":"0.00000195"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.000000325"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000156","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000156"},{"sku_label":">256K","price":"0.00000195"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000026","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.00000156","alibaba:prompt_tokens_tier2":"0.000000325","alibaba:completion_tokens_tier2":"0.00000195"},"pricing_version_id":"53fd3743-1752-4ce9-b9d5-d3fa4ae47312","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-16T08:12:47.605Z","status":0}},{"slug":"qwen/qwen3.5-397b-a17b","hf_slug":"Qwen/Qwen3.5-397B-A17B","updated_at":"2026-03-20T20:30:07.296Z","created_at":"2026-02-16T06:23:38.867Z","hf_updated_at":null,"name":"Qwen: Qwen3.5 397B A17B","short_name":"Qwen3.5 397B A17B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-397b-a17b-20260216","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"180484a2-e24b-495a-ba41-b34b680d5a9f","name":"Alibaba | qwen/qwen3.5-397b-a17b-20260216","context_length":262144,"model":{"slug":"qwen/qwen3.5-397b-a17b","hf_slug":"Qwen/Qwen3.5-397B-A17B","updated_at":"2026-03-20T20:30:07.296584+00:00","created_at":"2026-02-16T06:23:38.867499+00:00","hf_updated_at":null,"name":"Qwen: Qwen3.5 397B A17B","short_name":"Qwen3.5 397B A17B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3.5-397b-a17b-20260216","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3.5-397b-a17b","model_variant_permaslug":"qwen/qwen3.5-397b-a17b-20260216","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3.5-397b-a17b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":258048,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000039","completion":"0.00000234","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000039","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000234","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000039","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000234","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.00000039","alibaba:completion_tokens":"0.00000234"},"pricing_version_id":"d3de9f10-b244-4f94-b74f-9b8f385c6557","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-16T06:42:50.609Z","status":0}},{"slug":"minimax/minimax-m2.5","hf_slug":"MiniMaxAI/MiniMax-M2.5","updated_at":"2026-03-18T13:15:02.930Z","created_at":"2026-02-12T15:01:42.000Z","hf_updated_at":null,"name":"MiniMax: MiniMax M2.5","short_name":"MiniMax M2.5","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2.5-20260211","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3146f103-e8d8-4832-851c-2a0284feec7c","name":"Venice | minimax/minimax-m2.5-20260211","context_length":198000,"model":{"slug":"minimax/minimax-m2.5","hf_slug":"MiniMaxAI/MiniMax-M2.5","updated_at":"2026-03-18T13:15:02.930858+00:00","created_at":"2026-02-12T15:01:42+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M2.5","short_name":"MiniMax M2.5","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2.5-20260211","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m2.5","model_variant_permaslug":"minimax/minimax-m2.5-20260211","adapter_name":"VeniceAdapter","provider_name":"Venice","provider_info":{"name":"Venice","displayName":"Venice","slug":"venice","baseUrl":"https://api.venice.ai/api/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://venice.ai/legal/tos","privacyPolicyURL":"https://venice.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"VeniceAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://venice.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Venice","provider_slug":"venice","provider_model_id":"minimax-m25","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://venice.ai/legal/tos","privacyPolicyURL":"https://venice.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000027","completion":"0.00000095","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000027","openai:completion_tokens":"0.00000095","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"8584a918-533d-415b-88ac-8975bc6527c4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-02T16:04:45.697Z","status":0}},{"slug":"z-ai/glm-5","hf_slug":"zai-org/GLM-5","updated_at":"2026-02-11T21:59:34.617Z","created_at":"2026-02-11T16:59:42.000Z","hf_updated_at":null,"name":"Z.ai: GLM 5","short_name":"GLM 5","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5-20260211","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a9ca9362-3ad6-458a-bd00-a9f09e42796c","name":"GMICloud | z-ai/glm-5-20260211","context_length":202752,"model":{"slug":"z-ai/glm-5","hf_slug":"zai-org/GLM-5","updated_at":"2026-02-11T21:59:34.617041+00:00","created_at":"2026-02-11T16:59:42+00:00","hf_updated_at":null,"name":"Z.ai: GLM 5","short_name":"GLM 5","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.","model_version_group_id":null,"context_length":202752,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-5-20260211","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-5","model_variant_permaslug":"z-ai/glm-5-20260211","adapter_name":"GMICloudAdapter","provider_name":"GMICloud","provider_info":{"name":"GMICloud","displayName":"GMICloud","slug":"gmicloud","baseUrl":"https://api.gmi-serving.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"GMICloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://gmicloud.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"GMICloud","provider_slug":"gmicloud/fp8","provider_model_id":"zai-org/GLM-5-FP8","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy"},"pricing":{"prompt":"0.0000006","completion":"0.00000192","input_cache_read":"0.00000012","discount":0.4,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000192","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000192","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000001","openai:completion_tokens":"0.0000032","openai:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"8ff9a86d-78ff-45ba-a1b7-2146fb249032","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-11T20:38:38.909Z","status":0}},{"slug":"qwen/qwen3-max-thinking","hf_slug":null,"updated_at":"2026-02-09T21:47:13.196Z","created_at":"2026-02-09T21:18:21.683Z","hf_updated_at":null,"name":"Qwen: Qwen3 Max Thinking","short_name":"Qwen3 Max Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-max-thinking-20260123","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0c13d1a9-ea55-4e4f-ad48-55e6319c0a3e","name":"Alibaba | qwen/qwen3-max-thinking-20260123","context_length":262144,"model":{"slug":"qwen/qwen3-max-thinking","hf_slug":null,"updated_at":"2026-02-09T21:47:13.196115+00:00","created_at":"2026-02-09T21:18:21.683315+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Max Thinking","short_name":"Qwen3 Max Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-max-thinking-20260123","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-max-thinking","model_variant_permaslug":"qwen/qwen3-max-thinking-20260123","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-max-2026-01-23","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":258048,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000078","completion":"0.0000039","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000156","completion":"0.0000078"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000078"},{"sku_label":"≤128K","price":"0.00000156"},{"sku_label":">128K","price":"0.00000195"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000039","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000039"},{"sku_label":"≤128K","price":"0.0000078"},{"sku_label":">128K","price":"0.00000975"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000078"},{"sku_label":"≤128K","price":"0.00000156"},{"sku_label":">128K","price":"0.00000195"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000039","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000039"},{"sku_label":"≤128K","price":"0.0000078"},{"sku_label":">128K","price":"0.00000975"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000078","alibaba:tier2_threshold":"32000","alibaba:tier3_threshold":"128000","alibaba:completion_tokens":"0.0000039","alibaba:prompt_tokens_tier2":"0.00000156","alibaba:prompt_tokens_tier3":"0.00000195","alibaba:completion_tokens_tier2":"0.0000078","alibaba:completion_tokens_tier3":"0.00000975"},"pricing_version_id":"013d7bf1-910a-4e5b-a6a8-000c1e8a0823","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-09T21:18:22.211Z","status":0}},{"slug":"anthropic/claude-opus-4.6","hf_slug":"","updated_at":"2026-08-18T00:43:00.901Z","created_at":"2026-02-04T15:30:50.029Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.6 (batch)","short_name":"Claude Opus 4.6 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\n\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/guides/model-migrations/claude-4-6-opus)\n","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-opus-20260205","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","azure/global","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b98aa7bc-de98-4767-93fd-a6eeda03de93","name":"Anthropic | anthropic/claude-4.6-opus-20260205:batch","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.6","hf_slug":"","updated_at":"2026-08-18T00:43:00.901172+00:00","created_at":"2026-02-04T15:30:50.029498+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.6","short_name":"Claude Opus 4.6","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\n\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/guides/model-migrations/claude-4-6-opus)\n","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-opus-20260205","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","azure/global","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.6:batch","model_variant_permaslug":"anthropic/claude-4.6-opus-20260205:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-6","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000025","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"2.5e-7","anthropic:completion_tokens":"0.0000125","anthropic:cache_write_1h_tokens":"0.000005","anthropic:cache_write_5m_tokens":"0.000003125"},"pricing_version_id":"7b2052ab-fdcf-4714-b87b-1f531db5507e","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:09:36.286Z","status":0}},{"slug":"anthropic/claude-opus-4.6","hf_slug":"","updated_at":"2026-08-18T00:43:00.901Z","created_at":"2026-02-04T15:30:50.029Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.6","short_name":"Claude Opus 4.6","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\n\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/guides/model-migrations/claude-4-6-opus)\n","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-opus-20260205","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","azure/global","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"5bc0e1b6-d533-4cd1-ad21-20009af0a6d7","name":"Azure | anthropic/claude-4.6-opus-20260205","context_length":1000000,"model":{"slug":"anthropic/claude-opus-4.6","hf_slug":"","updated_at":"2026-08-18T00:43:00.901172+00:00","created_at":"2026-02-04T15:30:50.029498+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.6","short_name":"Claude Opus 4.6","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\n\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\n\nFor users upgrading from earlier Opus versions, see our [official migration guide here](https://openrouter.ai/docs/guides/guides/model-migrations/claude-4-6-opus)\n","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.6-opus-20260205","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":true,"supported_reasoning_efforts":["low","medium","high","max"],"default_reasoning_effort":"high","default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{},"default_order":["claude-on-aws","amazon-bedrock","google-vertex/global","anthropic","azure/global","google-vertex/europe"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.6","model_variant_permaslug":"anthropic/claude-4.6-opus-20260205","adapter_name":"InternalStreamAzureAnthropicAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Azure","provider_slug":"azure/global","provider_model_id":"claude-opus-4-6","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","verbosity","top_k","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.50e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"6.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"10e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":"5e-6","anthropic:web_search_calls":".01","anthropic:cache_read_tokens":"0.50e-6","anthropic:completion_tokens":"25e-6","anthropic:cache_write_1h_tokens":"10e-6","anthropic:cache_write_5m_tokens":"6.25e-6"},"pricing_version_id":"4b845f18-0b27-4fdd-9f01-ac7fca8c3003","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"structured_outputs":true}},"supported_video_parameters":{"supported_sizes":null},"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-18T11:49:53.780Z","status":0}},{"slug":"qwen/qwen3-coder-next","hf_slug":"Qwen/Qwen3-Coder-Next","updated_at":"2026-02-04T00:27:00.409Z","created_at":"2026-02-04T00:15:01.820Z","hf_updated_at":null,"name":"Qwen: Qwen3 Coder Next","short_name":"Qwen3 Coder Next","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment.\n\nThe model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-next-2025-02-03","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"abacc5e9-91e6-40bf-93c6-9112334a4042","name":"Parasail | qwen/qwen3-coder-next-2025-02-03","context_length":262144,"model":{"slug":"qwen/qwen3-coder-next","hf_slug":"Qwen/Qwen3-Coder-Next","updated_at":"2026-02-04T00:27:00.409072+00:00","created_at":"2026-02-04T00:15:01.820167+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Coder Next","short_name":"Qwen3 Coder Next","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment.\n\nThe model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-next-2025-02-03","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-coder-next","model_variant_permaslug":"qwen/qwen3-coder-next-2025-02-03","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-qwen3-coder-next","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":262144,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000012","completion":"0.0000008","input_cache_read":"0.00000007","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000012","openai:completion_tokens":"0.0000008","openai:cached_prompt_tokens":"0.00000007"},"pricing_version_id":"c74e9c6a-1b31-42b8-8a39-e5f029cee87e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-04T20:10:36.634Z","status":0}},{"slug":"openrouter/free","hf_slug":"","updated_at":"2026-02-02T23:43:02.565Z","created_at":"2026-02-01T03:43:47.518Z","hf_updated_at":null,"name":"Free Models Router","short_name":"Free Models Router","author":"openrouter","author_display_name":"OpenRouter","author_icon_uri":null,"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that support features needed for your request such as image understanding, tool calling, structured outputs and more. ","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openrouter/free","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":null},{"slug":"stepfun/step-3.5-flash","hf_slug":"stepfun-ai/Step-3.5-Flash","updated_at":"2026-05-28T16:21:27.767Z","created_at":"2026-01-29T23:12:17.060Z","hf_updated_at":null,"name":"StepFun: Step 3.5 Flash","short_name":"Step 3.5 Flash","author":"stepfun","author_display_name":"stepfun","author_icon_uri":null,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"stepfun/step-3.5-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"24266140-f37e-4c0f-8898-30821cb00ae3","name":"SiliconFlow | stepfun/step-3.5-flash","context_length":262144,"model":{"slug":"stepfun/step-3.5-flash","hf_slug":"stepfun-ai/Step-3.5-Flash","updated_at":"2026-05-28T16:21:27.76715+00:00","created_at":"2026-01-29T23:12:17.060093+00:00","hf_updated_at":null,"name":"StepFun: Step 3.5 Flash","short_name":"Step 3.5 Flash","author":"stepfun","author_display_name":"stepfun","author_icon_uri":null,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"stepfun/step-3.5-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"stepfun/step-3.5-flash","model_variant_permaslug":"stepfun/step-3.5-flash","adapter_name":"SiliconFlowAdapter","provider_name":"SiliconFlow","provider_info":{"name":"SiliconFlow","displayName":"SiliconFlow","slug":"siliconflow","baseUrl":"https://api.siliconflow.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.siliconflow.com/en/legals/terms-of-service","privacyPolicyURL":"https://docs.siliconflow.com/en/legals/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"SiliconFlowAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/SiliconFlow.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"SiliconFlow","provider_slug":"siliconflow/fp8","provider_model_id":"stepfun-ai/Step-3.5-Flash","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.siliconflow.com/en/legals/terms-of-service","privacyPolicyURL":"https://docs.siliconflow.com/en/legals/privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000003"},"pricing_version_id":"40fbb2cd-42bf-49e5-a445-54d9b2ecfe12","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-24T10:45:28.864Z","status":0}},{"slug":"moonshotai/kimi-k2.5","hf_slug":"moonshotai/Kimi-K2.5","updated_at":"2026-04-20T15:39:00.712Z","created_at":"2026-01-27T04:11:16.000Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.5","short_name":"Kimi K2.5","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.5-0127","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a1659736-3cfc-47d9-b48f-303c93c57b11","name":"DeepInfra | moonshotai/kimi-k2.5-0127","context_length":262144,"model":{"slug":"moonshotai/kimi-k2.5","hf_slug":"moonshotai/Kimi-K2.5","updated_at":"2026-04-20T15:39:00.712521+00:00","created_at":"2026-01-27T04:11:16+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2.5","short_name":"Kimi K2.5","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2.5-0127","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"is_mandatory_reasoning":false,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":false,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2.5","model_variant_permaslug":"moonshotai/kimi-k2.5-0127","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"moonshotai/Kimi-K2.5","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000045","completion":"0.00000225","input_cache_read":"0.00000007","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000225","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000045","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000225","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000045","openai:completion_tokens":"0.00000225","openai:cached_prompt_tokens":"0.00000007"},"pricing_version_id":"b09e7117-be37-4a07-bcbe-129b08b483de","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-01-29T01:35:23.692Z","status":0}},{"slug":"upstage/solar-pro-3","hf_slug":"","updated_at":"2026-03-02T16:57:12.877Z","created_at":"2026-01-27T02:33:20.601Z","hf_updated_at":null,"name":"Upstage: Solar Pro 3","short_name":"Solar Pro 3","author":"upstage","author_display_name":"upstage","author_icon_uri":null,"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free Solar Pro 3 period has ended. To continue using this model, please migrate to the paid slug: upstage/solar-pro-3","required_attestation_types":[],"is_private":false,"permaslug":"upstage/solar-pro-3","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"64e8da4e-6768-4de2-a17d-8dba04f8cdac","name":"Upstage | upstage/solar-pro-3","context_length":131072,"model":{"slug":"upstage/solar-pro-3","hf_slug":"","updated_at":"2026-03-02T16:57:12.877811+00:00","created_at":"2026-01-27T02:33:20.601032+00:00","hf_updated_at":null,"name":"Upstage: Solar Pro 3","short_name":"Solar Pro 3","author":"upstage","author_display_name":"upstage","author_icon_uri":null,"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free Solar Pro 3 period has ended. To continue using this model, please migrate to the paid slug: upstage/solar-pro-3","required_attestation_types":[],"is_private":false,"permaslug":"upstage/solar-pro-3","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"upstage/solar-pro-3","model_variant_permaslug":"upstage/solar-pro-3","adapter_name":"UpstageAdapter","provider_name":"Upstage","provider_info":{"name":"Upstage","displayName":"Upstage","slug":"upstage","baseUrl":"https://api.upstage.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.upstage.ai/terms-of-service","privacyPolicyURL":"https://www.upstage.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"UpstageAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://upstage.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Upstage","provider_slug":"upstage","provider_model_id":"solar-pro3","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice","structured_outputs","response_format","top_p","frequency_penalty","presence_penalty"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.upstage.ai/terms-of-service","privacyPolicyURL":"https://www.upstage.ai/privacy-policy"},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.6e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.015e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.15e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.6e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.015e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.15e-6","openai:completion_tokens":"0.6e-6","openai:cached_prompt_tokens":"0.015e-6"},"pricing_version_id":"1a687694-0285-4550-a828-0d6b610acfa6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":1500000,"created_at":"2026-03-02T16:56:03.194Z","status":0}},{"slug":"minimax/minimax-m2-her","hf_slug":"","updated_at":"2026-02-15T16:31:03.972Z","created_at":"2026-01-23T14:07:19.197Z","hf_updated_at":null,"name":"MiniMax: MiniMax M2-her","short_name":"MiniMax M2-her","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2-her-20260123","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"38c32567-be85-4c82-a6d8-592a4158d436","name":"Minimax | minimax/minimax-m2-her-20260123","context_length":65536,"model":{"slug":"minimax/minimax-m2-her","hf_slug":"","updated_at":"2026-02-15T16:31:03.972308+00:00","created_at":"2026-01-23T14:07:19.197529+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M2-her","short_name":"MiniMax M2-her","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2-her-20260123","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m2-her","model_variant_permaslug":"minimax/minimax-m2-her-20260123","adapter_name":"MinimaxChatCompletionV2Adapter","provider_name":"Minimax","provider_info":{"name":"Minimax","displayName":"MiniMax","slug":"minimax","baseUrl":"https://api.minimax.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MinimaxChatCompletionV2Adapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://minimaxi.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"MiniMax","provider_slug":"minimax","provider_model_id":"M2-her","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":2048,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy"},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000012","openai:cached_prompt_tokens":"0.00000003","openai:cache_creation_tokens":"0.000000375"},"pricing_version_id":"436dcdbc-ba0a-4aa3-9ab5-273bacf9ad27","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":false,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-01-23T14:15:24.112Z","status":0}},{"slug":"writer/palmyra-x5","hf_slug":"","updated_at":"2026-01-21T17:42:14.484Z","created_at":"2026-01-21T13:57:03.149Z","hf_updated_at":null,"name":"Writer: Palmyra X5","short_name":"Palmyra X5","author":"writer","author_display_name":"Writer","author_icon_uri":null,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million tokens, powered by a novel transformer architecture and hybrid attention mechanisms. This enables faster inference and expanded memory for processing large volumes of enterprise data, critical for scaling AI agents.","model_version_group_id":null,"context_length":1040000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"writer/palmyra-x5-20250428","supports_reasoning":false,"reasoning_config":{},"features":{"reasoning_config":{},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c684c4e7-1b77-4ca5-9516-7ecc66e2c455","name":"Amazon Bedrock | writer/palmyra-x5-20250428","context_length":1040000,"model":{"slug":"writer/palmyra-x5","hf_slug":"","updated_at":"2026-01-21T17:42:14.484786+00:00","created_at":"2026-01-21T13:57:03.149236+00:00","hf_updated_at":null,"name":"Writer: Palmyra X5","short_name":"Palmyra X5","author":"writer","author_display_name":"Writer","author_icon_uri":null,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million tokens, powered by a novel transformer architecture and hybrid attention mechanisms. This enables faster inference and expanded memory for processing large volumes of enterprise data, critical for scaling AI agents.","model_version_group_id":null,"context_length":1040000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"writer/palmyra-x5-20250428","supports_reasoning":false,"reasoning_config":{},"features":{"reasoning_config":{},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"writer/palmyra-x5","model_variant_permaslug":"writer/palmyra-x5-20250428","adapter_name":"AmazonBedrockConverseAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"bedrock_converse"},"provider_display_name":"Amazon Bedrock","provider_slug":"amazon-bedrock","provider_model_id":"us.writer.palmyra-x5-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000006","completion":"0.000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"bedrock_converse:prompt_tokens":"0.0000006","bedrock_converse:completion_tokens":"0.000006"},"pricing_version_id":"cd085d7a-cab5-402b-b6c9-a479ee148ee8","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-01-21T17:01:51.559Z","status":0}},{"slug":"openai/gpt-audio","hf_slug":"","updated_at":"2026-05-29T23:00:33.657Z","created_at":"2026-01-19T22:42:49.327Z","hf_updated_at":null,"name":"OpenAI: GPT Audio","short_name":"GPT Audio","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced at $32 per million input tokens and $64 per million output tokens.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","audio"],"output_modalities":["text","audio"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-audio","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"df1ccb5f-8dce-4d7e-8a34-5a6613b65995","name":"OpenAI | openai/gpt-audio","context_length":128000,"model":{"slug":"openai/gpt-audio","hf_slug":"","updated_at":"2026-05-29T23:00:33.657231+00:00","created_at":"2026-01-19T22:42:49.327397+00:00","hf_updated_at":null,"name":"OpenAI: GPT Audio","short_name":"GPT Audio","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced at $32 per million input tokens and $64 per million output tokens.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","audio"],"output_modalities":["text","audio"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-audio","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-audio","model_variant_permaslug":"openai/gpt-audio","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-audio-2025-08-28","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.00001","audio":"0.000032","audio_output":"0.000064","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000032","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Audio","price":"0.000064","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000032","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Audio","price":"0.000064","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.0000025,"openai:completion_tokens":0.00001,"openai:audio_input_tokens":0.000032,"openai:audio_output_tokens":0.000064},"pricing_version_id":"c5b77fd6-5846-4419-9491-2005aef727ee","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_resolutions":null,"supported_aspect_ratios":null,"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-01-19T22:44:11.342Z","status":0}},{"slug":"openai/gpt-audio-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-01-19T21:50:19.564Z","hf_updated_at":null,"name":"OpenAI: GPT Audio Mini","short_name":"GPT Audio Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million tokens and output is priced at $2.40 per million tokens.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","audio"],"output_modalities":["text","audio"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-audio-mini","supports_reasoning":false,"reasoning_config":{},"features":{"reasoning_config":{},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"53417803-f19f-4905-af00-f7e023d09858","name":"OpenAI | openai/gpt-audio-mini","context_length":128000,"model":{"slug":"openai/gpt-audio-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-01-19T21:50:19.564599+00:00","hf_updated_at":null,"name":"OpenAI: GPT Audio Mini","short_name":"GPT Audio Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million tokens and output is priced at $2.40 per million tokens.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","audio"],"output_modalities":["text","audio"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-audio-mini","supports_reasoning":false,"reasoning_config":{},"features":{"reasoning_config":{},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-audio-mini","model_variant_permaslug":"openai/gpt-audio-mini","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-audio-mini-2025-12-15","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000006","completion":"0.0000024","audio":"0.0000006","audio_output":"0.0000024","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Audio","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Audio","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":6e-7,"openai:completion_tokens":0.0000024,"openai:audio_input_tokens":6e-7,"openai:audio_output_tokens":0.0000024},"pricing_version_id":"69b3ad5b-b161-4c4a-b2ca-2526b32a5b35","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_resolutions":null,"supported_aspect_ratios":null,"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-01-19T21:51:40.369Z","status":0}},{"slug":"z-ai/glm-4.7-flash","hf_slug":"zai-org/GLM-4.7-Flash","updated_at":"2026-02-11T14:52:26.120Z","created_at":"2026-01-19T14:45:13.352Z","hf_updated_at":null,"name":"Z.ai: GLM 4.7 Flash","short_name":"GLM 4.7 Flash","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.","model_version_group_id":null,"context_length":202752,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.7-flash-20260119","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6efb5994-8fcb-4300-9c64-ba393193f5f6","name":"DeepInfra | z-ai/glm-4.7-flash-20260119","context_length":202752,"model":{"slug":"z-ai/glm-4.7-flash","hf_slug":"zai-org/GLM-4.7-Flash","updated_at":"2026-02-11T14:52:26.120265+00:00","created_at":"2026-01-19T14:45:13.352372+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.7 Flash","short_name":"GLM 4.7 Flash","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.","model_version_group_id":null,"context_length":200000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.7-flash-20260119","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.7-flash","model_variant_permaslug":"z-ai/glm-4.7-flash-20260119","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"zai-org/GLM-4.7-Flash","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","structured_outputs","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000006","completion":"0.0000004","input_cache_read":"0.00000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000006","openai:completion_tokens":"0.0000004","openai:cached_prompt_tokens":"0.00000001"},"pricing_version_id":"169e02e5-75bd-42a3-991f-06378f435eff","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-02T18:55:18.786Z","status":0}},{"slug":"openai/gpt-5.2-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2026-01-14T16:48:35.067Z","hf_updated_at":null,"name":"OpenAI: GPT-5.2-Codex","short_name":"GPT-5.2-Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-codex-20260114","supports_reasoning":true,"reasoning_config":{"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"112d4970-7f22-40d4-8ddb-3ca917583981","name":"Azure | openai/gpt-5.2-codex-20260114","context_length":400000,"model":{"slug":"openai/gpt-5.2-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2026-01-14T16:48:35.067026+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.2-Codex","short_name":"GPT-5.2-Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-codex-20260114","supports_reasoning":true,"reasoning_config":{"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.2-codex","model_variant_permaslug":"openai/gpt-5.2-codex-20260114","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.2-codex","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"0.00000175","openai_responses:completion_tokens":"0.000014","openai_responses:cached_prompt_tokens":"1.75e-7"},"pricing_version_id":"6402f409-1f1d-4df7-85ed-5c65e4ec2d86","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_apply_patch":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T16:02:30.861Z","status":0}},{"slug":"bytedance-seed/seed-1.6-flash","hf_slug":"","updated_at":"2025-12-23T15:50:11.246Z","created_at":"2025-12-23T15:50:11.000Z","hf_updated_at":null,"name":"ByteDance Seed: Seed 1.6 Flash","short_name":"Seed 1.6 Flash","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-1.6-flash-20250625","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e01a1227-001b-44d4-a376-90850668fa84","name":"Seed | bytedance-seed/seed-1.6-flash-20250625","context_length":262144,"model":{"slug":"bytedance-seed/seed-1.6-flash","hf_slug":"","updated_at":"2025-12-23T15:50:11.246001+00:00","created_at":"2025-12-23T15:50:11+00:00","hf_updated_at":null,"name":"ByteDance Seed: Seed 1.6 Flash","short_name":"Seed 1.6 Flash","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-1.6-flash-20250625","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance-seed/seed-1.6-flash","model_variant_permaslug":"bytedance-seed/seed-1.6-flash-20250625","adapter_name":"BytePlusAdapter","provider_name":"Seed","provider_info":{"name":"Seed","displayName":"Seed","slug":"seed","baseUrl":"https://ark.ap-southeast.bytepluses.com/api/v3","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"BytePlusAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256"},"sendClientIp":false,"pricingStrategy":"byteplus"},"provider_display_name":"Seed","provider_slug":"seed/fp8","provider_model_id":"ep-20251022091553-b9gf5","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy"},"pricing":{"prompt":"0.000000075","completion":"0.0000003","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000001","completion":"0.0000008"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000000075"},{"sku_label":">128K","price":"0.0000001"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000003"},{"sku_label":">128K","price":"0.0000008"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000000075"},{"sku_label":">128K","price":"0.0000001"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.0000003"},{"sku_label":">128K","price":"0.0000008"}]}],"pricing_json":{"byteplus:prompt_tokens":"0.000000075","byteplus:completion_tokens":"0.0000003","byteplus:long_context_threshold":"128000","byteplus:prompt_tokens_long_context":"0.0000001","byteplus:completion_tokens_long_context":"0.0000008"},"pricing_version_id":"29797e9e-b47b-44fc-935e-88c45a2a9678","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-22T17:22:19.760Z","status":0}},{"slug":"bytedance-seed/seed-1.6","hf_slug":"","updated_at":"2025-12-23T15:49:57.589Z","created_at":"2025-12-23T15:49:57.000Z","hf_updated_at":null,"name":"ByteDance Seed: Seed 1.6","short_name":"Seed 1.6","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-1.6-20250625","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d85c3862-4e0d-4f8d-955b-babc62f98124","name":"Seed | bytedance-seed/seed-1.6-20250625","context_length":262144,"model":{"slug":"bytedance-seed/seed-1.6","hf_slug":"","updated_at":"2025-12-23T15:49:57.589744+00:00","created_at":"2025-12-23T15:49:57+00:00","hf_updated_at":null,"name":"ByteDance Seed: Seed 1.6","short_name":"Seed 1.6","author":"bytedance-seed","author_display_name":"bytedance-seed","author_icon_uri":null,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"bytedance-seed/seed-1.6-20250625","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance-seed/seed-1.6","model_variant_permaslug":"bytedance-seed/seed-1.6-20250625","adapter_name":"BytePlusAdapter","provider_name":"Seed","provider_info":{"name":"Seed","displayName":"Seed","slug":"seed","baseUrl":"https://ark.ap-southeast.bytepluses.com/api/v3","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"BytePlusAdapter","statusPageUrl":null,"byokEnabled":false,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://avatars.githubusercontent.com/u/4158466?v=4&size=256"},"sendClientIp":false,"pricingStrategy":"byteplus"},"provider_display_name":"Seed","provider_slug":"seed/fp8","provider_model_id":"ep-20251022091355-w7xt5","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","privacyPolicyURL":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy"},"pricing":{"prompt":"0.00000025","completion":"0.000002","discount":0,"overrides":[{"min_prompt_tokens":128000,"prompt":"0.0000005","completion":"0.000004"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.00000025"},{"sku_label":">128K","price":"0.0000005"}]},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000002"},{"sku_label":">128K","price":"0.000004"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.00000025"},{"sku_label":">128K","price":"0.0000005"}]},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤128K","price":"0.000002"},{"sku_label":">128K","price":"0.000004"}]}],"pricing_json":{"byteplus:prompt_tokens":"0.00000025","byteplus:completion_tokens":"0.000002","byteplus:long_context_threshold":"128000","byteplus:prompt_tokens_long_context":"0.0000005","byteplus:completion_tokens_long_context":"0.000004"},"pricing_version_id":"8d4a996e-c067-4157-b7cf-4e933c622842","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-22T16:25:52.251Z","status":0}},{"slug":"minimax/minimax-m2.1","hf_slug":"MiniMaxAI/MiniMax-M2.1","updated_at":"2026-01-08T19:23:52.555Z","created_at":"2025-12-23T01:56:37.000Z","hf_updated_at":null,"name":"MiniMax: MiniMax M2.1","short_name":"MiniMax M2.1","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.\n\nCompared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":"You are MiniMax-M2.1, a helpful AI assistant built by MiniMax. Knowledge cutoff: 2025-06.","default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2.1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.9,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a300fcbb-ec0e-4c1f-a4d4-d06dc8c19cf9","name":"Novita | minimax/minimax-m2.1","context_length":204800,"model":{"slug":"minimax/minimax-m2.1","hf_slug":"MiniMaxAI/MiniMax-M2.1","updated_at":"2026-01-08T19:23:52.555156+00:00","created_at":"2025-12-23T01:56:37+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M2.1","short_name":"MiniMax M2.1","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.\n\nCompared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":"You are MiniMax-M2.1, a helpful AI assistant built by MiniMax. Knowledge cutoff: 2025-06.","default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2.1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.9,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m2.1","model_variant_permaslug":"minimax/minimax-m2.1","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"minimax/minimax-m2.1","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000012","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"c30e983e-bb66-4999-aa91-5957c4b772a0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-29T13:35:09.367Z","status":0}},{"slug":"z-ai/glm-4.7","hf_slug":"zai-org/GLM-4.7","updated_at":"2026-07-19T13:59:53.415Z","created_at":"2025-12-22T04:33:34.884Z","hf_updated_at":null,"name":"Z.ai: GLM 4.7","short_name":"GLM 4.7","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.7-20251222","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"ab79ffa8-8dcc-41c4-9a9f-6cc408135243","name":"DeepInfra | z-ai/glm-4.7-20251222","context_length":202752,"model":{"slug":"z-ai/glm-4.7","hf_slug":"zai-org/GLM-4.7","updated_at":"2026-07-19T13:59:53.415418+00:00","created_at":"2025-12-22T04:33:34.884504+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.7","short_name":"GLM 4.7","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.","model_version_group_id":null,"context_length":200000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.7-20251222","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true,"reasoning_return_mechanism":"reasoning-content"},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.7","model_variant_permaslug":"z-ai/glm-4.7-20251222","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"zai-org/GLM-4.7","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000004","completion":"0.00000175","input_cache_read":"0.00000008","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000004","openai:completion_tokens":"0.00000175","openai:cached_prompt_tokens":"0.00000008"},"pricing_version_id":"726476f9-2f3f-4341-a556-8138d0b62479","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-23T19:40:34.986Z","status":-5}},{"slug":"google/gemini-3-flash-preview","hf_slug":"","updated_at":"2026-04-27T19:36:36.393Z","created_at":"2025-12-17T15:57:58.000Z","hf_updated_at":null,"name":"Google: Gemini 3 Flash Preview (batch)","short_name":"Gemini 3 Flash Preview (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-flash-preview-20251217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"1f93e91a-080f-4ac4-a092-c86d90a2442c","name":"Google | google/gemini-3-flash-preview-20251217:batch","context_length":1048576,"model":{"slug":"google/gemini-3-flash-preview","hf_slug":"","updated_at":"2026-04-27T19:36:36.393512+00:00","created_at":"2025-12-17T15:57:58+00:00","hf_updated_at":null,"name":"Google: Gemini 3 Flash Preview","short_name":"Gemini 3 Flash Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-flash-preview-20251217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3-flash-preview:batch","model_variant_permaslug":"google/gemini-3-flash-preview-20251217:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-3-flash-preview","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","web_search":"0.014","internal_reasoning":"0.0000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":2.5e-7,"gemini:reasoning_tokens":0.0000015,"gemini:web_search_calls":"0.014","gemini:completion_tokens":0.0000015,"gemini:text_input_tokens":2.5e-7,"gemini:audio_input_tokens":5e-7,"gemini:image_input_tokens":2.5e-7,"gemini:video_input_tokens":2.5e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"d9dc2429-3ed7-49cf-af38-857bb1ecc041","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":false,"supports_native_web_search":true,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:08:02.756Z","status":0}},{"slug":"google/gemini-3-flash-preview","hf_slug":"","updated_at":"2026-04-27T19:36:36.393Z","created_at":"2025-12-17T15:57:58.000Z","hf_updated_at":null,"name":"Google: Gemini 3 Flash Preview","short_name":"Gemini 3 Flash Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-flash-preview-20251217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"6e82f652-2693-4b60-bbe0-7362d6e345f0","name":"Google AI Studio | google/gemini-3-flash-preview-20251217","context_length":1048576,"model":{"slug":"google/gemini-3-flash-preview","hf_slug":"","updated_at":"2026-04-27T19:36:36.393512+00:00","created_at":"2025-12-17T15:57:58+00:00","hf_updated_at":null,"name":"Google: Gemini 3 Flash Preview","short_name":"Gemini 3 Flash Preview","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","model_version_group_id":"53bf98ea-c68f-471f-95cd-a59b3a9881bb","context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-flash-preview-20251217","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":null,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high","minimal"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex","google-ai-studio"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3-flash-preview","model_variant_permaslug":"google/gemini-3-flash-preview-20251217","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-3-flash-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005","audio":"0.000001","input_audio_cache":"0.0000001","input_cache_read":"0.00000005","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":5e-7,"gemini:reasoning_tokens":0.000003,"gemini:cache_read_tokens":5e-8,"gemini:completion_tokens":0.000003,"gemini:text_input_tokens":5e-7,"gemini:audio_input_tokens":0.000001,"gemini:image_input_tokens":5e-7,"gemini:video_input_tokens":5e-7,"gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":5e-8,"gemini:cache_read_audio_tokens":1e-7,"gemini:cache_read_image_tokens":5e-8,"gemini:cache_read_video_tokens":5e-8,"gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":0.000001,"gemini:cache_read_tokens_high_context":1e-7,"gemini:cache_read_text_tokens_high_context":1e-7,"gemini:cache_read_audio_tokens_high_context":2e-7,"gemini:cache_read_image_tokens_high_context":1e-7,"gemini:cache_read_video_tokens_high_context":1e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"20cdc7df-d776-4175-b3ca-79e8396686f3","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":450,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_base64_video_input":true,"supports_video_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-17T16:11:08.603Z","status":0}},{"slug":"nvidia/nemotron-3-nano-30b-a3b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","updated_at":"2026-08-11T21:48:55.880Z","created_at":"2025-12-14T16:54:35.000Z","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","short_name":"Nemotron 3 Nano 30B A3B","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.\n\nThe model is fully open with open-weights, datasets and recipes so developers can easily\ncustomize, optimize, and deploy the model on their infrastructure for maximum privacy and\nsecurity.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](<https://www.nvidia.com/en-us/about-nvidia/privacy-policy/>). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](<https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf>)","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-nano-30b-a3b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2bd3912d-8b35-4818-b873-24ccfefa6cf9","name":"DeepInfra | nvidia/nemotron-3-nano-30b-a3b","context_length":262144,"model":{"slug":"nvidia/nemotron-3-nano-30b-a3b","hf_slug":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","updated_at":"2026-08-11T21:48:55.880726+00:00","created_at":"2025-12-14T16:54:35+00:00","hf_updated_at":null,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","short_name":"Nemotron 3 Nano 30B A3B","author":"nvidia","author_display_name":"Nvidia","author_icon_uri":null,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.\n\nThe model is fully open with open-weights, datasets and recipes so developers can easily\ncustomize, optimize, and deploy the model on their infrastructure for maximum privacy and\nsecurity.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see [Privacy Policy](<https://www.nvidia.com/en-us/about-nvidia/privacy-policy/>). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](<https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf>)","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"nvidia/nemotron-3-nano-30b-a3b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"nvidia/nemotron-3-nano-30b-a3b","model_variant_permaslug":"nvidia/nemotron-3-nano-30b-a3b","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"nvidia/Nemotron-3-Nano-30B-A3B","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":228000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tool_choice","tools","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000005","completion":"0.0000002","input_cache_read":"0.000000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000005","openai:completion_tokens":"0.0000002","openai:cached_prompt_tokens":"0.000000025"},"pricing_version_id":"3e752337-31ad-4e08-b961-d6ed4e853dc9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-15T22:43:17.856Z","status":0}},{"slug":"openai/gpt-5.2-chat","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-12-10T18:03:03.398Z","hf_updated_at":null,"name":"OpenAI: GPT-5.2 Chat","short_name":"GPT-5.2 Chat","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.2 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.","model_version_group_id":null,"context_length":128000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-chat-20251211","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d07e4a1d-4d2a-4d11-92dc-2985c1a5a596","name":"Azure | openai/gpt-5.2-chat-20251211","context_length":128000,"model":{"slug":"openai/gpt-5.2-chat","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-12-10T18:03:03.398082+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.2 Chat","short_name":"GPT-5.2 Chat","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.2 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.","model_version_group_id":null,"context_length":128000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-chat-20251211","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.2-chat","model_variant_permaslug":"openai/gpt-5.2-chat-20251211","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.2-chat","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":96000,"max_completion_tokens":32000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","structured_outputs","response_format","seed","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.00000175,"openai_responses:completion_tokens":0.000014,"openai_responses:cached_prompt_tokens":1.75e-7},"pricing_version_id":"c2440f19-600e-42e3-8313-7f969571f44b","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":10000000,"created_at":"2026-01-06T00:46:01.181Z","status":0}},{"slug":"openai/gpt-5.2-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-12-10T18:03:00.055Z","hf_updated_at":null,"name":"OpenAI: GPT-5.2 Pro (batch)","short_name":"GPT-5.2 Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-pro-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8bb13b1e-8039-4bb4-a532-7ecf2ad5f4b6","name":"OpenAI | openai/gpt-5.2-pro-20251211:batch","context_length":400000,"model":{"slug":"openai/gpt-5.2-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-12-10T18:03:00.055991+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.2 Pro","short_name":"GPT-5.2 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-pro-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.2-pro:batch","model_variant_permaslug":"openai/gpt-5.2-pro-20251211:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.2-pro-2025-12-11","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000105","completion":"0.000084","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.050000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"8.400000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.050000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"8.400000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.050000e-5","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"8.400000e-5"},"pricing_version_id":"3159db7e-3e8a-410e-b0b3-ae029c53f22b","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:23.928Z","status":0}},{"slug":"openai/gpt-5.2-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-12-10T18:03:00.055Z","hf_updated_at":null,"name":"OpenAI: GPT-5.2 Pro","short_name":"GPT-5.2 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-pro-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1abae580-6f7a-4092-ae6c-b87ce6067f61","name":"OpenAI | openai/gpt-5.2-pro-20251211","context_length":400000,"model":{"slug":"openai/gpt-5.2-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-12-10T18:03:00.055991+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.2 Pro","short_name":"GPT-5.2 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-pro-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["medium","high","xhigh"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.2-pro","model_variant_permaslug":"openai/gpt-5.2-pro-20251211","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.2-pro-2025-12-11","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000021","completion":"0.000168","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000021","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000168","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000021","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000168","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.000021,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.000168},"pricing_version_id":"28cb6295-41bb-4331-80fc-0126e243b777","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-10T18:29:21.427Z","status":0}},{"slug":"openai/gpt-5.2","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-12-10T18:02:55.765Z","hf_updated_at":null,"name":"OpenAI: GPT-5.2","short_name":"GPT-5.2","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1b754062-b0f3-4cab-89d6-48b43782a25d","name":"Azure | openai/gpt-5.2-20251211","context_length":400000,"model":{"slug":"openai/gpt-5.2","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-12-10T18:02:55.765028+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.2","short_name":"GPT-5.2","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.2","model_variant_permaslug":"openai/gpt-5.2-20251211","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.2","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.00000175,"openai_responses:completion_tokens":0.000014,"openai_responses:cached_prompt_tokens":1.75e-7},"pricing_version_id":"e6bc28b8-be2e-49bb-b64b-edc42b14e96c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":10000000,"created_at":"2026-01-06T00:46:01.181Z","status":0}},{"slug":"openai/gpt-5.2","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-12-10T18:02:55.765Z","hf_updated_at":null,"name":"OpenAI: GPT-5.2 (batch)","short_name":"GPT-5.2 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1a1f1f74-906f-4e46-a14c-78640ec6bfee","name":"OpenAI | openai/gpt-5.2-20251211:batch","context_length":400000,"model":{"slug":"openai/gpt-5.2","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-12-10T18:02:55.765028+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.2","short_name":"GPT-5.2","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.2-20251211","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high","xhigh"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.2:batch","model_variant_permaslug":"openai/gpt-5.2-20251211:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.2-2025-12-11","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000875","completion":"0.000007","input_cache_read":"0.0000000875","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"8.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"8.750000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"8.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"8.750000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"8.750000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"7.000000e-6","openai_responses:cached_prompt_tokens":"8.750000e-8","openai_responses:flex_tier_multiplier":"0.5","openai_responses:priority_tier_multiplier":"2"},"pricing_version_id":"eb3812d2-d364-442f-bb71-3e1f106b892d","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:52.389Z","status":0}},{"slug":"mistralai/devstral-2512","hf_slug":"mistralai/Devstral-2-123B-Instruct-2512","updated_at":"2026-05-14T22:39:37.042Z","created_at":"2025-12-09T13:03:39.000Z","hf_updated_at":null,"name":"Mistral: Devstral 2 2512","short_name":"Devstral 2 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.\n\nDevstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free Devstral 2 2512 period has ended. To continue using this model, please migrate to the paid slug: mistralai/devstral-2512","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/devstral-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4c36e65e-bcbc-4015-93a3-016865d9c861","name":"Mistral | mistralai/devstral-2512","context_length":262144,"model":{"slug":"mistralai/devstral-2512","hf_slug":"mistralai/Devstral-2-123B-Instruct-2512","updated_at":"2026-05-14T22:39:37.042733+00:00","created_at":"2025-12-09T13:03:39+00:00","hf_updated_at":null,"name":"Mistral: Devstral 2 2512","short_name":"Devstral 2 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.\n\nDevstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free Devstral 2 2512 period has ended. To continue using this model, please migrate to the paid slug: mistralai/devstral-2512","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/devstral-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/devstral-2512","model_variant_permaslug":"mistralai/devstral-2512","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.eu.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral/eu","provider_model_id":"devstral-2512","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000044","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000044","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.00000044","mistral:completion_tokens":"0.0000022","mistral:cached_prompt_tokens":"0.000000044"},"pricing_version_id":"fc09b8a2-21ae-4c87-bc7e-25513b57fa56","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"eu","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-19T19:49:09.303Z","status":-5}},{"slug":"relace/relace-search","hf_slug":null,"updated_at":"2025-12-08T17:15:38.319Z","created_at":"2025-12-08T17:06:00.000Z","hf_updated_at":null,"name":"Relace: Relace Search","short_name":"Relace Search","author":"relace","author_display_name":"relace","author_icon_uri":null,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. \n\nIn contrast to RAG, relace-search performs agentic multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an \"oracle\" coding agent, who orchestrates/performs the rest of the coding task.\n\nTo use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the [Relace documentation](https://docs.relace.ai/docs/fast-agentic-search/agent).","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"relace/relace-search-20251208","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"fbf41fc0-742d-4108-b97e-147ee85eff31","name":"Relace | relace/relace-search-20251208","context_length":256000,"model":{"slug":"relace/relace-search","hf_slug":null,"updated_at":"2025-12-08T17:15:38.31992+00:00","created_at":"2025-12-08T17:06:00+00:00","hf_updated_at":null,"name":"Relace: Relace Search","short_name":"Relace Search","author":"relace","author_display_name":"relace","author_icon_uri":null,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. \n\nIn contrast to RAG, relace-search performs agentic multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an \"oracle\" coding agent, who orchestrates/performs the rest of the coding task.\n\nTo use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the [Relace documentation](https://docs.relace.ai/docs/fast-agentic-search/agent).","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"relace/relace-search-20251208","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"relace/relace-search","model_variant_permaslug":"relace/relace-search-20251208","adapter_name":"OpenAIAdapter","provider_name":"Relace","provider_info":{"name":"Relace","displayName":"Relace","slug":"relace","baseUrl":"https://models.relace.ai/v1/search","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://relace.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Relace","provider_slug":"relace/bf16","provider_model_id":"relace-search","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["tools","tool_choice","response_format","temperature","top_p","stop","seed","max_tokens"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy"},"pricing":{"prompt":"0.000001","completion":"0.000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000001","openai:completion_tokens":"0.000003"},"pricing_version_id":"cd3d8a1d-244a-476a-87dd-a6b67f3b4170","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":100,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-11-24T16:04:24.562Z","status":0}},{"slug":"z-ai/glm-4.6v","hf_slug":"zai-org/GLM-4.6V","updated_at":"2026-02-11T14:52:35.163Z","created_at":"2025-12-08T15:24:22.464Z","hf_updated_at":null,"name":"Z.ai: GLM 4.6V","short_name":"GLM 4.6V","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.6-20251208","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.8,"top_p":0.6,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a44ea9fe-fc2b-4765-804b-2e31215b5ca5","name":"Novita | z-ai/glm-4.6-20251208","context_length":131072,"model":{"slug":"z-ai/glm-4.6v","hf_slug":"zai-org/GLM-4.6V","updated_at":"2026-02-11T14:52:35.163983+00:00","created_at":"2025-12-08T15:24:22.464154+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.6V","short_name":"GLM 4.6V","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text","video"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.6-20251208","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.8,"top_p":0.6,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.6v","model_variant_permaslug":"z-ai/glm-4.6-20251208","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/bf16","provider_model_id":"zai-org/glm-4.6v","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.000000055","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000055","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000055","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000009","openai:cached_prompt_tokens":"0.000000055"},"pricing_version_id":"39e5876c-8050-4a5a-a700-9f1784e60619","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_base64_video_input":false,"supports_video_urls":false,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-09T01:31:51.193Z","status":-2}},{"slug":"openrouter/bodybuilder","hf_slug":"","updated_at":"2025-12-15T14:27:58.552Z","created_at":"2025-12-05T03:00:53.239Z","hf_updated_at":null,"name":"Body Builder (beta)","short_name":"Body Builder (beta)","author":"openrouter","author_display_name":"OpenRouter","author_icon_uri":null,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example: \"count to 10 using gemini and opus.\"\n\nThis is useful for creating multi-model requests, custom model routers, or programmatic generation of API calls from human descriptions.\n\n**BETA NOTICE**: Body Builder is in beta, and currently free. Pricing and functionality may change in the future.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openrouter/bodybuilder","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"text","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":null},{"slug":"openai/gpt-5.1-codex-max","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-12-04T20:08:54.100Z","hf_updated_at":null,"name":"OpenAI: GPT-5.1-Codex-Max","short_name":"GPT-5.1-Codex-Max","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. \nGPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle. ","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-codex-max-20251204","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"40b40238-5f11-44f4-b56b-0c702bd6c5b2","name":"Azure | openai/gpt-5.1-codex-max-20251204","context_length":400000,"model":{"slug":"openai/gpt-5.1-codex-max","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-12-04T20:08:54.10013+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.1-Codex-Max","short_name":"GPT-5.1-Codex-Max","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. \nGPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle. ","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-codex-max-20251204","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high","xhigh"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.1-codex-max","model_variant_permaslug":"openai/gpt-5.1-codex-max-20251204","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.1-codex-max","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.00000125,"openai_responses:completion_tokens":0.00001,"openai_responses:cached_prompt_tokens":1.25e-7},"pricing_version_id":"af20e033-f7e3-42fb-90af-295012bd87e2","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":10000000,"created_at":"2026-01-06T00:46:01.181Z","status":0}},{"slug":"amazon/nova-2-lite-v1","hf_slug":"","updated_at":"2025-12-05T00:11:57.060Z","created_at":"2025-12-02T17:31:12.000Z","hf_updated_at":null,"name":"Amazon: Nova 2 Lite","short_name":"Nova 2 Lite","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. \n\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-2-lite-v1","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b1b489e5-7029-4ab2-9e12-5415b55b4afa","name":"Amazon Bedrock | amazon/nova-2-lite-v1","context_length":1000000,"model":{"slug":"amazon/nova-2-lite-v1","hf_slug":"","updated_at":"2025-12-05T00:11:57.060181+00:00","created_at":"2025-12-02T17:31:12+00:00","hf_updated_at":null,"name":"Amazon: Nova 2 Lite","short_name":"Nova 2 Lite","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. \n\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-2-lite-v1","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"amazon/nova-2-lite-v1","model_variant_permaslug":"amazon/nova-2-lite-v1","adapter_name":"AmazonBedrockConverseNovaReasoningAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseNovaReasoningAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"bedrock_converse"},"provider_display_name":"Amazon Bedrock (ZDR)","provider_slug":"amazon-bedrock","provider_model_id":"us.amazon.nova-2-lite-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65535,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000003","completion":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"bedrock_converse:prompt_tokens":"0.0000003","bedrock_converse:completion_tokens":"0.0000025"},"pricing_version_id":"5726c5b8-108e-4be2-ace6-ad23c184fa54","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_base64_video_input":true,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-11-29T06:52:23.017Z","status":0}},{"slug":"mistralai/ministral-14b-2512","hf_slug":"mistralai/Ministral-3-14B-Instruct-2512","updated_at":"2025-12-10T16:54:21.432Z","created_at":"2025-12-02T13:22:15.851Z","hf_updated_at":null,"name":"Mistral: Ministral 3 14B 2512","short_name":"Ministral 3 14B 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-14b-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"92bddaca-2023-43db-b04f-97032276bc71","name":"Mistral | mistralai/ministral-14b-2512","context_length":262144,"model":{"slug":"mistralai/ministral-14b-2512","hf_slug":"mistralai/Ministral-3-14B-Instruct-2512","updated_at":"2025-12-10T16:54:21.432818+00:00","created_at":"2025-12-02T13:22:15.851192+00:00","hf_updated_at":null,"name":"Mistral: Ministral 3 14B 2512","short_name":"Ministral 3 14B 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-14b-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/ministral-14b-2512","model_variant_permaslug":"mistralai/ministral-14b-2512","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral/zdr","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral (ZDR)","provider_slug":"mistral/zdr","provider_model_id":"ministral-14b-2512","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.0000002","mistral:completion_tokens":2e-7,"mistral:cached_prompt_tokens":"0.00000002"},"pricing_version_id":"c264ef66-2985-4b9b-95e7-bacd1ee7010d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T16:05:02.410Z","status":-5}},{"slug":"mistralai/ministral-8b-2512","hf_slug":"mistralai/Ministral-3-8B-Instruct-2512","updated_at":"2025-12-10T16:54:03.715Z","created_at":"2025-12-02T13:20:54.103Z","hf_updated_at":null,"name":"Mistral: Ministral 3 8B 2512","short_name":"Ministral 3 8B 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-8b-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4cd33cd8-b087-45c0-ad7f-424100ba09a4","name":"Mistral | mistralai/ministral-8b-2512","context_length":262144,"model":{"slug":"mistralai/ministral-8b-2512","hf_slug":"mistralai/Ministral-3-8B-Instruct-2512","updated_at":"2025-12-10T16:54:03.715606+00:00","created_at":"2025-12-02T13:20:54.103183+00:00","hf_updated_at":null,"name":"Mistral: Ministral 3 8B 2512","short_name":"Ministral 3 8B 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-8b-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/ministral-8b-2512","model_variant_permaslug":"mistralai/ministral-8b-2512","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral/zdr","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral (ZDR)","provider_slug":"mistral/zdr","provider_model_id":"ministral-8b-2512","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.00000015","mistral:completion_tokens":1.5e-7,"mistral:cached_prompt_tokens":"0.000000015"},"pricing_version_id":"ce6e321a-7ab0-44ac-8775-33ca82f44b23","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T16:05:12.635Z","status":-5}},{"slug":"mistralai/ministral-3b-2512","hf_slug":"mistralai/Ministral-3-3B-Instruct-2512","updated_at":"2025-12-10T16:53:53.577Z","created_at":"2025-12-02T13:19:20.726Z","hf_updated_at":null,"name":"Mistral: Ministral 3 3B 2512","short_name":"Ministral 3 3B 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-3b-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b32dc02b-9622-4917-b3ed-a37798d30c91","name":"Mistral | mistralai/ministral-3b-2512","context_length":131072,"model":{"slug":"mistralai/ministral-3b-2512","hf_slug":"mistralai/Ministral-3-3B-Instruct-2512","updated_at":"2025-12-10T16:53:53.577361+00:00","created_at":"2025-12-02T13:19:20.726635+00:00","hf_updated_at":null,"name":"Mistral: Ministral 3 3B 2512","short_name":"Ministral 3 3B 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-3b-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/ministral-3b-2512","model_variant_permaslug":"mistralai/ministral-3b-2512","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral/zdr","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral (ZDR)","provider_slug":"mistral/zdr","provider_model_id":"ministral-3b-2512","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.0000001","mistral:completion_tokens":1e-7,"mistral:cached_prompt_tokens":"0.00000001"},"pricing_version_id":"fa2bcee0-26f3-4290-8e71-f0e1b6cd97e1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T16:05:10.864Z","status":0}},{"slug":"mistralai/mistral-large-2512","hf_slug":"","updated_at":"2026-05-14T22:39:37.721Z","created_at":"2025-12-01T21:27:52.651Z","hf_updated_at":null,"name":"Mistral: Mistral Large 3 2512","short_name":"Mistral Large 3 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-large-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.0645,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"text","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"66d228a7-697c-4868-a1bf-531cf47e2dff","name":"Mistral | mistralai/mistral-large-2512","context_length":262144,"model":{"slug":"mistralai/mistral-large-2512","hf_slug":"","updated_at":"2026-05-14T22:39:37.721339+00:00","created_at":"2025-12-01T21:27:52.65109+00:00","hf_updated_at":null,"name":"Mistral: Mistral Large 3 2512","short_name":"Mistral Large 3 2512","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","model_version_group_id":null,"context_length":256000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-large-2512","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.0645,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"text","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-large-2512","model_variant_permaslug":"mistralai/mistral-large-2512","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral/zdr","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral (ZDR)","provider_slug":"mistral/zdr","provider_model_id":"mistral-large-2512","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.0000005","mistral:completion_tokens":0.0000015,"mistral:cached_prompt_tokens":"0.00000005"},"pricing_version_id":"e2d8d929-ff08-4348-9272-858b7a06f460","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T16:05:17.732Z","status":-5}},{"slug":"deepseek/deepseek-v3.2","hf_slug":"deepseek-ai/DeepSeek-V3.2","updated_at":"2026-03-03T14:24:05.821Z","created_at":"2025-12-01T13:10:42.818Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.2","short_name":"DeepSeek V3.2","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.\n\nUsers can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v3.2-20251201","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4a4416f7-de7b-42d6-982d-3ab52d67a775","name":"GMICloud | deepseek/deepseek-v3.2-20251201","context_length":163840,"model":{"slug":"deepseek/deepseek-v3.2","hf_slug":"deepseek-ai/DeepSeek-V3.2","updated_at":"2026-03-03T14:24:05.821681+00:00","created_at":"2025-12-01T13:10:42.818885+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.2","short_name":"DeepSeek V3.2","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.\n\nUsers can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"","required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v3.2-20251201","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":false},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":false},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v3.2","model_variant_permaslug":"deepseek/deepseek-v3.2-20251201","adapter_name":"GMICloudAdapter","provider_name":"GMICloud","provider_info":{"name":"GMICloud","displayName":"GMICloud","slug":"gmicloud","baseUrl":"https://api.gmi-serving.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"GMICloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://gmicloud.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"GMICloud","provider_slug":"gmicloud/fp8","provider_model_id":"deepseek-ai/DeepSeek-V3.2","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy"},"pricing":{"prompt":"0.0000002088","completion":"0.0000003096","input_cache_read":"0.0000000216","discount":0.28,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002088","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003096","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000216","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002088","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003096","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000216","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000029","openai:completion_tokens":"0.00000043","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"2e908b01-93d4-42a8-a1ef-0c899e502970","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-06T17:41:51.619Z","status":0}},{"slug":"anthropic/claude-opus-4.5","hf_slug":"","updated_at":"2026-08-18T00:41:18.543Z","created_at":"2025-11-24T18:56:20.000Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.5 (batch)","short_name":"Claude Opus 4.5 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","model_version_group_id":null,"context_length":200000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-opus-20251124","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{},"default_order":["amazon-bedrock","google-vertex/global","claude-on-aws","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"672356cd-5f32-4756-b0aa-5c0aef4bfc88","name":"Anthropic | anthropic/claude-4.5-opus-20251124:batch","context_length":200000,"model":{"slug":"anthropic/claude-opus-4.5","hf_slug":"","updated_at":"2026-08-18T00:41:18.543714+00:00","created_at":"2025-11-24T18:56:20+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.5","short_name":"Claude Opus 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","model_version_group_id":null,"context_length":200000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-opus-20251124","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{},"default_order":["amazon-bedrock","google-vertex/global","claude-on-aws","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.5:batch","model_variant_permaslug":"anthropic/claude-4.5-opus-20251124:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-5-20251101","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.00000025","input_cache_write":"0.000003125","input_cache_write_1h":"0.000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000003125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000025","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"2.5e-7","anthropic:completion_tokens":"0.0000125","anthropic:cache_write_1h_tokens":"0.000005","anthropic:cache_write_5m_tokens":"0.000003125"},"pricing_version_id":"d4fc08c7-7031-4cc2-afce-79f396abcabb","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:09:38.136Z","status":0}},{"slug":"anthropic/claude-opus-4.5","hf_slug":"","updated_at":"2026-08-18T00:41:18.543Z","created_at":"2025-11-24T18:56:20.000Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.5","short_name":"Claude Opus 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","model_version_group_id":null,"context_length":200000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-opus-20251124","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{},"default_order":["amazon-bedrock","google-vertex/global","claude-on-aws","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"4d2d1f7b-36e3-4858-a7a3-0404d6f71c0c","name":"Claude Platform on AWS | anthropic/claude-4.5-opus-20251124","context_length":200000,"model":{"slug":"anthropic/claude-opus-4.5","hf_slug":"","updated_at":"2026-08-18T00:41:18.543714+00:00","created_at":"2025-11-24T18:56:20+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.5","short_name":"Claude Opus 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","model_version_group_id":null,"context_length":200000,"input_modalities":["file","image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-opus-20251124","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{},"default_order":["amazon-bedrock","google-vertex/global","claude-on-aws","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.5","model_variant_permaslug":"anthropic/claude-4.5-opus-20251124","adapter_name":"ClaudeOnAwsAdapter","provider_name":"Claude Platform on AWS","provider_info":{"name":"Claude Platform on AWS","displayName":"Claude Platform on AWS","slug":"claude-on-aws","baseUrl":"https://aws-external-anthropic.us-east-1.api.aws/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"ClaudeOnAwsAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":false,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Claude Platform on AWS","provider_slug":"claude-on-aws","provider_model_id":"claude-opus-4-5-20251101","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tool_choice","tools","structured_outputs","response_format","verbosity"],"excluded_parameters":["top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000625","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000625","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.000005","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"0.0000005","anthropic:completion_tokens":"0.000025","anthropic:cache_write_1h_tokens":"0.00001","anthropic:cache_write_5m_tokens":"0.00000625"},"pricing_version_id":"eebecb0c-b8ce-4c49-af97-fc1e13ce0ab5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-17T23:36:37.252Z","status":0}},{"slug":"allenai/olmo-3-32b-think","hf_slug":"allenai/Olmo-3-32B-Think","updated_at":"2026-01-08T19:23:52.555Z","created_at":"2025-11-21T20:51:16.304Z","hf_updated_at":null,"name":"AllenAI: Olmo 3 32B Think","short_name":"Olmo 3 32B Think","author":"allenai","author_display_name":"Ai2","author_icon_uri":null,"description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and highly nuanced conversational reasoning. Developed by Ai2 under the Apache 2.0 license, Olmo 3 32B Think embodies the Olmo initiative’s commitment to openness, offering full transparency across weights, code and training methodology.","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free Olmo 3.1 32B period has ended. To continue using this model, please migrate to the paid slug: allenai/olmo-3.1-32b-think","required_attestation_types":[],"is_private":false,"permaslug":"allenai/olmo-3-32b-think-20251121","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7282df05-53d5-4f61-9104-05a2ea109ffa","name":"Parasail | allenai/olmo-3-32b-think-20251121","context_length":65536,"model":{"slug":"allenai/olmo-3-32b-think","hf_slug":"allenai/Olmo-3-32B-Think","updated_at":"2026-01-08T19:23:52.555156+00:00","created_at":"2025-11-21T20:51:16.304522+00:00","hf_updated_at":null,"name":"AllenAI: Olmo 3 32B Think","short_name":"Olmo 3 32B Think","author":"allenai","author_display_name":"Ai2","author_icon_uri":null,"description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and highly nuanced conversational reasoning. Developed by Ai2 under the Apache 2.0 license, Olmo 3 32B Think embodies the Olmo initiative’s commitment to openness, offering full transparency across weights, code and training methodology.","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":"The free Olmo 3.1 32B period has ended. To continue using this model, please migrate to the paid slug: allenai/olmo-3.1-32b-think","required_attestation_types":[],"is_private":false,"permaslug":"allenai/olmo-3-32b-think-20251121","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"allenai/olmo-3-32b-think","model_variant_permaslug":"allenai/olmo-3-32b-think-20251121","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-olmo-3-32b-think","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format"],"excluded_parameters":["tool_choice","tools"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000015","completion":"0.0000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000015","openai:completion_tokens":"0.0000005"},"pricing_version_id":"3d1bbca2-dd00-435f-a2a7-cbd2963dd173","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":50,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"disable_free_endpoint_limits":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-12-02T17:42:16.234Z","status":0}},{"slug":"google/gemini-3-pro-image-preview","hf_slug":"","updated_at":"2026-01-08T19:23:52.555Z","created_at":"2025-11-20T15:49:57.064Z","hf_updated_at":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","short_name":"Nano Banana Pro (Gemini 3 Pro Image Preview)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.","model_version_group_id":null,"context_length":65536,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-pro-image-preview-20251120","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3-pro-image-preview-20251120/22a29428-074d-4a75-acaf-bc50051bcaa4/original-0.jpg","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3-pro-image-preview-20251120/22a29428-074d-4a75-acaf-bc50051bcaa4/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-3-pro-image-preview-20251120/22a29428-074d-4a75-acaf-bc50051bcaa4/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f5a725e2-8f66-4754-9232-7550685ab3d0","name":"Google AI Studio | google/gemini-3-pro-image-preview-20251120","context_length":65536,"model":{"slug":"google/gemini-3-pro-image-preview","hf_slug":"","updated_at":"2026-01-08T19:23:52.555156+00:00","created_at":"2025-11-20T15:49:57.064095+00:00","hf_updated_at":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","short_name":"Nano Banana Pro (Gemini 3 Pro Image Preview)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\n\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.","model_version_group_id":null,"context_length":65536,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-3-pro-image-preview-20251120","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":false,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":[],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-3-pro-image-preview","model_variant_permaslug":"google/gemini-3-pro-image-preview-20251120","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio/global","provider_model_id":"gemini-3-pro-image-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","image_output":"0.00012","audio":"0.000002","input_audio_cache":"0.0000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.014","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"gemini:prompt_tokens":0.000002,"gemini:reasoning_tokens":0.000012,"gemini:cache_read_tokens":2e-7,"gemini:completion_tokens":0.000012,"gemini:text_input_tokens":0.000002,"gemini:audio_input_tokens":0.000002,"gemini:image_input_tokens":0.000002,"gemini:video_input_tokens":0.000002,"gemini:image_output_tokens":0.00012,"gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":2e-7,"gemini:cache_read_audio_tokens":2e-7,"gemini:cache_read_image_tokens":2e-7,"gemini:cache_read_video_tokens":2e-7,"gemini:cache_write_storage_hours":0.0000045,"gemini:prompt_tokens_high_context":0.000004,"gemini:reasoning_tokens_high_context":0.000018,"gemini:cache_read_tokens_high_context":4e-7,"gemini:completion_tokens_high_context":0.000018,"gemini:cache_read_text_tokens_high_context":4e-7,"gemini:cache_read_audio_tokens_high_context":4e-7,"gemini:cache_read_image_tokens_high_context":4e-7,"gemini:cache_read_video_tokens_high_context":4e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"11ab01c0-c950-4fb8-81ab-5bd551685b4d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":250,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":{"resolutions":["1K","2K","4K"],"aspect_ratios":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"],"output_formats":null,"qualities":null,"backgrounds":null,"n":{"min":1,"max":1},"input_references":{"min":0,"max":14},"output_compression":null,"seed":null},"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":["cachedContent"],"capacity_tpm":null,"created_at":"2025-11-20T16:23:08.965Z","status":0}},{"slug":"openai/gpt-5.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-11-13T18:58:25.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.1 (batch)","short_name":"GPT-5.1 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6c6e6f9c-10ac-41ec-8ba9-6989c3ee9c90","name":"OpenAI | openai/gpt-5.1-20251113:batch","context_length":400000,"model":{"slug":"openai/gpt-5.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-11-13T18:58:25+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.1","short_name":"GPT-5.1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.1:batch","model_variant_permaslug":"openai/gpt-5.1-20251113:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5.1-2025-11-13","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000625","completion":"0.000005","input_cache_read":"0.0000000625","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"6.250000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"5.000000e-6","openai_responses:cached_prompt_tokens":"6.250000e-8","openai_responses:flex_tier_multiplier":"0.5","openai_responses:priority_tier_multiplier":"2"},"pricing_version_id":"89287c60-5ab3-4370-9142-b2d13b9c0b59","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:51.590Z","status":0}},{"slug":"openai/gpt-5.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-11-13T18:58:25.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.1","short_name":"GPT-5.1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"764eb97f-8bab-4326-b29b-7a8799b00a70","name":"OpenAI | openai/gpt-5.1-20251113","context_length":400000,"model":{"slug":"openai/gpt-5.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-11-13T18:58:25+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.1","short_name":"GPT-5.1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["none","low","medium","high"],"default_reasoning_effort":"none","default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.1","model_variant_permaslug":"openai/gpt-5.1-20251113","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai/default","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai/default","provider_model_id":"gpt-5.1-2025-11-13","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.00000125,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.00001,"openai_responses:cached_prompt_tokens":1.25e-7,"openai_responses:flex_tier_multiplier":"0.5","openai_responses:priority_tier_multiplier":"2"},"pricing_version_id":"219e08c0-a844-4ff6-95bf-6f9e8fecfa9b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-11-13T17:57:07.867Z","status":0}},{"slug":"openai/gpt-5.1-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-11-13T18:58:18.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5.1-Codex","short_name":"GPT-5.1-Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-codex-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6cbf24ac-808c-4cbf-9e6c-c971f69c4de6","name":"Azure | openai/gpt-5.1-codex-20251113","context_length":400000,"model":{"slug":"openai/gpt-5.1-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-11-13T18:58:18+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.1-Codex","short_name":"GPT-5.1-Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-codex-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.1-codex","model_variant_permaslug":"openai/gpt-5.1-codex-20251113","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.1-codex","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.00000013","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.00000125,"openai_responses:completion_tokens":0.00001,"openai_responses:cached_prompt_tokens":1.3e-7},"pricing_version_id":"7ae97ba8-cc15-4298-8b63-588145fca332","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":10000000,"created_at":"2026-01-06T00:46:01.181Z","status":0}},{"slug":"openai/gpt-5.1-codex-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-11-13T18:17:00.379Z","hf_updated_at":null,"name":"OpenAI: GPT-5.1-Codex-Mini","short_name":"GPT-5.1-Codex-Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-codex-mini-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"cdb3ebc6-45e5-40ec-b586-48336ea95841","name":"Azure | openai/gpt-5.1-codex-mini-20251113","context_length":400000,"model":{"slug":"openai/gpt-5.1-codex-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-11-13T18:17:00.379348+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5.1-Codex-Mini","short_name":"GPT-5.1-Codex-Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5.1-codex-mini-20251113","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5.1-codex-mini","model_variant_permaslug":"openai/gpt-5.1-codex-mini-20251113","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-foundry-east-resource.cognitiveservices.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5.1-codex-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","structured_outputs","response_format","seed","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000025","completion":"0.000002","input_cache_read":"0.00000003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":2.5e-7,"openai_responses:completion_tokens":0.000002,"openai_responses:cached_prompt_tokens":3e-8},"pricing_version_id":"19a4fa4c-5b48-4aaa-85cb-53f49eee289a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":10000000,"created_at":"2026-01-06T00:46:01.181Z","status":0}},{"slug":"moonshotai/kimi-k2-thinking","hf_slug":"moonshotai/Kimi-K2-Thinking","updated_at":"2026-07-08T17:53:01.236Z","created_at":"2025-11-06T14:50:22.752Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2 Thinking","short_name":"Kimi K2 Thinking","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\n\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2-thinking-20251106","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"a5cbd682-c60f-49d4-afda-520de76d9435","name":"Novita | moonshotai/kimi-k2-thinking-20251106","context_length":262144,"model":{"slug":"moonshotai/kimi-k2-thinking","hf_slug":"moonshotai/Kimi-K2-Thinking","updated_at":"2026-07-08T17:53:01.236048+00:00","created_at":"2025-11-06T14:50:22.752525+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2 Thinking","short_name":"Kimi K2 Thinking","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\n\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2-thinking-20251106","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2-thinking","model_variant_permaslug":"moonshotai/kimi-k2-thinking-20251106","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/bf16","provider_model_id":"moonshotai/kimi-k2-thinking","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100352,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000006","completion":"0.0000025","input_cache_read":"0.00000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000006","openai:completion_tokens":"0.0000025","openai:cached_prompt_tokens":"0.00000015"},"pricing_version_id":"7f1afff8-1cff-4cbf-a9d7-e566c6090dee","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-11-08T23:59:31.467Z","status":0}},{"slug":"amazon/nova-premier-v1","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-10-31T22:38:52.074Z","hf_updated_at":null,"name":"Amazon: Nova Premier 1.0","short_name":"Nova Premier 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-premier-v1","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6e4da481-6c8d-45d0-a3f5-11a9ba527485","name":"Amazon Bedrock | amazon/nova-premier-v1","context_length":1000000,"model":{"slug":"amazon/nova-premier-v1","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-10-31T22:38:52.074161+00:00","hf_updated_at":null,"name":"Amazon: Nova Premier 1.0","short_name":"Nova Premier 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-premier-v1","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"amazon/nova-premier-v1","model_variant_permaslug":"amazon/nova-premier-v1","adapter_name":"AmazonBedrockConverseAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"bedrock_converse"},"provider_display_name":"Amazon Bedrock","provider_slug":"amazon-bedrock","provider_model_id":"us.amazon.nova-premier-v1:0\t","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.000000625","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000625","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000625","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"bedrock_converse:prompt_tokens":"0.0000025","bedrock_converse:cache_read_tokens":"0.000000625","bedrock_converse:completion_tokens":"0.0000125"},"pricing_version_id":"4378842f-42d9-4f63-8fa0-b5300091c23a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-31T22:42:55.586Z","status":0}},{"slug":"perplexity/sonar-pro-search","hf_slug":"","updated_at":"2026-01-08T19:23:52.555Z","created_at":"2025-10-30T19:59:26.000Z","hf_updated_at":null,"name":"Perplexity: Sonar Pro Search","short_name":"Sonar Pro Search","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform.\n\nSonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-pro-search","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c78926bd-fa25-4883-8794-22de8c1ce79c","name":"Perplexity | perplexity/sonar-pro-search","context_length":200000,"model":{"slug":"perplexity/sonar-pro-search","hf_slug":"","updated_at":"2026-01-08T19:23:52.555156+00:00","created_at":"2025-10-30T19:59:26+00:00","hf_updated_at":null,"name":"Perplexity: Sonar Pro Search","short_name":"Sonar Pro Search","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform.\n\nSonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-pro-search","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"perplexity/sonar-pro-search","model_variant_permaslug":"perplexity/sonar-pro-search","adapter_name":"PerplexityAdapter","provider_name":"Perplexity","provider_info":{"name":"Perplexity","displayName":"Perplexity","slug":"perplexity","baseUrl":"https://api.perplexity.ai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"PerplexityAdapter","statusPageUrl":"https://status.perplexity.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Perplexity.svg"},"sendClientIp":false,"pricingStrategy":"perplexity"},"provider_display_name":"Perplexity","provider_slug":"perplexity","provider_model_id":"sonar-pro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":8000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options","structured_outputs"],"excluded_parameters":["tool_choice","tools"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy"},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.018","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.018","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.018","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"perplexity:prompt_tokens":0.000003,"perplexity:web_search_calls":0.018,"perplexity:completion_tokens":0.000015},"pricing_version_id":"18bd4da3-4dfe-4f77-8c36-2ef552929c01","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-17T22:25:19.588Z","status":0}},{"slug":"mistralai/voxtral-small-24b-2507","hf_slug":"mistralai/Voxtral-Small-24B-2507","updated_at":"2026-05-14T22:39:38.404Z","created_at":"2025-10-30T14:39:04.000Z","hf_updated_at":null,"name":"Mistral: Voxtral Small 24B 2507","short_name":"Voxtral Small 24B 2507","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio is priced at $100 per million seconds.","model_version_group_id":null,"context_length":32000,"input_modalities":["text","audio","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/voxtral-small-24b-2507","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.2,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"814f9be0-e226-4b8c-bb5d-bf684359da13","name":"Mistral | mistralai/voxtral-small-24b-2507","context_length":32000,"model":{"slug":"mistralai/voxtral-small-24b-2507","hf_slug":"mistralai/Voxtral-Small-24B-2507","updated_at":"2026-05-14T22:39:38.404496+00:00","created_at":"2025-10-30T14:39:04+00:00","hf_updated_at":null,"name":"Mistral: Voxtral Small 24B 2507","short_name":"Voxtral Small 24B 2507","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio is priced at $100 per million seconds.","model_version_group_id":null,"context_length":32000,"input_modalities":["text","audio","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/voxtral-small-24b-2507","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.2,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/voxtral-small-24b-2507","model_variant_permaslug":"mistralai/voxtral-small-24b-2507","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"voxtral-small-2507","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000003","audio":"0.0001","input_cache_read":"0.00000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Input Audio","price":"0.0001","displayMultiplier":60,"unitLabel":"/minute"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Input Audio","price":"0.0001","displayMultiplier":60,"unitLabel":"/minute"}],"pricing_json":{"mistral:prompt_tokens":"1e-7","mistral:completion_tokens":3e-7,"mistral:audio_input_tokens":0.0001,"mistral:cached_prompt_tokens":"1e-8"},"pricing_version_id":"ef078d00-4ffb-467b-96b3-4d5fd2282265","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-13T19:55:03.393Z","status":0}},{"slug":"openai/gpt-oss-safeguard-20b","hf_slug":"openai/gpt-oss-safeguard-20b","updated_at":"2026-07-29T12:43:32.396Z","created_at":"2025-10-29T15:47:16.557Z","hf_updated_at":null,"name":"OpenAI: gpt-oss-safeguard-20b","short_name":"gpt-oss-safeguard-20b","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.\n\nLearn more about this model in OpenAI's gpt-oss-safeguard [user guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-oss-safeguard-20b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"none"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"none"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"d83e34dd-4624-428d-8c3e-524be778e27f","name":"Groq | openai/gpt-oss-safeguard-20b","context_length":131072,"model":{"slug":"openai/gpt-oss-safeguard-20b","hf_slug":"openai/gpt-oss-safeguard-20b","updated_at":"2026-07-29T12:43:32.396096+00:00","created_at":"2025-10-29T15:47:16.557286+00:00","hf_updated_at":null,"name":"OpenAI: gpt-oss-safeguard-20b","short_name":"gpt-oss-safeguard-20b","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.\n\nLearn more about this model in OpenAI's gpt-oss-safeguard [user guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).","model_version_group_id":null,"context_length":0,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-oss-safeguard-20b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"none"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"reasoning_return_mechanism":"none"},"chat_template_config":{}},"default_parameters":{},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-oss-safeguard-20b","model_variant_permaslug":"openai/gpt-oss-safeguard-20b","adapter_name":"GroqAdapter","provider_name":"Groq","provider_info":{"name":"Groq","displayName":"Groq","slug":"groq","baseUrl":"https://api.groq.com/openai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://groq.com/terms-of-use/","privacyPolicyURL":"https://groq.com/privacy-policy/","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GroqAdapter","statusPageUrl":"https://status.groq.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://groq.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Groq","provider_slug":"groq","provider_model_id":"openai/gpt-oss-safeguard-20b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://groq.com/terms-of-use/","privacyPolicyURL":"https://groq.com/privacy-policy/"},"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000375","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000075","openai:completion_tokens":"0.0000003","openai:cached_prompt_tokens":"0.0000000375"},"pricing_version_id":"a4c1a53a-f565-4115-b651-37bb924ae758","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-29T16:33:42.666Z","status":0}},{"slug":"minimax/minimax-m2","hf_slug":"MiniMaxAI/MiniMax-M2","updated_at":"2026-01-08T19:23:52.555Z","created_at":"2025-10-23T20:41:33.120Z","hf_updated_at":null,"name":"MiniMax: MiniMax M2","short_name":"MiniMax M2","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.\n\nThe model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.\n\nBenchmarked by [Artificial Analysis](https://artificialanalysis.ai/models/minimax-m2), MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"46585386-044e-4e91-852c-f56bf056e1af","name":"Minimax | minimax/minimax-m2","context_length":204800,"model":{"slug":"minimax/minimax-m2","hf_slug":"MiniMaxAI/MiniMax-M2","updated_at":"2026-01-08T19:23:52.555156+00:00","created_at":"2025-10-23T20:41:33.120854+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M2","short_name":"MiniMax M2","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.\n\nThe model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.\n\nBenchmarked by [Artificial Analysis](https://artificialanalysis.ai/models/minimax-m2), MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m2","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m2","model_variant_permaslug":"minimax/minimax-m2","adapter_name":"MinimaxAdapter","provider_name":"Minimax","provider_info":{"name":"Minimax","displayName":"MiniMax","slug":"minimax","baseUrl":"https://api.minimaxi.chat/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MinimaxAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://minimaxi.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"MiniMax","provider_slug":"minimax/fp8","provider_model_id":"MiniMax-M2-Stable","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tool_choice","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy"},"pricing":{"prompt":"0.000000255","completion":"0.00000102","discount":0.15,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000255","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000102","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000255","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000102","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000012"},"pricing_version_id":"a7386e0d-7146-410d-871e-5373c505d14f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":500,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"reasoning_return_mechanism":"content-string","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"should_send_reasoning_text_in_text_content":false,"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":50000000,"created_at":"2025-11-04T16:15:56.680Z","status":0}},{"slug":"qwen/qwen3-vl-32b-instruct","hf_slug":"Qwen/Qwen3-VL-32B-Instruct","updated_at":"2026-03-20T20:31:25.739Z","created_at":"2025-10-23T14:55:32.539Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 32B Instruct","short_name":"Qwen3 VL 32B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text comprehension, enabling fine-grained spatial reasoning, document and scene analysis, and long-horizon video understanding.Robust OCR in 32 languages, and enhanced multimodal fusion through Interleaved-MRoPE and DeepStack architectures. Optimized for agentic interaction and visual tool use, Qwen3-VL-32B delivers state-of-the-art performance for complex real-world multimodal tasks.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-32b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5e9377cb-bd6f-4940-8a25-c787a4ccec95","name":"Alibaba | qwen/qwen3-vl-32b-instruct","context_length":131072,"model":{"slug":"qwen/qwen3-vl-32b-instruct","hf_slug":"Qwen/Qwen3-VL-32B-Instruct","updated_at":"2026-03-20T20:31:25.739939+00:00","created_at":"2025-10-23T14:55:32.53917+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 32B Instruct","short_name":"Qwen3 VL 32B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text comprehension, enabling fine-grained spatial reasoning, document and scene analysis, and long-horizon video understanding.Robust OCR in 32 languages, and enhanced multimodal fusion through Interleaved-MRoPE and DeepStack architectures. Optimized for agentic interaction and visual tool use, Qwen3-VL-32B delivers state-of-the-art performance for complex real-world multimodal tasks.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-32b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-32b-instruct","model_variant_permaslug":"qwen/qwen3-vl-32b-instruct","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-vl-32b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":129024,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000104","completion":"0.000000416","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000104","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000416","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000104","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000416","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000000104","alibaba:completion_tokens":"0.000000416"},"pricing_version_id":"7cab83f1-4426-43b1-8090-1326ac21f3f9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:22:22.334Z","status":0}},{"slug":"ibm-granite/granite-4.0-h-micro","hf_slug":"ibm-granite/granite-4.0-h-micro","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-10-20T02:34:55.126Z","hf_updated_at":null,"name":"IBM: Granite 4.0 Micro","short_name":"Granite 4.0 Micro","author":"ibm-granite","author_display_name":"ibm-granite","author_icon_uri":null,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling. ","model_version_group_id":null,"context_length":131000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"ibm-granite/granite-4.0-h-micro","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"99acb983-d859-4f77-bb89-5d9f05985bbe","name":"Cloudflare | ibm-granite/granite-4.0-h-micro","context_length":131000,"model":{"slug":"ibm-granite/granite-4.0-h-micro","hf_slug":"ibm-granite/granite-4.0-h-micro","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-10-20T02:34:55.126105+00:00","hf_updated_at":null,"name":"IBM: Granite 4.0 Micro","short_name":"Granite 4.0 Micro","author":"ibm-granite","author_display_name":"ibm-granite","author_icon_uri":null,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling. ","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"ibm-granite/granite-4.0-h-micro","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"ibm-granite/granite-4.0-h-micro","model_variant_permaslug":"ibm-granite/granite-4.0-h-micro","adapter_name":"CloudflareAdapter","provider_name":"Cloudflare","provider_info":{"name":"Cloudflare","displayName":"Cloudflare","slug":"cloudflare","baseUrl":"https://api.cloudflare.com/client/v4/accounts/{accountId}/ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"CloudflareAdapter","statusPageUrl":"https://www.cloudflarestatus.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.cloudflare.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Cloudflare","provider_slug":"cloudflare","provider_model_id":"@cf/ibm-granite/granite-4.0-h-micro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy"},"pricing":{"prompt":"0.000000017","completion":"0.000000112","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000017","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000112","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000017","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000112","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000017","openai:completion_tokens":"0.000000112"},"pricing_version_id":"87b6f77a-950c-41f7-be88-da9116f3da43","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":false,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-20T02:34:55.378Z","status":0}},{"slug":"openai/gpt-5-image-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-10-16T14:23:03.143Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Image Mini","short_name":"GPT-5 Image Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-image-mini","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5-image-mini/27cfc306-9f9c-4368-9ff7-cd2e4291a9c7/original-0.png","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5-image-mini/27cfc306-9f9c-4368-9ff7-cd2e4291a9c7/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5-image-mini/27cfc306-9f9c-4368-9ff7-cd2e4291a9c7/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7c09094a-64ec-4d53-bd69-c165ac31c465","name":"OpenAI | openai/gpt-5-image-mini","context_length":400000,"model":{"slug":"openai/gpt-5-image-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-10-16T14:23:03.143259+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Image Mini","short_name":"GPT-5 Image Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.","model_version_group_id":null,"context_length":400000,"input_modalities":["file","image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-image-mini","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-image-mini","model_variant_permaslug":"openai/gpt-5-image-mini","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-mini-2025-08-07","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.000002","image_output":"0.000008","input_cache_read":"0.00000025","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.0000025,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.000002,"openai_responses:image_output_tokens":0.000008,"openai_responses:cached_prompt_tokens":2.5e-7},"pricing_version_id":"f2440c26-2f98-41c2-8d81-fcbca956e29a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":{"resolutions":null,"aspect_ratios":["1:1","3:2","2:3","auto"],"output_formats":null,"qualities":["auto","low","medium","high"],"backgrounds":["auto","transparent","opaque"],"n":{"min":1,"max":10},"input_references":{"min":0,"max":16},"output_compression":{"min":0,"max":100},"seed":null},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["moderation"],"capacity_tpm":null,"created_at":"2025-10-16T19:07:50.459Z","status":0}},{"slug":"anthropic/claude-haiku-4.5","hf_slug":"","updated_at":"2026-05-12T01:54:22.936Z","created_at":"2025-10-15T17:00:38.000Z","hf_updated_at":null,"name":"Anthropic: Claude Haiku 4.5 (batch)","short_name":"Claude Haiku 4.5 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","model_version_group_id":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-haiku-20251001","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/global","google-vertex","anthropic","google-vertex/europe","amazon-bedrock"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"5f81131e-c48b-4650-ad7b-de5c514c942f","name":"Anthropic | anthropic/claude-4.5-haiku-20251001:batch","context_length":200000,"model":{"slug":"anthropic/claude-haiku-4.5","hf_slug":"","updated_at":"2026-05-12T01:54:22.936623+00:00","created_at":"2025-10-15T17:00:38+00:00","hf_updated_at":null,"name":"Anthropic: Claude Haiku 4.5","short_name":"Claude Haiku 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","model_version_group_id":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-haiku-20251001","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/global","google-vertex","anthropic","google-vertex/europe","amazon-bedrock"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-haiku-4.5:batch","model_variant_permaslug":"anthropic/claude-4.5-haiku-20251001:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-haiku-4-5-20251001","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000005","completion":"0.0000025","input_cache_read":"0.00000005","input_cache_write":"0.000000625","input_cache_write_1h":"0.000001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000625","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000000625","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000005","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"0.00000005","anthropic:completion_tokens":"0.0000025","anthropic:cache_write_1h_tokens":"0.000001","anthropic:cache_write_5m_tokens":"0.000000625"},"pricing_version_id":"81b015d1-34d5-43ef-ba72-66c69844c2e5","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":125,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-14T02:38:50.828Z","status":0}},{"slug":"anthropic/claude-haiku-4.5","hf_slug":"","updated_at":"2026-05-12T01:54:22.936Z","created_at":"2025-10-15T17:00:38.000Z","hf_updated_at":null,"name":"Anthropic: Claude Haiku 4.5","short_name":"Claude Haiku 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","model_version_group_id":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-haiku-20251001","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/global","google-vertex","anthropic","google-vertex/europe","amazon-bedrock"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"41d2915a-92e6-4993-b537-210b4e10cba8","name":"Anthropic | anthropic/claude-4.5-haiku-20251001","context_length":200000,"model":{"slug":"anthropic/claude-haiku-4.5","hf_slug":"","updated_at":"2026-05-12T01:54:22.936623+00:00","created_at":"2025-10-15T17:00:38+00:00","hf_updated_at":null,"name":"Anthropic: Claude Haiku 4.5","short_name":"Claude Haiku 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","model_version_group_id":"2f438a66-518a-455c-8c1e-7c1c71dbe8ec","context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-haiku-20251001","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock/global","google-vertex","anthropic","google-vertex/europe","amazon-bedrock"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-haiku-4.5","model_variant_permaslug":"anthropic/claude-4.5-haiku-20251001","adapter_name":"AnthropicMessageAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicMessageAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-haiku-4-5-20251001","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":0.000001,"anthropic:web_search_calls":0.01,"anthropic:cache_read_tokens":1e-7,"anthropic:completion_tokens":0.000005,"anthropic:cache_write_1h_tokens":0.000002,"anthropic:cache_write_5m_tokens":0.00000125},"pricing_version_id":"37ac63dd-eb6a-47b4-96ea-c8ed46256597","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":125,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-14T19:38:10.102Z","status":0}},{"slug":"qwen/qwen3-vl-8b-thinking","hf_slug":"Qwen/Qwen3-VL-8B-Thinking","updated_at":"2026-01-08T19:23:52.555Z","created_at":"2025-10-14T17:42:26.552Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 8B Thinking","short_name":"Qwen3 VL 8B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and long-context processing (native 256K, expandable to 1M tokens) for tasks such as scientific visual analysis, causal inference, and mathematical reasoning over image or video inputs.\n\nCompared to the Instruct edition, the Thinking version introduces deeper visual-language fusion and deliberate reasoning pathways that improve performance on long-chain logic tasks, STEM problem-solving, and multi-step video understanding. It achieves stronger temporal grounding via Interleaved-MRoPE and timestamp-aware embeddings, while maintaining robust OCR, multilingual comprehension, and text generation on par with large text-only LLMs.","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-8b-thinking","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6cb46014-347b-4d67-aefa-7b83e065b8c3","name":"Alibaba | qwen/qwen3-vl-8b-thinking","context_length":131072,"model":{"slug":"qwen/qwen3-vl-8b-thinking","hf_slug":"Qwen/Qwen3-VL-8B-Thinking","updated_at":"2026-01-08T19:23:52.555156+00:00","created_at":"2025-10-14T17:42:26.552544+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 8B Thinking","short_name":"Qwen3 VL 8B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and long-context processing (native 256K, expandable to 1M tokens) for tasks such as scientific visual analysis, causal inference, and mathematical reasoning over image or video inputs.\n\nCompared to the Instruct edition, the Thinking version introduces deeper visual-language fusion and deliberate reasoning pathways that improve performance on long-chain logic tasks, STEM problem-solving, and multi-step video understanding. It achieves stronger temporal grounding via Interleaved-MRoPE and timestamp-aware embeddings, while maintaining robust OCR, multilingual comprehension, and text generation on par with large text-only LLMs.","model_version_group_id":null,"context_length":256000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-8b-thinking","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{"temperature":1,"top_p":0.95},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-8b-thinking","model_variant_permaslug":"qwen/qwen3-vl-8b-thinking","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-vl-8b-thinking","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":126976,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000018","completion":"0.0000021","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.8e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000021","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.8e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000021","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":1.8e-7,"alibaba:completion_tokens":0.0000021},"pricing_version_id":"9dc4d7fc-22d5-4569-944c-c19d407c6272","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-14T17:43:16.203Z","status":0}},{"slug":"qwen/qwen3-vl-8b-instruct","hf_slug":"Qwen/Qwen3-VL-8B-Instruct","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-10-14T17:35:08.402Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 8B Instruct","short_name":"Qwen3 VL 8B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization.\n\nThe model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.","model_version_group_id":null,"context_length":262144,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-8b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0122dcb7-c876-4445-8a8e-610a7b44d12b","name":"Alibaba | qwen/qwen3-vl-8b-instruct","context_length":131072,"model":{"slug":"qwen/qwen3-vl-8b-instruct","hf_slug":"Qwen/Qwen3-VL-8B-Instruct","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-10-14T17:35:08.402158+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 8B Instruct","short_name":"Qwen3 VL 8B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization.\n\nThe model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.","model_version_group_id":null,"context_length":256000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-8b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-8b-instruct","model_variant_permaslug":"qwen/qwen3-vl-8b-instruct","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-vl-8b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":129024,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000117","completion":"0.000000455","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000117","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000455","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000117","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000455","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000000117","alibaba:completion_tokens":"0.000000455"},"pricing_version_id":"93c1b06d-b3b7-4a9b-9fbd-632f9cebcd99","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-14T17:38:20.084Z","status":0}},{"slug":"openai/gpt-5-image","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-10-14T13:19:46.029Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Image","short_name":"GPT-5 Image","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["image","text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-image","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"image_generation","previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5-image/e1e250ca-4a7d-4928-ae8e-1920360ec354/original-0.png","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5-image/e1e250ca-4a7d-4928-ae8e-1920360ec354/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/openai/gpt-5-image/e1e250ca-4a7d-4928-ae8e-1920360ec354/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"be0ed145-8bfc-4aec-a62d-685ed334fe17","name":"OpenAI | openai/gpt-5-image","context_length":400000,"model":{"slug":"openai/gpt-5-image","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-10-14T13:19:46.029021+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Image","short_name":"GPT-5 Image","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["image","text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-image","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"image_generation","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-image","model_variant_permaslug":"openai/gpt-5-image","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-2025-08-07","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00001","image_output":"0.00004","input_cache_read":"0.00000125","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.00001,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.00001,"openai_responses:image_output_tokens":0.00004,"openai_responses:cached_prompt_tokens":0.00000125},"pricing_version_id":"b9d2cf4c-5f0e-41c0-b7ba-082300d4a127","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":{"resolutions":null,"aspect_ratios":["1:1","3:2","2:3","auto"],"output_formats":null,"qualities":["auto","low","medium","high"],"backgrounds":["auto","transparent","opaque"],"n":{"min":1,"max":10},"input_references":{"min":0,"max":16},"output_compression":{"min":0,"max":100},"seed":null},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["moderation"],"capacity_tpm":null,"created_at":"2025-10-14T13:24:23.713Z","status":0}},{"slug":"google/gemini-2.5-flash-image","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-10-07T20:53:51.000Z","hf_updated_at":null,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","short_name":"Nano Banana (Gemini 2.5 Flash Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)","model_version_group_id":null,"context_length":32768,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash-image","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["google-vertex"],"quick_start_example_type":null,"previews_by_modality":{"image":{"url":"https://model-assets.openrouter.ai/model-examples/google/gemini-2.5-flash-image/90e14706-8f92-496b-a6e6-bd81e95001f5/original-0.png","thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-2.5-flash-image/90e14706-8f92-496b-a6e6-bd81e95001f5/thumb-0.webp"}},"preview_thumbnail_url":"https://model-assets.openrouter.ai/model-examples/google/gemini-2.5-flash-image/90e14706-8f92-496b-a6e6-bd81e95001f5/thumb-0.webp","preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2341e1bc-99ea-46ab-ae2d-9a83846afb43","name":"Google AI Studio | google/gemini-2.5-flash-image","context_length":32768,"model":{"slug":"google/gemini-2.5-flash-image","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-10-07T20:53:51+00:00","hf_updated_at":null,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","short_name":"Nano Banana (Gemini 2.5 Flash Image)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the [image_config API Parameter](https://openrouter.ai/docs/features/multimodal/image-generation#image-aspect-ratio-configuration)","model_version_group_id":null,"context_length":32768,"input_modalities":["image","text"],"output_modalities":["image","text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash-image","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["google-vertex"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-flash-image","model_variant_permaslug":"google/gemini-2.5-flash-image","adapter_name":"GoogleAIStudioGeminiAdapter","provider_name":"Google AI Studio","provider_info":{"name":"Google AI Studio","displayName":"Google AI Studio","slug":"google-ai-studio","baseUrl":"https://generativelanguage.googleapis.com/v1beta","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleAIStudioGeminiAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/GoogleAIStudio.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google AI Studio","provider_slug":"google-ai-studio","provider_model_id":"gemini-2.5-flash-image","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":55,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","image_output":"0.00003","audio":"0.000001","input_audio_cache":"0.0000001","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Output","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":3e-7,"gemini:reasoning_tokens":0.0000025,"gemini:cache_read_tokens":3e-8,"gemini:completion_tokens":0.0000025,"gemini:text_input_tokens":3e-7,"gemini:audio_input_tokens":0.000001,"gemini:image_input_tokens":3e-7,"gemini:video_input_tokens":3e-7,"gemini:image_output_tokens":0.00003,"gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":3e-8,"gemini:cache_read_audio_tokens":1e-7,"gemini:cache_read_image_tokens":3e-8,"gemini:cache_read_video_tokens":3e-8,"gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":0.000001,"gemini:cache_read_tokens_high_context":1e-7,"gemini:cache_read_text_tokens_high_context":1e-7,"gemini:cache_read_audio_tokens_high_context":2e-7,"gemini:cache_read_image_tokens_high_context":1e-7,"gemini:cache_read_video_tokens_high_context":1e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"907e666b-a0fb-4426-a3a7-01f4f7d4de85","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":1000,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":{"resolutions":null,"aspect_ratios":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"],"output_formats":null,"qualities":null,"backgrounds":null,"n":{"min":1,"max":1},"input_references":{"min":0,"max":3},"output_compression":null,"seed":null},"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":["cachedContent"],"capacity_tpm":null,"created_at":"2025-10-02T22:43:20.484Z","status":0}},{"slug":"qwen/qwen3-vl-30b-a3b-thinking","hf_slug":"Qwen/Qwen3-VL-30B-A3B-Thinking","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-10-06T23:47:59.575Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 30B A3B Thinking","short_name":"Qwen3 VL 30B A3B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-30b-a3b-thinking","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":0.8,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"bad35a82-60b3-4cbb-ad64-fb0fa0e25318","name":"Alibaba | qwen/qwen3-vl-30b-a3b-thinking","context_length":131072,"model":{"slug":"qwen/qwen3-vl-30b-a3b-thinking","hf_slug":"Qwen/Qwen3-VL-30B-A3B-Thinking","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-10-06T23:47:59.575824+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 30B A3B Thinking","short_name":"Qwen3 VL 30B A3B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.","model_version_group_id":null,"context_length":0,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-30b-a3b-thinking","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":0.8,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-30b-a3b-thinking","model_variant_permaslug":"qwen/qwen3-vl-30b-a3b-thinking","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-vl-30b-a3b-thinking","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":126976,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.0000024","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.0000002","alibaba:completion_tokens":"0.0000024"},"pricing_version_id":"1248aaa1-3196-4c10-a378-0bae3196f6c2","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:22:23.429Z","status":0}},{"slug":"qwen/qwen3-vl-30b-a3b-instruct","hf_slug":"Qwen/Qwen3-VL-30B-A3B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-10-06T23:47:56.430Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 30B A3B Instruct","short_name":"Qwen3 VL 30B A3B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-30b-a3b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"27e433ca-988e-4aaa-902a-37bc06c59e3b","name":"Alibaba | qwen/qwen3-vl-30b-a3b-instruct","context_length":131072,"model":{"slug":"qwen/qwen3-vl-30b-a3b-instruct","hf_slug":"Qwen/Qwen3-VL-30B-A3B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-10-06T23:47:56.430294+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 30B A3B Instruct","short_name":"Qwen3 VL 30B A3B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-30b-a3b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-30b-a3b-instruct","model_variant_permaslug":"qwen/qwen3-vl-30b-a3b-instruct","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-vl-30b-a3b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":129024,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000013","completion":"0.00000052","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000052","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000052","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.00000013","alibaba:completion_tokens":"0.00000052"},"pricing_version_id":"f13a3d6c-9c36-489c-96f1-671f379923f6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:22:22.902Z","status":0}},{"slug":"openai/gpt-5-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-10-06T18:51:03.215Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Pro (batch)","short_name":"GPT-5 Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-pro-2025-10-06","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a76d0730-f1fa-4377-9503-6dc8f0157a25","name":"OpenAI | openai/gpt-5-pro-2025-10-06:batch","context_length":400000,"model":{"slug":"openai/gpt-5-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-10-06T18:51:03.215373+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Pro","short_name":"GPT-5 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-pro-2025-10-06","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-pro:batch","model_variant_permaslug":"openai/gpt-5-pro-2025-10-06:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-pro-2025-10-06","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000075","completion":"0.00006","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"7.500000e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"6.000000e-5"},"pricing_version_id":"64006a0f-adfb-48cf-a3aa-bd218e2c8e94","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:22.951Z","status":0}},{"slug":"openai/gpt-5-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-10-06T18:51:03.215Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Pro","short_name":"GPT-5 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-pro-2025-10-06","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"86e3e664-d291-415d-a769-8e08b96a79e9","name":"OpenAI | openai/gpt-5-pro-2025-10-06","context_length":400000,"model":{"slug":"openai/gpt-5-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-10-06T18:51:03.215373+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Pro","short_name":"GPT-5 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-pro-2025-10-06","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-pro","model_variant_permaslug":"openai/gpt-5-pro-2025-10-06","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-pro-2025-10-06","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000015","completion":"0.00012","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.000015,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.00012},"pricing_version_id":"f10148f9-4c52-440d-8ba0-7b474ed90068","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-06T18:53:57.070Z","status":0}},{"slug":"z-ai/glm-4.6","hf_slug":"zai-org/GLM-4.6","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-30T12:32:56.306Z","hf_updated_at":null,"name":"Z.ai: GLM 4.6","short_name":"GLM 4.6","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"Compared with GLM-4.5, this generation brings several key improvements:\n\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","model_version_group_id":null,"context_length":204800,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.6","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"76fb879b-32f4-4ac0-8020-d29c0f9c60fa","name":"Venice | z-ai/glm-4.6","context_length":198000,"model":{"slug":"z-ai/glm-4.6","hf_slug":"zai-org/GLM-4.6","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-30T12:32:56.306946+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.6","short_name":"GLM 4.6","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"Compared with GLM-4.5, this generation brings several key improvements:\n\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","model_version_group_id":null,"context_length":200000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.6","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.6","model_variant_permaslug":"z-ai/glm-4.6","adapter_name":"VeniceAdapter","provider_name":"Venice","provider_info":{"name":"Venice","displayName":"Venice","slug":"venice","baseUrl":"https://api.venice.ai/api/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://venice.ai/legal/tos","privacyPolicyURL":"https://venice.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"VeniceAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://venice.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Venice","provider_slug":"venice/fp4","provider_model_id":"zai-org-glm-4.6","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://venice.ai/legal/tos","privacyPolicyURL":"https://venice.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000043","completion":"0.00000175","input_cache_read":"0.00000008","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000043","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000043","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000175","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000043","openai:completion_tokens":"0.00000175","openai:cached_prompt_tokens":"0.00000008"},"pricing_version_id":"3bfb2dff-7b6f-494a-bc10-c549859e1d28","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":{"supported_resolutions":null,"supported_aspect_ratios":null,"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-20T16:46:18.048Z","status":0}},{"slug":"anthropic/claude-sonnet-4.5","hf_slug":"","updated_at":"2026-04-03T22:04:08.646Z","created_at":"2025-09-29T16:01:16.552Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.5 (batch)","short_name":"Claude Sonnet 4.5 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-sonnet-20250929","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex/global","anthropic-2","anthropic","google-vertex"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f221ae41-0f60-429b-9e24-75e9ac650bdf","name":"Anthropic | anthropic/claude-4.5-sonnet-20250929:batch","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-4.5","hf_slug":"","updated_at":"2026-04-03T22:04:08.646529+00:00","created_at":"2025-09-29T16:01:16.552976+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.5","short_name":"Claude Sonnet 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-sonnet-20250929","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex/global","anthropic-2","anthropic","google-vertex"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-4.5:batch","model_variant_permaslug":"anthropic/claude-4.5-sonnet-20250929:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-sonnet-4-5-20250929","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000015","completion":"0.0000075","input_cache_read":"0.00000015","input_cache_write":"0.000001875","input_cache_write_1h":"0.000003","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000003","completion":"0.00001125","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000015"},{"sku_label":">200K","price":"0.000003"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000075"},{"sku_label":">200K","price":"0.00001125"}]},{"kind":"token","sku_label":"Cache Read","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.5e-7"},{"sku_label":">200K","price":"3e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001875"},{"sku_label":">200K","price":"0.00000375"}]},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000003"},{"sku_label":">200K","price":"0.000006"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000015"},{"sku_label":">200K","price":"0.000003"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.0000075"},{"sku_label":">200K","price":"0.00001125"}]},{"kind":"token","sku_label":"Cache Read","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.5e-7"},{"sku_label":">200K","price":"3e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"0.000001875","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000001875"},{"sku_label":">200K","price":"0.00000375"}]},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000003"},{"sku_label":">200K","price":"0.000006"}]},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000015","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"1.5e-7","anthropic:completion_tokens":"0.0000075","anthropic:cache_write_1h_tokens":"0.000003","anthropic:cache_write_5m_tokens":"0.000001875","anthropic:long_context_threshold":"200000","anthropic:prompt_tokens_long_context":"0.000003","anthropic:cache_read_tokens_long_context":"3e-7","anthropic:completion_tokens_long_context":"0.00001125","anthropic:cache_write_1h_tokens_long_context":"0.000006","anthropic:cache_write_5m_tokens_long_context":"0.00000375"},"pricing_version_id":"65d59ab1-2a5a-4853-ae1b-b5da01fa0c2c","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:10:13.452Z","status":0}},{"slug":"anthropic/claude-sonnet-4.5","hf_slug":"","updated_at":"2026-04-03T22:04:08.646Z","created_at":"2025-09-29T16:01:16.552Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.5","short_name":"Claude Sonnet 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-sonnet-20250929","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex/global","anthropic-2","anthropic","google-vertex"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3a2c65ff-b039-4459-804a-9aafcb4d693c","name":"Google | anthropic/claude-4.5-sonnet-20250929","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-4.5","hf_slug":"","updated_at":"2026-04-03T22:04:08.646529+00:00","created_at":"2025-09-29T16:01:16.552976+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4.5","short_name":"Claude Sonnet 4.5","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.5-sonnet-20250929","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex/global","anthropic-2","anthropic","google-vertex"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-4.5","model_variant_permaslug":"anthropic/claude-4.5-sonnet-20250929","adapter_name":"InternalStreamGoogleVertexAnthropicAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (Global)","slug":"google-vertex/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Google Vertex (Global)","provider_slug":"google-vertex/global","provider_model_id":"claude-sonnet-4-5@20250929","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice","top_k"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000003"},{"sku_label":">200K","price":"0.000006"}]},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000015"},{"sku_label":">200K","price":"0.0000225"}]},{"kind":"token","sku_label":"Cache Read","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"3e-7"},{"sku_label":">200K","price":"6e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000375"},{"sku_label":">200K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000003"},{"sku_label":">200K","price":"0.000006"}]},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000015"},{"sku_label":">200K","price":"0.0000225"}]},{"kind":"token","sku_label":"Cache Read","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"3e-7"},{"sku_label":">200K","price":"6e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000375"},{"sku_label":">200K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]}],"pricing_json":{"anthropic:prompt_tokens":0.000003,"anthropic:web_search_calls":0.01,"anthropic:cache_read_tokens":3e-7,"anthropic:completion_tokens":0.000015,"anthropic:cache_write_1h_tokens":0.000006,"anthropic:cache_write_5m_tokens":0.00000375,"anthropic:long_context_threshold":200000,"anthropic:prompt_tokens_long_context":0.000006,"anthropic:cache_read_tokens_long_context":6e-7,"anthropic:completion_tokens_long_context":0.0000225,"anthropic:cache_write_1h_tokens_long_context":0.000012,"anthropic:cache_write_5m_tokens_long_context":0.0000075},"pricing_version_id":"c8022271-87de-4516-a5b5-641e812f6442","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":1000,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-29T16:08:22.821Z","status":0}},{"slug":"deepseek/deepseek-v3.2-exp","hf_slug":"deepseek-ai/DeepSeek-V3.2-Exp","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-29T12:54:41.802Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.2 Exp","short_name":"DeepSeek V3.2 Exp","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model was trained under conditions aligned with V3.1-Terminus to enable direct comparison. Benchmarking shows performance roughly on par with V3.1 across reasoning, coding, and agentic tool-use tasks, with minor tradeoffs and gains depending on the domain. This release focuses on validating architectural optimizations for extended context lengths rather than advancing raw task accuracy, making it primarily a research-oriented model for exploring efficient transformer designs.","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-v3.1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v3.2-exp","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-07-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1b484aef-be8f-4016-8762-2e3caabbab9f","name":"Novita | deepseek/deepseek-v3.2-exp","context_length":163840,"model":{"slug":"deepseek/deepseek-v3.2-exp","hf_slug":"deepseek-ai/DeepSeek-V3.2-Exp","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-29T12:54:41.802445+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.2 Exp","short_name":"DeepSeek V3.2 Exp","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model was trained under conditions aligned with V3.1-Terminus to enable direct comparison. Benchmarking shows performance roughly on par with V3.1 across reasoning, coding, and agentic tool-use tasks, with minor tradeoffs and gains depending on the domain. This release focuses on validating architectural optimizations for extended context lengths rather than advancing raw task accuracy, making it primarily a research-oriented model for exploring efficient transformer designs.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-v3.1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v3.2-exp","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-07-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v3.2-exp","model_variant_permaslug":"deepseek/deepseek-v3.2-exp","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"deepseek/deepseek-v3.2-exp","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000027","completion":"0.00000041","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000041","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000041","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000027","openai:completion_tokens":"0.00000041"},"pricing_version_id":"cdfa878f-173e-4013-82da-570a2185871f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-29T14:39:59.148Z","status":0}},{"slug":"thedrummer/cydonia-24b-v4.1","hf_slug":"thedrummer/cydonia-24b-v4.1","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-27T00:11:18.116Z","hf_updated_at":null,"name":"TheDrummer: Cydonia 24B V4.1","short_name":"Cydonia 24B V4.1","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/cydonia-24b-v4.1","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4d46db86-63fe-47eb-85f1-6a7567af190c","name":"Parasail | thedrummer/cydonia-24b-v4.1","context_length":131072,"model":{"slug":"thedrummer/cydonia-24b-v4.1","hf_slug":"thedrummer/cydonia-24b-v4.1","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-27T00:11:18.116138+00:00","hf_updated_at":null,"name":"TheDrummer: Cydonia 24B V4.1","short_name":"Cydonia 24B V4.1","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/cydonia-24b-v4.1","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"thedrummer/cydonia-24b-v4.1","model_variant_permaslug":"thedrummer/cydonia-24b-v4.1","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-cydonia-24-v41","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.00000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000003","openai:completion_tokens":"0.0000005","openai:cached_prompt_tokens":"0.00000015"},"pricing_version_id":"797db847-2767-4d2e-97aa-8cf3f001c702","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-27T00:15:42.092Z","status":0}},{"slug":"relace/relace-apply-3","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-09-26T12:59:32.878Z","hf_updated_at":null,"name":"Relace: Relace Apply 3","short_name":"Relace Apply 3","author":"relace","author_display_name":"relace","author_icon_uri":null,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"relace/relace-apply-3","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"fast_apply","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7df5d5d2-c60a-487a-9770-7f68c2229d38","name":"Relace | relace/relace-apply-3","context_length":256000,"model":{"slug":"relace/relace-apply-3","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-09-26T12:59:32.878706+00:00","hf_updated_at":null,"name":"Relace: Relace Apply 3","short_name":"Relace Apply 3","author":"relace","author_display_name":"relace","author_icon_uri":null,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"relace/relace-apply-3","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"fast_apply","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"relace/relace-apply-3","model_variant_permaslug":"relace/relace-apply-3","adapter_name":"RelaceAdapter","provider_name":"Relace","provider_info":{"name":"Relace","displayName":"Relace","slug":"relace","baseUrl":"https://models.relace.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"RelaceAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://relace.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Relace","provider_slug":"relace/fp8","provider_model_id":"relace-apply-3","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["stop","seed","max_tokens"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.relace.ai/terms-of-use","privacyPolicyURL":"https://www.relace.ai/privacy-policy"},"pricing":{"prompt":"0.00000085","completion":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000085","openai:completion_tokens":"0.00000125"},"pricing_version_id":"9b0b1dc0-75a7-4972-be47-8f54376792fc","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-26T13:05:21.921Z","status":0}},{"slug":"qwen/qwen3-vl-235b-a22b-thinking","hf_slug":"Qwen/Qwen3-VL-235B-A22B-Thinking","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-23T23:04:50.000Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 235B A22B Thinking","short_name":"Qwen3 VL 235B A22B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-235b-a22b-thinking","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":0.8,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a4766f32-79c6-485a-8371-bff388d93df8","name":"Alibaba | qwen/qwen3-vl-235b-a22b-thinking","context_length":131072,"model":{"slug":"qwen/qwen3-vl-235b-a22b-thinking","hf_slug":"Qwen/Qwen3-VL-235B-A22B-Thinking","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-23T23:04:50+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 235B A22B Thinking","short_name":"Qwen3 VL 235B A22B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-235b-a22b-thinking","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":0.8,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-235b-a22b-thinking","model_variant_permaslug":"qwen/qwen3-vl-235b-a22b-thinking","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-vl-235b-a22b-thinking","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":126976,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.0000004","completion":"0.000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.0000004","alibaba:completion_tokens":"0.000004"},"pricing_version_id":"e457d302-a4e8-44f4-aecc-507e38d4dded","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:20:51.130Z","status":0}},{"slug":"qwen/qwen3-vl-235b-a22b-instruct","hf_slug":"Qwen/Qwen3-VL-235B-A22B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-23T23:04:47.000Z","hf_updated_at":null,"name":"Qwen: Qwen3 VL 235B A22B Instruct","short_name":"Qwen3 VL 235B A22B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","model_version_group_id":null,"context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-235b-a22b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a352cc82-2bdb-411b-9f99-bd7829655412","name":"DeepInfra | qwen/qwen3-vl-235b-a22b-instruct","context_length":262144,"model":{"slug":"qwen/qwen3-vl-235b-a22b-instruct","hf_slug":"Qwen/Qwen3-VL-235B-A22B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-23T23:04:47+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 VL 235B A22B Instruct","short_name":"Qwen3 VL 235B A22B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-vl-235b-a22b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-vl-235b-a22b-instruct","model_variant_permaslug":"qwen/qwen3-vl-235b-a22b-instruct","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000002","completion":"0.00000088","input_cache_read":"0.00000011","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000088","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000088","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000002","openai:completion_tokens":"0.00000088","openai:cached_prompt_tokens":"0.00000011"},"pricing_version_id":"28572f07-cbf5-41fe-8858-c785a94114eb","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":true},"supported_parameters":{"response_format":false,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-14T22:53:07.729Z","status":-2}},{"slug":"qwen/qwen3-max","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-23T21:26:48.000Z","hf_updated_at":null,"name":"Qwen: Qwen3 Max","short_name":"Qwen3 Max","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-max","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5e31ba3c-d5bf-4ced-a52d-96e2e6635f95","name":"Alibaba | qwen/qwen3-max","context_length":262144,"model":{"slug":"qwen/qwen3-max","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-23T21:26:48+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Max","short_name":"Qwen3 Max","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-max","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":1,"top_p":1,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-max","model_variant_permaslug":"qwen/qwen3-max","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-max","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":258048,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000078","completion":"0.0000039","input_cache_read":"0.000000156","input_cache_write":"0.000000975","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000156","completion":"0.0000078","input_cache_read":"0.000000312","input_cache_write":"0.00000195"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975","input_cache_read":"0.00000039","input_cache_write":"0.0000024375"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000078"},{"sku_label":"≤128K","price":"0.00000156"},{"sku_label":">128K","price":"0.00000195"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000039","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000039"},{"sku_label":"≤128K","price":"0.0000078"},{"sku_label":">128K","price":"0.00000975"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000156","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000156"},{"sku_label":"≤128K","price":"0.000000312"},{"sku_label":">128K","price":"0.00000039"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000975","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000975"},{"sku_label":"≤128K","price":"0.00000195"},{"sku_label":">128K","price":"0.0000024375"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000078"},{"sku_label":"≤128K","price":"0.000000156"},{"sku_label":">128K","price":"0.000000195"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000078"},{"sku_label":"≤128K","price":"0.00000156"},{"sku_label":">128K","price":"0.00000195"}]},{"kind":"token","sku_label":"Output Price","price":"0.0000039","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000039"},{"sku_label":"≤128K","price":"0.0000078"},{"sku_label":">128K","price":"0.00000975"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000156","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000156"},{"sku_label":"≤128K","price":"0.000000312"},{"sku_label":">128K","price":"0.00000039"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000975","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000975"},{"sku_label":"≤128K","price":"0.00000195"},{"sku_label":">128K","price":"0.0000024375"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000078"},{"sku_label":"≤128K","price":"0.000000156"},{"sku_label":">128K","price":"0.000000195"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000078","alibaba:tier2_threshold":"32000","alibaba:tier3_threshold":"128000","alibaba:completion_tokens":"0.0000039","alibaba:prompt_tokens_tier2":"0.00000156","alibaba:prompt_tokens_tier3":"0.00000195","alibaba:cached_prompt_tokens":"0.000000156","alibaba:cache_creation_tokens":"0.000000975","alibaba:completion_tokens_tier2":"0.0000078","alibaba:completion_tokens_tier3":"0.00000975","alibaba:cached_prompt_tokens_tier2":"0.000000312","alibaba:cached_prompt_tokens_tier3":"0.00000039","alibaba:cache_creation_tokens_tier2":"0.00000195","alibaba:cache_creation_tokens_tier3":"0.0000024375","alibaba:explicit_cached_prompt_tokens":"0.000000078","alibaba:explicit_cached_prompt_tokens_tier2":"0.000000156","alibaba:explicit_cached_prompt_tokens_tier3":"0.000000195"},"pricing_version_id":"9ee7056f-803a-4a74-9fda-13ec9497cf0c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":20,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-05T12:50:29.444Z","status":0}},{"slug":"qwen/qwen3-coder-plus","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-23T21:25:07.000Z","hf_updated_at":null,"name":"Qwen: Qwen3 Coder Plus","short_name":"Qwen3 Coder Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-plus","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"bc011219-e28e-416d-9cca-9aaf022f227e","name":"Alibaba | qwen/qwen3-coder-plus","context_length":1000000,"model":{"slug":"qwen/qwen3-coder-plus","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-23T21:25:07+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Coder Plus","short_name":"Qwen3 Coder Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-plus","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-coder-plus","model_variant_permaslug":"qwen/qwen3-coder-plus","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-coder-plus","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":997952,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000065","completion":"0.00000325","input_cache_read":"0.00000013","input_cache_write":"0.0000008125","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.00000117","completion":"0.00000585","input_cache_read":"0.000000234","input_cache_write":"0.0000014625"},{"min_prompt_tokens":128000,"prompt":"0.00000195","completion":"0.00000975","input_cache_read":"0.00000039","input_cache_write":"0.0000024375"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000065","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000065"},{"sku_label":"≤128K","price":"0.00000117"},{"sku_label":">128K","price":"0.00000195"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000325"},{"sku_label":"≤128K","price":"0.00000585"},{"sku_label":">128K","price":"0.00000975"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000013"},{"sku_label":"≤128K","price":"0.000000234"},{"sku_label":">128K","price":"0.00000039"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.0000008125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000008125"},{"sku_label":"≤128K","price":"0.0000014625"},{"sku_label":">128K","price":"0.0000024375"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000065","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000065"},{"sku_label":"≤128K","price":"0.000000117"},{"sku_label":">128K","price":"0.000000195"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000065","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000065"},{"sku_label":"≤128K","price":"0.00000117"},{"sku_label":">128K","price":"0.00000195"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000325"},{"sku_label":"≤128K","price":"0.00000585"},{"sku_label":">128K","price":"0.00000975"}]},{"kind":"token","sku_label":"Cache Read","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000013"},{"sku_label":"≤128K","price":"0.000000234"},{"sku_label":">128K","price":"0.00000039"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.0000008125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000008125"},{"sku_label":"≤128K","price":"0.0000014625"},{"sku_label":">128K","price":"0.0000024375"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000065","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000065"},{"sku_label":"≤128K","price":"0.000000117"},{"sku_label":">128K","price":"0.000000195"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000065","alibaba:tier2_threshold":"32000","alibaba:tier3_threshold":"128000","alibaba:completion_tokens":"0.00000325","alibaba:prompt_tokens_tier2":"0.00000117","alibaba:prompt_tokens_tier3":"0.00000195","alibaba:cached_prompt_tokens":"0.00000013","alibaba:cache_creation_tokens":"0.0000008125","alibaba:completion_tokens_tier2":"0.00000585","alibaba:completion_tokens_tier3":"0.00000975","alibaba:cached_prompt_tokens_tier2":"0.000000234","alibaba:cached_prompt_tokens_tier3":"0.00000039","alibaba:cache_creation_tokens_tier2":"0.0000014625","alibaba:cache_creation_tokens_tier3":"0.0000024375","alibaba:explicit_cached_prompt_tokens":"0.000000065","alibaba:explicit_cached_prompt_tokens_tier2":"0.000000117","alibaba:explicit_cached_prompt_tokens_tier3":"0.000000195"},"pricing_version_id":"58782e37-2a56-4eb4-9556-b2a7373832eb","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_implicit_caching":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-22T21:31:55.445Z","status":0}},{"slug":"openai/gpt-5-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-09-23T16:03:23.098Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Codex (batch)","short_name":"GPT-5 Codex (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-codex","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1199faf7-2948-4d08-a884-58fe1aff7af2","name":"OpenAI | openai/gpt-5-codex:batch","context_length":400000,"model":{"slug":"openai/gpt-5-codex","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-09-23T16:03:23.098042+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Codex","short_name":"GPT-5 Codex","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-codex","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-codex:batch","model_variant_permaslug":"openai/gpt-5-codex:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-codex","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":["temperature","top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000625","completion":"0.000005","input_cache_read":"0.0000000625","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"6.250000e-7","openai_responses:completion_tokens":"5.000000e-6","openai_responses:cached_prompt_tokens":"6.250000e-8"},"pricing_version_id":"ba301bcd-ed85-4355-a75a-0890fcf996e5","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:26.739Z","status":0}},{"slug":"deepseek/deepseek-v3.1-terminus","hf_slug":"deepseek-ai/DeepSeek-V3.1-Terminus","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-22T13:37:55.611Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.1 Terminus","short_name":"DeepSeek V3.1 Terminus","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. ","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-v3.1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v3.1-terminus","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"812bc18a-5b61-42d0-a550-f9ed8c2164c5","name":"Novita | deepseek/deepseek-v3.1-terminus","context_length":131072,"model":{"slug":"deepseek/deepseek-v3.1-terminus","hf_slug":"deepseek-ai/DeepSeek-V3.1-Terminus","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-22T13:37:55.611452+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.1 Terminus","short_name":"DeepSeek V3.1 Terminus","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. ","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-v3.1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-v3.1-terminus","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-v3.1-terminus","model_variant_permaslug":"deepseek/deepseek-v3.1-terminus","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"deepseek/deepseek-v3.1-terminus","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000027","completion":"0.000001","input_cache_read":"0.000000135","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000135","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000135","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000027","openai:completion_tokens":"0.000001","openai:cached_prompt_tokens":"0.000000135"},"pricing_version_id":"3e6b4b38-b024-4a51-9f8f-abf1e08cde0f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-22T16:07:26.596Z","status":0}},{"slug":"qwen/qwen3-coder-flash","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-17T13:25:36.216Z","hf_updated_at":null,"name":"Qwen: Qwen3 Coder Flash","short_name":"Qwen3 Coder Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-flash","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"ded5f1ed-4249-476c-a19e-df63b005a8b7","name":"Alibaba | qwen/qwen3-coder-flash","context_length":1000000,"model":{"slug":"qwen/qwen3-coder-flash","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-17T13:25:36.216914+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Coder Flash","short_name":"Qwen3 Coder Flash","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-flash","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-coder-flash","model_variant_permaslug":"qwen/qwen3-coder-flash","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-coder-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":997952,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000195","completion":"0.000000975","input_cache_read":"0.000000039","input_cache_write":"0.00000024375","discount":0,"overrides":[{"min_prompt_tokens":32000,"prompt":"0.000000325","completion":"0.000001625","input_cache_read":"0.000000065","input_cache_write":"0.00000040625"},{"min_prompt_tokens":128000,"prompt":"0.00000052","completion":"0.0000026","input_cache_read":"0.000000104","input_cache_write":"0.00000065"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000195","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000195"},{"sku_label":"≤128K","price":"0.000000325"},{"sku_label":">128K","price":"0.00000052"}]},{"kind":"token","sku_label":"Output Price","price":"0.000000975","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000975"},{"sku_label":"≤128K","price":"0.000001625"},{"sku_label":">128K","price":"0.0000026"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000039","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000039"},{"sku_label":"≤128K","price":"0.000000065"},{"sku_label":">128K","price":"0.000000104"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000024375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000024375"},{"sku_label":"≤128K","price":"0.00000040625"},{"sku_label":">128K","price":"0.00000065"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000000195","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000000195"},{"sku_label":"≤128K","price":"0.0000000325"},{"sku_label":">128K","price":"0.000000052"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000195","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000195"},{"sku_label":"≤128K","price":"0.000000325"},{"sku_label":">128K","price":"0.00000052"}]},{"kind":"token","sku_label":"Output Price","price":"0.000000975","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000975"},{"sku_label":"≤128K","price":"0.000001625"},{"sku_label":">128K","price":"0.0000026"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000039","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.000000039"},{"sku_label":"≤128K","price":"0.000000065"},{"sku_label":">128K","price":"0.000000104"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.00000024375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.00000024375"},{"sku_label":"≤128K","price":"0.00000040625"},{"sku_label":">128K","price":"0.00000065"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.0000000195","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤32K","price":"0.0000000195"},{"sku_label":"≤128K","price":"0.0000000325"},{"sku_label":">128K","price":"0.000000052"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.000000195","alibaba:tier2_threshold":"32000","alibaba:tier3_threshold":"128000","alibaba:completion_tokens":"0.000000975","alibaba:prompt_tokens_tier2":"0.000000325","alibaba:prompt_tokens_tier3":"0.00000052","alibaba:cached_prompt_tokens":"0.000000039","alibaba:cache_creation_tokens":"0.00000024375","alibaba:completion_tokens_tier2":"0.000001625","alibaba:completion_tokens_tier3":"0.0000026","alibaba:cached_prompt_tokens_tier2":"0.000000065","alibaba:cached_prompt_tokens_tier3":"0.000000104","alibaba:cache_creation_tokens_tier2":"0.00000040625","alibaba:cache_creation_tokens_tier3":"0.00000065","alibaba:explicit_cached_prompt_tokens":"0.0000000195","alibaba:explicit_cached_prompt_tokens_tier2":"0.0000000325","alibaba:explicit_cached_prompt_tokens_tier3":"0.000000052"},"pricing_version_id":"962d11b8-7b16-4239-8b1d-3aaacde6ac3c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-17T13:28:06.247Z","status":0}},{"slug":"qwen/qwen3-next-80b-a3b-thinking","hf_slug":"Qwen/Qwen3-Next-80B-A3B-Thinking","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-11T17:38:04.192Z","hf_updated_at":null,"name":"Qwen: Qwen3 Next 80B A3B Thinking","short_name":"Qwen3 Next 80B A3B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.\n\nThe model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-next-80b-a3b-thinking-2509","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1b075e5f-051b-4d60-9bc3-20f69ff6355d","name":"Alibaba | qwen/qwen3-next-80b-a3b-thinking-2509","context_length":131072,"model":{"slug":"qwen/qwen3-next-80b-a3b-thinking","hf_slug":"Qwen/Qwen3-Next-80B-A3B-Thinking","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-11T17:38:04.192907+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Next 80B A3B Thinking","short_name":"Qwen3 Next 80B A3B Thinking","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.\n\nThe model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-next-80b-a3b-thinking-2509","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-next-80b-a3b-thinking","model_variant_permaslug":"qwen/qwen3-next-80b-a3b-thinking-2509","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-next-80b-a3b-thinking","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":126976,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000015","completion":"0.0000012","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.00000015","alibaba:completion_tokens":"0.0000012"},"pricing_version_id":"998809e9-37ff-4223-9288-24b4c91eacd7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-11T18:04:09.189Z","status":0}},{"slug":"qwen/qwen3-next-80b-a3b-instruct","hf_slug":"Qwen/Qwen3-Next-80B-A3B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-11T17:36:53.637Z","hf_updated_at":null,"name":"Qwen: Qwen3 Next 80B A3B Instruct","short_name":"Qwen3 Next 80B A3B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.\n\nThe model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-next-80b-a3b-instruct-2509","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"74635ab6-7ba2-4cd7-8f2f-10651305385a","name":"DeepInfra | qwen/qwen3-next-80b-a3b-instruct-2509","context_length":262144,"model":{"slug":"qwen/qwen3-next-80b-a3b-instruct","hf_slug":"Qwen/Qwen3-Next-80B-A3B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-11T17:36:53.6379+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Next 80B A3B Instruct","short_name":"Qwen3 Next 80B A3B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.\n\nThe model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-next-80b-a3b-instruct-2509","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-next-80b-a3b-instruct","model_variant_permaslug":"qwen/qwen3-next-80b-a3b-instruct-2509","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000009","completion":"0.0000011","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000009","openai:completion_tokens":"0.0000011"},"pricing_version_id":"e713bbeb-5c04-42ee-bb0e-e98a32b60600","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-11T23:34:07.659Z","status":0}},{"slug":"qwen/qwen-plus-2025-07-28","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-08T16:06:39.935Z","hf_updated_at":null,"name":"Qwen: Qwen Plus 0728","short_name":"Qwen Plus 0728","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-plus-2025-07-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"23a86833-b536-4529-94c4-a18746e95c60","name":"Alibaba | qwen/qwen-plus-2025-07-28","context_length":1000000,"model":{"slug":"qwen/qwen-plus-2025-07-28","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-08T16:06:39.935416+00:00","hf_updated_at":null,"name":"Qwen: Qwen Plus 0728","short_name":"Qwen Plus 0728","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-plus-2025-07-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen-plus-2025-07-28","model_variant_permaslug":"qwen/qwen-plus-2025-07-28","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen-plus-2025-07-28","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":995904,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000026","completion":"0.00000078","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.00000078"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000078"},{"sku_label":">256K","price":"0.00000234"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.00000078"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000078"},{"sku_label":">256K","price":"0.00000234"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000026","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.00000078","alibaba:prompt_tokens_tier2":"0.00000078","alibaba:completion_tokens_tier2":"0.00000234"},"pricing_version_id":"ada8651a-d7d8-444b-9a91-f56b90fdf080","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-08T16:08:55.302Z","status":0}},{"slug":"qwen/qwen-plus-2025-07-28","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-08T16:06:39.935Z","hf_updated_at":null,"name":"Qwen: Qwen Plus 0728 (thinking)","short_name":"Qwen Plus 0728 (thinking)","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-plus-2025-07-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3d871d0b-eade-4fd4-95b3-1d5f25e2b0c3","name":"Alibaba | qwen/qwen-plus-2025-07-28:thinking","context_length":1000000,"model":{"slug":"qwen/qwen-plus-2025-07-28","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-08T16:06:39.935416+00:00","hf_updated_at":null,"name":"Qwen: Qwen Plus 0728","short_name":"Qwen Plus 0728","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-plus-2025-07-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen-plus-2025-07-28:thinking","model_variant_permaslug":"qwen/qwen-plus-2025-07-28:thinking","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen-plus-2025-07-28","quantization":"unknown","variant":"thinking","is_free":false,"can_abort":false,"max_prompt_tokens":995904,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","presence_penalty","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000026","completion":"0.00000078","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.00000078"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000078"},{"sku_label":">256K","price":"0.00000234"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.00000078"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000078"},{"sku_label":">256K","price":"0.00000234"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000026","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.00000078","alibaba:prompt_tokens_tier2":"0.00000078","alibaba:completion_tokens_tier2":"0.00000234"},"pricing_version_id":"a66ed6ce-f450-40a0-8b6b-a9e051e35a43","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-08T16:09:45.158Z","status":0}},{"slug":"moonshotai/kimi-k2-0905","hf_slug":"moonshotai/Kimi-K2-Instruct-0905","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-09-04T21:25:47.673Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2 0905","short_name":"Kimi K2 0905","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k.\n\nThis update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2-0905","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"262402a8-8891-4131-bc3c-a76c4bb9b391","name":"Novita | moonshotai/kimi-k2-0905","context_length":262144,"model":{"slug":"moonshotai/kimi-k2-0905","hf_slug":"moonshotai/Kimi-K2-Instruct-0905","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-09-04T21:25:47.673205+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2 0905","short_name":"Kimi K2 0905","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k.\n\nThis update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2-0905","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2-0905","model_variant_permaslug":"moonshotai/kimi-k2-0905","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"moonshotai/kimi-k2-0905","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100352,"max_tokens_per_image":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000006","completion":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000006","openai:completion_tokens":"0.0000025"},"pricing_version_id":"7249d9af-17d4-44e1-aab6-e0a1f09e071c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-05T13:03:29.420Z","status":0}},{"slug":"qwen/qwen3-30b-a3b-thinking-2507","hf_slug":"Qwen/Qwen3-30B-A3B-Thinking-2507","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-28T16:39:52.539Z","hf_updated_at":null,"name":"Qwen: Qwen3 30B A3B Thinking 2507","short_name":"Qwen3 30B A3B Thinking 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.\n\nCompared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.","model_version_group_id":null,"context_length":81920,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-30b-a3b-thinking-2507","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"86834360-63c5-482a-8ef9-85b22ddf0980","name":"Alibaba | qwen/qwen3-30b-a3b-thinking-2507","context_length":81920,"model":{"slug":"qwen/qwen3-30b-a3b-thinking-2507","hf_slug":"Qwen/Qwen3-30B-A3B-Thinking-2507","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-28T16:39:52.539313+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 30B A3B Thinking 2507","short_name":"Qwen3 30B A3B Thinking 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.\n\nCompared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-30b-a3b-thinking-2507","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-30b-a3b-thinking-2507","model_variant_permaslug":"qwen/qwen3-30b-a3b-thinking-2507","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-30b-a3b-thinking-2507","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":126976,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.0000024","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":2e-7,"alibaba:completion_tokens":0.0000024},"pricing_version_id":"d1596c9a-5349-44e8-9bf1-c96aa11f23d9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-28T18:00:44.881Z","status":0}},{"slug":"nousresearch/hermes-4-70b","hf_slug":"NousResearch/Hermes-4-70B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-26T19:23:02.446Z","hf_updated_at":null,"name":"Nous: Hermes 4 70B","short_name":"Hermes 4 70B","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThis 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-4-70b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9e1bd3ed-059c-4fcf-9435-c1993ef564db","name":"Nebius | nousresearch/hermes-4-70b","context_length":131072,"model":{"slug":"nousresearch/hermes-4-70b","hf_slug":"NousResearch/Hermes-4-70B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-26T19:23:02.446988+00:00","hf_updated_at":null,"name":"Nous: Hermes 4 70B","short_name":"Hermes 4 70B","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThis 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-4-70b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"nousresearch/hermes-4-70b","model_variant_permaslug":"nousresearch/hermes-4-70b","adapter_name":"NebiusAdapter","provider_name":"Nebius","provider_info":{"name":"Nebius","displayName":"Nebius Token Factory","slug":"nebius","baseUrl":"https://api.studio.nebius.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.nebius.com/legal/studio/terms-of-use/","privacyPolicyURL":"https://docs.nebius.com/legal/studio/privacy/","requiresUserIDs":false},"headquarters":"NL","hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NebiusAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://docs.nebius.com/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Nebius Token Factory","provider_slug":"nebius/fp8","provider_model_id":"NousResearch/Hermes-4-70B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","repetition_penalty","response_format"],"excluded_parameters":["stop","seed","logit_bias","logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.nebius.com/legal/studio/terms-of-use/","privacyPolicyURL":"https://docs.nebius.com/legal/studio/privacy/"},"pricing":{"prompt":"0.00000013","completion":"0.0000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000013","openai:completion_tokens":"0.0000004"},"pricing_version_id":"5d5263db-b406-4f68-9c2b-0f658604eca9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-26T19:24:29.292Z","status":0}},{"slug":"nousresearch/hermes-4-405b","hf_slug":"NousResearch/Hermes-4-405B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-26T19:11:03.380Z","hf_updated_at":null,"name":"Nous: Hermes 4 405B","short_name":"Hermes 4 405B","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-4-405b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c575da03-bbd8-4d9e-963d-497ea0ffcb13","name":"Nebius | nousresearch/hermes-4-405b","context_length":131072,"model":{"slug":"nousresearch/hermes-4-405b","hf_slug":"NousResearch/Hermes-4-405B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-26T19:11:03.380181+00:00","hf_updated_at":null,"name":"Nous: Hermes 4 405B","short_name":"Hermes 4 405B","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.","model_version_group_id":null,"context_length":0,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-4-405b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":"You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"nousresearch/hermes-4-405b","model_variant_permaslug":"nousresearch/hermes-4-405b","adapter_name":"NebiusAdapter","provider_name":"Nebius","provider_info":{"name":"Nebius","displayName":"Nebius Token Factory","slug":"nebius","baseUrl":"https://api.studio.nebius.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.nebius.com/legal/studio/terms-of-use/","privacyPolicyURL":"https://docs.nebius.com/legal/studio/privacy/","requiresUserIDs":false},"headquarters":"NL","hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NebiusAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://docs.nebius.com/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Nebius Token Factory","provider_slug":"nebius/fp8","provider_model_id":"NousResearch/Hermes-4-405B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","repetition_penalty","response_format"],"excluded_parameters":["stop","seed","logit_bias","logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.nebius.com/legal/studio/terms-of-use/","privacyPolicyURL":"https://docs.nebius.com/legal/studio/privacy/"},"pricing":{"prompt":"0.000001","completion":"0.000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000001","openai:completion_tokens":"0.000003"},"pricing_version_id":"d8d32b20-c0b6-4cdf-9750-e0e137f4fa7f","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-26T19:14:25.102Z","status":0}},{"slug":"deepseek/deepseek-chat-v3.1","hf_slug":"deepseek-ai/DeepSeek-V3.1","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-21T12:33:48.000Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.1","short_name":"DeepSeek V3.1","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. \n\nIt succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-v3.1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-chat-v3.1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"012f7d1f-23d4-4d03-9aa3-432d8ad82757","name":"DeepInfra | deepseek/deepseek-chat-v3.1","context_length":163840,"model":{"slug":"deepseek/deepseek-chat-v3.1","hf_slug":"deepseek-ai/DeepSeek-V3.1","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-21T12:33:48+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3.1","short_name":"DeepSeek V3.1","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. \n\nIt succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-v3.1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-chat-v3.1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-chat-v3.1","model_variant_permaslug":"deepseek/deepseek-chat-v3.1","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"deepseek-ai/DeepSeek-V3.1","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"excluded_parameters":["logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000025","completion":"0.00000095","input_cache_read":"0.00000013","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000095","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000025","openai:completion_tokens":"0.00000095","openai:cached_prompt_tokens":"0.00000013"},"pricing_version_id":"00f3c1cb-44af-413e-95e9-113c7149805a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":500,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-23T00:29:48.794Z","status":0}},{"slug":"mistralai/mistral-medium-3.1","hf_slug":"","updated_at":"2026-05-14T22:39:39.071Z","created_at":"2025-08-13T14:33:59.459Z","hf_updated_at":null,"name":"Mistral: Mistral Medium 3.1","short_name":"Mistral Medium 3.1","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-medium-3.1","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"13c5002b-8c5b-490c-8a5f-52ec0242804f","name":"Mistral | mistralai/mistral-medium-3.1","context_length":131072,"model":{"slug":"mistralai/mistral-medium-3.1","hf_slug":"","updated_at":"2026-05-14T22:39:39.071337+00:00","created_at":"2025-08-13T14:33:59.459114+00:00","hf_updated_at":null,"name":"Mistral: Mistral Medium 3.1","short_name":"Mistral Medium 3.1","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-medium-3.1","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-medium-3.1","model_variant_permaslug":"mistralai/mistral-medium-3.1","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"mistral-medium-2508","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"4e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"4e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"4e-7","mistral:completion_tokens":0.000002,"mistral:cached_prompt_tokens":"4e-8"},"pricing_version_id":"886c2e5e-afd6-4b72-b4f1-59bc5d998670","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-13T14:34:24.282Z","status":0}},{"slug":"z-ai/glm-4.5v","hf_slug":"zai-org/GLM-4.5V","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-11T14:24:48.340Z","hf_updated_at":null,"name":"Z.ai: GLM 4.5V","short_name":"GLM 4.5V","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":65536,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.5v","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"30f10717-f218-430f-a3d7-858bf5fdf303","name":"Novita | z-ai/glm-4.5v","context_length":65536,"model":{"slug":"z-ai/glm-4.5v","hf_slug":"zai-org/GLM-4.5V","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-11T14:24:48.340676+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.5V","short_name":"GLM 4.5V","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":65536,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.5v","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.5v","model_variant_permaslug":"z-ai/glm-4.5v","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"zai-org/glm-4.5v","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000006","completion":"0.0000018","input_cache_read":"0.00000011","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000006","openai:completion_tokens":"0.0000018","openai:cached_prompt_tokens":"0.00000011"},"pricing_version_id":"e6847a35-8151-4bb4-893d-caa884086509","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_input_audio":false,"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-11T15:07:54.675Z","status":0}},{"slug":"openai/gpt-5","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-08-07T17:23:33.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5 (batch)","short_name":"GPT-5 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"74c59f3a-ff24-4194-aa97-7ecc53b8fd93","name":"OpenAI | openai/gpt-5-2025-08-07:batch","context_length":400000,"model":{"slug":"openai/gpt-5","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-08-07T17:23:33+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5","short_name":"GPT-5","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5:batch","model_variant_permaslug":"openai/gpt-5-2025-08-07:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-2025-08-07","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000625","completion":"0.000005","input_cache_read":"0.0000000625","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"6.250000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"5.000000e-6","openai_responses:cached_prompt_tokens":"6.250000e-8"},"pricing_version_id":"1edd7de3-1cbe-42cc-85bb-db06b71591c9","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:49.687Z","status":0}},{"slug":"openai/gpt-5","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-08-07T17:23:33.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5","short_name":"GPT-5","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4","name":"OpenAI | openai/gpt-5-2025-08-07","context_length":400000,"model":{"slug":"openai/gpt-5","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-08-07T17:23:33+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5","short_name":"GPT-5","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["minimal","low","medium","high"],"default_reasoning_effort":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5","model_variant_permaslug":"openai/gpt-5-2025-08-07","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai/default","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai/default","provider_model_id":"gpt-5-2025-08-07","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":272000,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.00000125,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.00001,"openai_responses:cached_prompt_tokens":1.25e-7},"pricing_version_id":"c6d64142-2e88-4d34-8469-6b1dd34b407a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-07T01:55:28.866Z","status":0}},{"slug":"openai/gpt-5-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-08-07T17:23:27.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Mini","short_name":"GPT-5 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-mini-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2609e67e-dcd4-401e-ae80-014ea7f111d8","name":"Azure | openai/gpt-5-mini-2025-08-07","context_length":400000,"model":{"slug":"openai/gpt-5-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-08-07T17:23:27+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Mini","short_name":"GPT-5 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-mini-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-mini","model_variant_permaslug":"openai/gpt-5-mini-2025-08-07","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000025","completion":"0.000002","input_cache_read":"0.00000003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":2.5e-7,"openai_responses:completion_tokens":0.000002,"openai_responses:cached_prompt_tokens":3e-8},"pricing_version_id":"cd54f047-0acd-46ea-87ab-30c2ad28d408","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-11T19:12:29.864Z","status":0}},{"slug":"openai/gpt-5-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-08-07T17:23:27.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Mini (batch)","short_name":"GPT-5 Mini (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-mini-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e4e688dd-454d-484a-b4c3-cf2d81407583","name":"OpenAI | openai/gpt-5-mini-2025-08-07:batch","context_length":400000,"model":{"slug":"openai/gpt-5-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-08-07T17:23:27+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Mini","short_name":"GPT-5 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-mini-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-mini:batch","model_variant_permaslug":"openai/gpt-5-mini-2025-08-07:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-mini-2025-08-07","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000125","completion":"0.000001","input_cache_read":"0.0000000125","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.250000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"1.000000e-6","openai_responses:cached_prompt_tokens":"1.250000e-8","openai_responses:flex_tier_multiplier":"0.5"},"pricing_version_id":"bf3f4683-cc93-430f-b0d1-3d4945360be2","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:50.667Z","status":0}},{"slug":"openai/gpt-5-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-08-07T17:23:22.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Nano (batch)","short_name":"GPT-5 Nano (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-nano-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1745e1e7-4a49-4e0c-8464-b08e3465ebb3","name":"OpenAI | openai/gpt-5-nano-2025-08-07:batch","context_length":400000,"model":{"slug":"openai/gpt-5-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-08-07T17:23:22+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Nano","short_name":"GPT-5 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-nano-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-nano:batch","model_variant_permaslug":"openai/gpt-5-nano-2025-08-07:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-5-nano-2025-08-07","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000025","completion":"0.0000002","input_cache_read":"0.0000000025","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"0.000000025","openai_responses:completion_tokens":"0.0000002","openai_responses:cached_prompt_tokens":"0.0000000025"},"pricing_version_id":"c6c82a1b-2781-41c1-836b-c1775a46041c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_implicit_caching":true,"supports_file_urls":true,"supports_native_web_search":true,"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-20T17:57:08.161Z","status":0}},{"slug":"openai/gpt-5-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-08-07T17:23:22.000Z","hf_updated_at":null,"name":"OpenAI: GPT-5 Nano","short_name":"GPT-5 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-nano-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"36b76b2b-0b8d-423c-9e90-a8bba875ef45","name":"Azure | openai/gpt-5-nano-2025-08-07","context_length":400000,"model":{"slug":"openai/gpt-5-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-08-07T17:23:22+00:00","hf_updated_at":null,"name":"OpenAI: GPT-5 Nano","short_name":"GPT-5 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","model_version_group_id":null,"context_length":400000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-5-nano-2025-08-07","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["minimal","low","medium","high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-05-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-5-nano","model_variant_permaslug":"openai/gpt-5-nano-2025-08-07","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-5-nano","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","reasoning","include_reasoning","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000005","completion":"0.0000004","input_cache_read":"0.00000001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":5e-8,"openai_responses:completion_tokens":4e-7,"openai_responses:cached_prompt_tokens":1e-8},"pricing_version_id":"81f738a4-68aa-4a86-8607-72a21ba463d9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_native_apply_patch":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-11T19:19:10.197Z","status":0}},{"slug":"openai/gpt-oss-120b","hf_slug":"openai/gpt-oss-120b","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-05T17:17:11.000Z","hf_updated_at":null,"name":"OpenAI: gpt-oss-120b","short_name":"gpt-oss-120b","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-oss-120b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5595698f-9ce8-4aa8-8037-f0d7d3c13d2a","name":"CoreWeave | openai/gpt-oss-120b","context_length":131072,"model":{"slug":"openai/gpt-oss-120b","hf_slug":"openai/gpt-oss-120b","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-05T17:17:11+00:00","hf_updated_at":null,"name":"OpenAI: gpt-oss-120b","short_name":"gpt-oss-120b","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-oss-120b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-oss-120b","model_variant_permaslug":"openai/gpt-oss-120b","adapter_name":"WandbAdapter","provider_name":"CoreWeave","provider_info":{"name":"CoreWeave","displayName":"CoreWeave","slug":"coreweave","baseUrl":"https://api.inference.wandb.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"WandbAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/CoreWeave.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"CoreWeave","provider_slug":"coreweave/fp4","provider_model_id":"openai/gpt-oss-120b","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy"},"pricing":{"prompt":"0.00000003","completion":"0.00000017","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000017","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000017","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000003","openai:completion_tokens":"0.00000017","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"807dafed-98fe-4d61-ba4f-3351c7dc3359","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":250,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T21:06:52.094Z","status":0}},{"slug":"openai/gpt-oss-20b","hf_slug":"openai/gpt-oss-20b","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-08-05T17:17:09.000Z","hf_updated_at":null,"name":"OpenAI: gpt-oss-20b","short_name":"gpt-oss-20b","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-oss-20b","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e668be79-ecd1-4163-9cec-7a3664486541","name":"CoreWeave | openai/gpt-oss-20b","context_length":131072,"model":{"slug":"openai/gpt-oss-20b","hf_slug":"openai/gpt-oss-20b","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-08-05T17:17:09+00:00","hf_updated_at":null,"name":"OpenAI: gpt-oss-20b","short_name":"gpt-oss-20b","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-oss-20b","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["low","medium","high"],"default_reasoning_effort":"medium"},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"reasoning","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-oss-20b","model_variant_permaslug":"openai/gpt-oss-20b","adapter_name":"WandbAdapter","provider_name":"CoreWeave","provider_info":{"name":"CoreWeave","displayName":"CoreWeave","slug":"coreweave","baseUrl":"https://api.inference.wandb.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"WandbAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/CoreWeave.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"CoreWeave","provider_slug":"coreweave/fp4","provider_model_id":"openai/gpt-oss-20b","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.coreweave.com/policies/terms-of-service","privacyPolicyURL":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy"},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000003","openai:completion_tokens":"0.00000013","openai:cached_prompt_tokens":"0.00000003"},"pricing_version_id":"c681defe-e356-4acd-9934-7e2b6427643e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T21:06:51.602Z","status":0}},{"slug":"anthropic/claude-opus-4.1","hf_slug":"","updated_at":"2026-04-11T05:41:05.394Z","created_at":"2025-08-05T16:33:11.634Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.1 (batch)","short_name":"Claude Opus 4.1 (batch)","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.1-opus-20250805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a4d7df36-7bdd-44cc-9c51-4625aedc52a0","name":"Anthropic | anthropic/claude-4.1-opus-20250805:batch","context_length":200000,"model":{"slug":"anthropic/claude-opus-4.1","hf_slug":"","updated_at":"2026-04-11T05:41:05.394154+00:00","created_at":"2025-08-05T16:33:11.634562+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.1","short_name":"Claude Opus 4.1","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.1-opus-20250805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.1:batch","model_variant_permaslug":"anthropic/claude-4.1-opus-20250805:batch","adapter_name":"AnthropicBatchAdapter","provider_name":"Anthropic","provider_info":{"name":"Anthropic","displayName":"Anthropic","slug":"anthropic","baseUrl":"https://api.anthropic.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"AnthropicBatchAdapter","statusPageUrl":"https://status.anthropic.com/","byokEnabled":true,"icon":{"url":"/images/icons/Anthropic.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Anthropic","provider_slug":"anthropic","provider_model_id":"claude-opus-4-1-20250805","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","tools","tool_choice","structured_outputs","response_format"],"excluded_parameters":["top_p"],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.anthropic.com/legal/commercial-terms","privacyPolicyURL":"https://www.anthropic.com/legal/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000075","completion":"0.0000375","input_cache_read":"0.00000075","input_cache_write":"0.000009375","input_cache_write_1h":"0.000015","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000009375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.000009375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"anthropic:prompt_tokens":"0.0000075","anthropic:web_search_calls":"0.01","anthropic:cache_read_tokens":"7.5e-7","anthropic:completion_tokens":"0.0000375","anthropic:cache_write_1h_tokens":"0.000015","anthropic:cache_write_5m_tokens":"0.000009375"},"pricing_version_id":"6a8687fc-e323-4779-8a12-1288b4a92b82","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-22T22:10:15.586Z","status":0}},{"slug":"anthropic/claude-opus-4.1","hf_slug":"","updated_at":"2026-04-11T05:41:05.394Z","created_at":"2025-08-05T16:33:11.634Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.1","short_name":"Claude Opus 4.1","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.1-opus-20250805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"ece5c3c6-e437-4297-92fc-150a1771ec56","name":"Amazon Bedrock | anthropic/claude-4.1-opus-20250805","context_length":200000,"model":{"slug":"anthropic/claude-opus-4.1","hf_slug":"","updated_at":"2026-04-11T05:41:05.394154+00:00","created_at":"2025-08-05T16:33:11.634562+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4.1","short_name":"Claude Opus 4.1","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4.1-opus-20250805","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4.1","model_variant_permaslug":"anthropic/claude-4.1-opus-20250805","adapter_name":"InternalStreamAmazonBedrockInvokeAnthropicAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Amazon Bedrock","provider_slug":"amazon-bedrock","provider_model_id":"us.anthropic.claude-opus-4-1-20250805-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000015","completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":0.000015,"anthropic:web_search_calls":0.01,"anthropic:cache_read_tokens":0.0000015,"anthropic:completion_tokens":0.000075,"anthropic:cache_write_1h_tokens":0.00003,"anthropic:cache_write_5m_tokens":0.00001875},"pricing_version_id":"ce33ad08-2e47-4675-9bac-0d5dbf2173f3","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-09T13:47:34.607Z","status":0}},{"slug":"mistralai/codestral-2508","hf_slug":"","updated_at":"2026-05-14T22:39:39.743Z","created_at":"2025-08-01T20:20:30.639Z","hf_updated_at":null,"name":"Mistral: Codestral 2508","short_name":"Codestral 2508","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","model_version_group_id":null,"context_length":256000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/codestral-2508","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"dfdc2841-297c-4de9-96fe-eab0ccfa25a6","name":"Mistral | mistralai/codestral-2508","context_length":256000,"model":{"slug":"mistralai/codestral-2508","hf_slug":"","updated_at":"2026-05-14T22:39:39.743685+00:00","created_at":"2025-08-01T20:20:30.639517+00:00","hf_updated_at":null,"name":"Mistral: Codestral 2508","short_name":"Codestral 2508","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","model_version_group_id":null,"context_length":256000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/codestral-2508","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/codestral-2508","model_variant_permaslug":"mistralai/codestral-2508","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"codestral-2508","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"9e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"9e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"3e-7","mistral:completion_tokens":9e-7,"mistral:cached_prompt_tokens":"3e-8"},"pricing_version_id":"8de0c675-cc4f-42ff-ba8c-ee058c7a5a96","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-01T20:21:25.547Z","status":0}},{"slug":"qwen/qwen3-coder-30b-a3b-instruct","hf_slug":"Qwen/Qwen3-Coder-30B-A3B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-31T14:32:59.359Z","hf_updated_at":null,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","short_name":"Qwen3 Coder 30B A3B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.\n\nThis model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats. ","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-30b-a3b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"ded7fa7f-5261-4772-87fb-96994d95c6b9","name":"Novita | qwen/qwen3-coder-30b-a3b-instruct","context_length":160000,"model":{"slug":"qwen/qwen3-coder-30b-a3b-instruct","hf_slug":"Qwen/Qwen3-Coder-30B-A3B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-31T14:32:59.359308+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","short_name":"Qwen3 Coder 30B A3B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.\n\nThis model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats. ","model_version_group_id":null,"context_length":0,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-30b-a3b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-coder-30b-a3b-instruct","model_variant_permaslug":"qwen/qwen3-coder-30b-a3b-instruct","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"qwen/qwen3-coder-30b-a3b-instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000007","completion":"0.00000027","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000027","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000007","openai:completion_tokens":"0.00000027"},"pricing_version_id":"44aee927-ccb8-4658-9933-8a1e1d761e83","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-10T18:41:28.549Z","status":0}},{"slug":"qwen/qwen3-30b-a3b-instruct-2507","hf_slug":"Qwen/Qwen3-30B-A3B-Instruct-2507","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-29T16:36:05.687Z","hf_updated_at":null,"name":"Qwen: Qwen3 30B A3B Instruct 2507","short_name":"Qwen3 30B A3B Instruct 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-30b-a3b-instruct-2507","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4ea9b8c2-e4a8-4707-8e4b-a8693745edbe","name":"StreamLake | qwen/qwen3-30b-a3b-instruct-2507","context_length":128000,"model":{"slug":"qwen/qwen3-30b-a3b-instruct-2507","hf_slug":"Qwen/Qwen3-30B-A3B-Instruct-2507","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-29T16:36:05.687988+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 30B A3B Instruct 2507","short_name":"Qwen3 30B A3B Instruct 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-30b-a3b-instruct-2507","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-30b-a3b-instruct-2507","model_variant_permaslug":"qwen/qwen3-30b-a3b-instruct-2507","adapter_name":"StreamLakeAdapter","provider_name":"StreamLake","provider_info":{"name":"StreamLake","displayName":"StreamLake","slug":"streamlake","baseUrl":"https://vanchin.streamlake.ai/api/gateway/v1/endpoints","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"StreamLakeAdapter","statusPageUrl":"https://status.streamlake.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.streamlake.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"StreamLake","provider_slug":"streamlake","provider_model_id":"qwen3-30b-a3b-instruct-2507","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32000,"max_tokens_per_image":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54"},"pricing":{"prompt":"0.00000004815","completion":"0.00000019305","discount":0.55,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004815","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000019305","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004815","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000019305","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000107","openai:completion_tokens":"0.000000429"},"pricing_version_id":"26115e1d-3d99-4a76-94e4-6e3360604427","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-01T14:21:32.816Z","status":0}},{"slug":"z-ai/glm-4.5","hf_slug":"zai-org/GLM-4.5","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-25T19:22:27.278Z","hf_updated_at":null,"name":"Z.ai: GLM 4.5","short_name":"GLM 4.5","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.5","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":false},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":false},"chat_template_config":{}},"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"48b95ad9-4c60-411f-8b5b-c3f1745c4f62","name":"Z.AI | z-ai/glm-4.5","context_length":131072,"model":{"slug":"z-ai/glm-4.5","hf_slug":"zai-org/GLM-4.5","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-25T19:22:27.278283+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.5","short_name":"GLM 4.5","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.5","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":false},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":false},"chat_template_config":{}},"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.5","model_variant_permaslug":"z-ai/glm-4.5","adapter_name":"ZAIAdapter","provider_name":"Z.AI","provider_info":{"name":"Z.AI","displayName":"Z.ai","slug":"z-ai","baseUrl":"https://api.z.ai/api/paas/v4","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"ZAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://z.ai/model-api&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Z.ai","provider_slug":"z-ai/fp8","provider_model_id":"glm-4.5","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":98304,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://chat.z.ai/legal-agreement/terms-of-service","privacyPolicyURL":"https://chat.z.ai/legal-agreement/privacy-policy"},"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":6e-7,"openai:completion_tokens":0.0000022,"openai:cached_prompt_tokens":1.1e-7},"pricing_version_id":"e593176f-82ab-4968-9998-36e823be735b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":false},"supported_parameters":{"response_format":true,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":"2026-12-31T16:00:00.000Z","allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-25T19:21:11.287Z","status":0}},{"slug":"z-ai/glm-4.5-air","hf_slug":"zai-org/GLM-4.5-Air","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-25T19:20:58.066Z","hf_updated_at":null,"name":"Z.ai: GLM 4.5 Air","short_name":"GLM 4.5 Air","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a \"thinking mode\" for advanced reasoning and tool use, and a \"non-thinking mode\" for real-time interaction. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.5-air","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"90fc9bb3-01bb-419f-bb58-dea60a80d201","name":"Novita | z-ai/glm-4.5-air","context_length":131072,"model":{"slug":"z-ai/glm-4.5-air","hf_slug":"zai-org/GLM-4.5-Air","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-25T19:20:58.066206+00:00","hf_updated_at":null,"name":"Z.ai: GLM 4.5 Air","short_name":"GLM 4.5 Air","author":"z-ai","author_display_name":"Z.ai","author_icon_uri":null,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a \"thinking mode\" for advanced reasoning and tool use, and a \"non-thinking mode\" for real-time interaction. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"z-ai/glm-4.5-air","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.75,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"z-ai/glm-4.5-air","model_variant_permaslug":"z-ai/glm-4.5-air","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/bf16","provider_model_id":"zai-org/glm-4.5-air","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":98304,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"excluded_parameters":["response_format"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000013","completion":"0.00000085","input_cache_read":"0.000000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000013","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000013","openai:completion_tokens":"0.00000085","openai:cached_prompt_tokens":"0.000000025"},"pricing_version_id":"7d6a6bc1-e820-4865-8e9d-2ac8c862fb7b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"reasoning_return_mechanism":"reasoning-content","supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":false},"is_mandatory_reasoning":false},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-20T11:57:21.172Z","status":0}},{"slug":"qwen/qwen3-235b-a22b-thinking-2507","hf_slug":"Qwen/Qwen3-235B-A22B-Thinking-2507","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-25T13:19:17.179Z","hf_updated_at":null,"name":"Qwen: Qwen3 235B A22B Thinking 2507","short_name":"Qwen3 235B A22B Thinking 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This \"thinking-only\" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.\n\nThe model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-235b-a22b-thinking-2507","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f246192a-ff8f-4b6c-b2ac-62b3bd24c455","name":"Alibaba | qwen/qwen3-235b-a22b-thinking-2507","context_length":131072,"model":{"slug":"qwen/qwen3-235b-a22b-thinking-2507","hf_slug":"Qwen/Qwen3-235B-A22B-Thinking-2507","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-25T13:19:17.179049+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 235B A22B Thinking 2507","short_name":"Qwen3 235B A22B Thinking 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This \"thinking-only\" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.\n\nThe model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-235b-a22b-thinking-2507","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-235b-a22b-thinking-2507","model_variant_permaslug":"qwen/qwen3-235b-a22b-thinking-2507","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-235b-a22b-thinking-2507","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000023","completion":"0.0000023","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000023","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000023","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000023","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000023","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.00000023","alibaba:completion_tokens":"0.0000023"},"pricing_version_id":"bf73646c-8994-455c-9870-1139fca084dd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:17:10.503Z","status":0}},{"slug":"qwen/qwen3-coder","hf_slug":"Qwen/Qwen3-Coder-480B-A35B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-23T00:29:06.000Z","hf_updated_at":null,"name":"Qwen: Qwen3 Coder 480B A35B","short_name":"Qwen3 Coder 480B A35B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).\n\nPricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-480b-a35b-07-25","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"803d4906-0d0b-49b6-8705-7ae0a4d45217","name":"Google | qwen/qwen3-coder-480b-a35b-07-25","context_length":262144,"model":{"slug":"qwen/qwen3-coder","hf_slug":"Qwen/Qwen3-Coder-480B-A35B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-23T00:29:06+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 Coder 480B A35B","short_name":"Qwen3 Coder 480B A35B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).\n\nPricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-coder-480b-a35b-07-25","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-coder","model_variant_permaslug":"qwen/qwen3-coder-480b-a35b-07-25","adapter_name":"VertexOpenAIAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexOpenAIAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/us-south1","provider_model_id":"qwen/qwen3-coder-480b-a35b-instruct-maas","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000022","completion":"0.0000018","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000018","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000018","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000022","openai:completion_tokens":"0.0000018"},"pricing_version_id":"cc825bb2-dbf6-4c67-9394-382d7c78fc2c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":80,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"us-south1","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-09-07T20:26:32.649Z","status":0}},{"slug":"bytedance/ui-tars-1.5-7b","hf_slug":"ByteDance-Seed/UI-TARS-1.5-7B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-22T17:24:16.947Z","hf_updated_at":null,"name":"ByteDance: UI-TARS 7B ","short_name":"UI-TARS 7B ","author":"bytedance","author_display_name":"bytedance","author_icon_uri":null,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces.\n\nThis model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.","model_version_group_id":null,"context_length":128000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance/ui-tars-1.5-7b","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"22a474a1-cb4e-42d2-b19a-c1be103f5abd","name":"Parasail | bytedance/ui-tars-1.5-7b","context_length":128000,"model":{"slug":"bytedance/ui-tars-1.5-7b","hf_slug":"ByteDance-Seed/UI-TARS-1.5-7B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-22T17:24:16.94785+00:00","hf_updated_at":null,"name":"ByteDance: UI-TARS 7B ","short_name":"UI-TARS 7B ","author":"bytedance","author_display_name":"bytedance","author_icon_uri":null,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces.\n\nThis model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.","model_version_group_id":null,"context_length":128000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"bytedance/ui-tars-1.5-7b","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"bytedance/ui-tars-1.5-7b","model_variant_permaslug":"bytedance/ui-tars-1.5-7b","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-ui-tars-1p5-7b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":2048,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.0000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000002","openai:cached_prompt_tokens":"0.0000001"},"pricing_version_id":"6fa87ba2-e4e2-4dbf-99c0-14c8c73bbb5e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-22T17:26:09.925Z","status":0}},{"slug":"google/gemini-2.5-flash-lite","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-22T16:04:36.283Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash Lite (batch)","short_name":"Gemini 2.5 Flash Lite (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash-lite","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"392c012a-f29d-4745-99b7-adbc44202965","name":"Google | google/gemini-2.5-flash-lite:batch","context_length":1048576,"model":{"slug":"google/gemini-2.5-flash-lite","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-22T16:04:36.283638+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash Lite","short_name":"Gemini 2.5 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash-lite","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-flash-lite:batch","model_variant_permaslug":"google/gemini-2.5-flash-lite:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (EU)","slug":"google-vertex/eu","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex (EU)","provider_slug":"google-vertex/eu","provider_model_id":"gemini-2.5-flash-lite","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65535,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000005","completion":"0.0000002","image":"0.00000005","audio":"0.00000015","input_audio_cache":"0.00000003","input_cache_read":"0.00000001","web_search":"0.014","internal_reasoning":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":5e-8,"gemini:reasoning_tokens":2e-7,"gemini:cache_read_tokens":1e-8,"gemini:completion_tokens":2e-7,"gemini:text_input_tokens":5e-8,"gemini:audio_input_tokens":1.5e-7,"gemini:image_input_tokens":5e-8,"gemini:video_input_tokens":5e-8,"gemini:cache_read_text_tokens":1e-8,"gemini:cache_read_audio_tokens":3e-8,"gemini:cache_read_image_tokens":1e-8,"gemini:cache_read_video_tokens":1e-8,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"1adf6768-6b9a-4fe6-b05f-0262ad2d58b7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_native_web_search":false,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"europe-west4","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:12:07.372Z","status":0}},{"slug":"google/gemini-2.5-flash-lite","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-22T16:04:36.283Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash Lite","short_name":"Gemini 2.5 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash-lite","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6b2ea9bc-3a79-441d-97a4-9b7d33210122","name":"Google | google/gemini-2.5-flash-lite","context_length":1048576,"model":{"slug":"google/gemini-2.5-flash-lite","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-22T16:04:36.283638+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash Lite","short_name":"Gemini 2.5 Flash Lite","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash-lite","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-flash-lite","model_variant_permaslug":"google/gemini-2.5-flash-lite","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (EU)","slug":"google-vertex/eu","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex (EU)","provider_slug":"google-vertex/eu","provider_model_id":"gemini-2.5-flash-lite","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65535,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","audio":"0.0000003","input_audio_cache":"0.00000003","input_cache_read":"0.00000001","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.0000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":1e-7,"gemini:reasoning_tokens":4e-7,"gemini:cache_read_tokens":1e-8,"gemini:completion_tokens":4e-7,"gemini:text_input_tokens":1e-7,"gemini:audio_input_tokens":3e-7,"gemini:image_input_tokens":1e-7,"gemini:video_input_tokens":1e-7,"gemini:cache_read_text_tokens":1e-8,"gemini:cache_read_audio_tokens":3e-8,"gemini:cache_read_image_tokens":1e-8,"gemini:cache_read_video_tokens":1e-8,"gemini:cache_write_storage_hours":0.000001,"gemini:cache_read_tokens_high_context":3e-8,"gemini:cache_read_text_tokens_high_context":3e-8,"gemini:cache_read_audio_tokens_high_context":6e-8,"gemini:cache_read_image_tokens_high_context":3e-8,"gemini:cache_read_video_tokens_high_context":3e-8,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"a993e279-3605-400d-a546-60168869ffa0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_base64_video_input":true,"supports_video_urls":false,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"europe-west4","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-04-28T20:44:52.471Z","status":0}},{"slug":"qwen/qwen3-235b-a22b-2507","hf_slug":"Qwen/Qwen3-235B-A22B-Instruct-2507","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-21T17:39:15.880Z","hf_updated_at":null,"name":"Qwen: Qwen3 235B A22B Instruct 2507","short_name":"Qwen3 235B A22B Instruct 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement \"thinking mode\" (<think> blocks).\n\nCompared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-235b-a22b-07-25","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7f8598e4-091b-424e-a9c2-158532af1537","name":"GMICloud | qwen/qwen3-235b-a22b-07-25","context_length":262144,"model":{"slug":"qwen/qwen3-235b-a22b-2507","hf_slug":"Qwen/Qwen3-235B-A22B-Instruct-2507","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-21T17:39:15.880992+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 235B A22B Instruct 2507","short_name":"Qwen3 235B A22B Instruct 2507","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement \"thinking mode\" (<think> blocks).\n\nCompared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-235b-a22b-07-25","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-235b-a22b-2507","model_variant_permaslug":"qwen/qwen3-235b-a22b-07-25","adapter_name":"GMICloudAdapter","provider_name":"GMICloud","provider_info":{"name":"GMICloud","displayName":"GMICloud","slug":"gmicloud","baseUrl":"https://api.gmi-serving.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"GMICloudAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://gmicloud.ai/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"GMICloud","provider_slug":"gmicloud/fp8","provider_model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507-FP8","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.gmicloud.ai/terms-and-conditions","privacyPolicyURL":"https://docs.gmicloud.ai/privacy"},"pricing":{"prompt":"0.0000000875","completion":"0.00000035","input_cache_read":"0.0000000175","discount":0.75,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000000875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000175","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000000875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000000175","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000035","openai:completion_tokens":"0.0000014","openai:cached_prompt_tokens":"0.00000007"},"pricing_version_id":"2cb96e92-fdb1-444a-8e44-8f85b001f293","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-19T14:13:11.602Z","status":0}},{"slug":"moonshotai/kimi-k2","hf_slug":"moonshotai/Kimi-K2-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-11T19:47:32.565Z","hf_updated_at":null,"name":"MoonshotAI: Kimi K2 0711","short_name":"Kimi K2 0711","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f5265deb-6c78-49da-97e8-0f0b3dae6c5b","name":"Novita | moonshotai/kimi-k2","context_length":131072,"model":{"slug":"moonshotai/kimi-k2","hf_slug":"moonshotai/Kimi-K2-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-11T19:47:32.565514+00:00","hf_updated_at":null,"name":"MoonshotAI: Kimi K2 0711","short_name":"Kimi K2 0711","author":"moonshotai","author_display_name":"moonshotai","author_icon_uri":null,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"moonshotai/kimi-k2","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"moonshotai/kimi-k2","model_variant_permaslug":"moonshotai/kimi-k2","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"moonshotai/kimi-k2-instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100352,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000057","completion":"0.0000023","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000057","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000023","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000057","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000023","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000057","openai:completion_tokens":"0.0000023"},"pricing_version_id":"b97bc411-245b-40f7-ba89-745da17920ed","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":50,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-11T20:34:34.927Z","status":0}},{"slug":"cognitivecomputations/dolphin-mistral-24b-venice-edition","hf_slug":"cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-09T21:02:46.328Z","hf_updated_at":null,"name":"Venice: Uncensored","short_name":"Uncensored","author":"venice","author_display_name":"venice","author_icon_uri":null,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving user control over alignment, system prompts, and behavior. Intended for advanced and unrestricted use cases, Venice Uncensored emphasizes steerability and transparent behavior, removing default safety and alignment layers typically found in mainstream assistant models.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"venice/uncensored","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7e8cc035-ab66-4fe4-a484-657a83d1be50","name":"Venice | venice/uncensored","context_length":128000,"model":{"slug":"cognitivecomputations/dolphin-mistral-24b-venice-edition","hf_slug":"cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-09T21:02:46.328189+00:00","hf_updated_at":null,"name":"Venice: Uncensored","short_name":"Uncensored","author":"venice","author_display_name":"venice","author_icon_uri":null,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving user control over alignment, system prompts, and behavior. Intended for advanced and unrestricted use cases, Venice Uncensored emphasizes steerability and transparent behavior, removing default safety and alignment layers typically found in mainstream assistant models.","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"venice/uncensored","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"cognitivecomputations/dolphin-mistral-24b-venice-edition","model_variant_permaslug":"venice/uncensored","adapter_name":"VeniceAdapter","provider_name":"Venice","provider_info":{"name":"Venice","displayName":"Venice","slug":"venice","baseUrl":"https://api.venice.ai/api/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://venice.ai/legal/tos","privacyPolicyURL":"https://venice.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"VeniceAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://venice.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Venice","provider_slug":"venice/fp16","provider_model_id":"venice-uncensored-1-2","quantization":"fp16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://venice.ai/legal/tos","privacyPolicyURL":"https://venice.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.0000009","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000002","openai:completion_tokens":"0.0000009"},"pricing_version_id":"a02c955a-1a88-44fb-8a69-4987b1a10904","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-25T20:56:55.583Z","status":0}},{"slug":"tencent/hunyuan-a13b-instruct","hf_slug":"tencent/Hunyuan-A13B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-07-08T15:14:24.006Z","hf_updated_at":null,"name":"Tencent: Hunyuan A13B Instruct","short_name":"Hunyuan A13B Instruct","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hunyuan-a13b-instruct","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"519e0e1e-7254-41de-abe1-2e0ebf026ce9","name":"SiliconFlow | tencent/hunyuan-a13b-instruct","context_length":131072,"model":{"slug":"tencent/hunyuan-a13b-instruct","hf_slug":"tencent/Hunyuan-A13B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-07-08T15:14:24.006774+00:00","hf_updated_at":null,"name":"Tencent: Hunyuan A13B Instruct","short_name":"Hunyuan A13B Instruct","author":"tencent","author_display_name":"tencent","author_icon_uri":null,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"tencent/hunyuan-a13b-instruct","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"tencent/hunyuan-a13b-instruct","model_variant_permaslug":"tencent/hunyuan-a13b-instruct","adapter_name":"SiliconFlowAdapter","provider_name":"SiliconFlow","provider_info":{"name":"SiliconFlow","displayName":"SiliconFlow","slug":"siliconflow","baseUrl":"https://api.siliconflow.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.siliconflow.com/en/legals/terms-of-service","privacyPolicyURL":"https://docs.siliconflow.com/en/legals/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"SiliconFlowAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"/images/icons/SiliconFlow.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"SiliconFlow","provider_slug":"siliconflow/fp8","provider_model_id":"tencent/Hunyuan-A13B-Instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.siliconflow.com/en/legals/terms-of-service","privacyPolicyURL":"https://docs.siliconflow.com/en/legals/privacy-policy"},"pricing":{"prompt":"0.00000014","completion":"0.00000057","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000057","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000057","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000014","openai:completion_tokens":"0.00000057"},"pricing_version_id":"f5fd1260-7cec-469f-aca9-7bc79fd94626","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-28T20:44:06.437Z","status":0}},{"slug":"morph/morph-v3-large","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-07-07T17:54:18.685Z","hf_updated_at":null,"name":"Morph: Morph V3 Large","short_name":"Morph V3 Large","author":"morph","author_display_name":"morph","author_icon_uri":null,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)","model_version_group_id":null,"context_length":262144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"morph/morph-v3-large","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"fast_apply","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"df8da1e4-a390-4020-a25f-d12d77f65b22","name":"Morph | morph/morph-v3-large","context_length":262144,"model":{"slug":"morph/morph-v3-large","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-07-07T17:54:18.685519+00:00","hf_updated_at":null,"name":"Morph: Morph V3 Large","short_name":"Morph V3 Large","author":"morph","author_display_name":"morph","author_icon_uri":null,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)","model_version_group_id":null,"context_length":81920,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"morph/morph-v3-large","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"fast_apply","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"morph/morph-v3-large","model_variant_permaslug":"morph/morph-v3-large","adapter_name":"MorphFastApplyAdapter","provider_name":"Morph","provider_info":{"name":"Morph","displayName":"Morph","slug":"morph","baseUrl":"https://api.morphllm.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.morphllm.com/privacy/tos","privacyPolicyURL":"https://morphllm.com/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"MorphFastApplyAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://morphllm.com&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Morph","provider_slug":"morph/fp8","provider_model_id":"morph-v3-large","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.morphllm.com/privacy/tos","privacyPolicyURL":"https://morphllm.com/privacy"},"pricing":{"prompt":"0.0000009","completion":"0.0000019","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000019","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000019","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000009","openai:completion_tokens":"0.0000019"},"pricing_version_id":"0e4be404-33d2-4c64-86fa-43ef54f4a58e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":false,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-07T17:56:01.840Z","status":0}},{"slug":"morph/morph-v3-fast","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-07-07T17:40:02.233Z","hf_updated_at":null,"name":"Morph: Morph V3 Fast","short_name":"Morph V3 Fast","author":"morph","author_display_name":"morph","author_icon_uri":null,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)","model_version_group_id":null,"context_length":81920,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"morph/morph-v3-fast","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"fast_apply","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f636f582-98c3-45dd-b468-0b9b0973b1f6","name":"Morph | morph/morph-v3-fast","context_length":81920,"model":{"slug":"morph/morph-v3-fast","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-07-07T17:40:02.233313+00:00","hf_updated_at":null,"name":"Morph: Morph V3 Fast","short_name":"Morph V3 Fast","author":"morph","author_display_name":"morph","author_icon_uri":null,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)","model_version_group_id":null,"context_length":81920,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"morph/morph-v3-fast","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":"fast_apply","previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"morph/morph-v3-fast","model_variant_permaslug":"morph/morph-v3-fast","adapter_name":"MorphFastApplyAdapter","provider_name":"Morph","provider_info":{"name":"Morph","displayName":"Morph Fast","slug":"morph","baseUrl":"https://api.morphllm.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.morphllm.com/privacy/tos","privacyPolicyURL":"https://morphllm.com/privacy","requiresUserIDs":false},"headquarters":"US","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"MorphFastApplyAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://morphllm.com&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Morph Fast","provider_slug":"morph","provider_model_id":"morph-v3-fast","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":38000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.morphllm.com/privacy/tos","privacyPolicyURL":"https://morphllm.com/privacy"},"pricing":{"prompt":"0.0000008","completion":"0.0000012","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000008","openai:completion_tokens":"0.0000012"},"pricing_version_id":"08aa7ccc-24fd-4d84-bd81-ed67161d0614","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":false,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_multipart":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":{"supported_sizes":null,"supported_frame_images":null,"generate_audio":null,"seed":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-07T17:50:47.258Z","status":0}},{"slug":"baidu/ernie-4.5-vl-424b-a47b","hf_slug":"baidu/ERNIE-4.5-VL-424B-A47B-PT","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-06-30T16:28:23.022Z","hf_updated_at":null,"name":"Baidu: ERNIE 4.5 VL 424B A47B ","short_name":"ERNIE 4.5 VL 424B A47B ","author":"baidu","author_display_name":"baidu","author_icon_uri":null,"description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.","model_version_group_id":null,"context_length":123000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"baidu/ernie-4.5-vl-424b-a47b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1fe59382-263d-4107-a768-d7d2007bd3b6","name":"Novita | baidu/ernie-4.5-vl-424b-a47b","context_length":123000,"model":{"slug":"baidu/ernie-4.5-vl-424b-a47b","hf_slug":"baidu/ERNIE-4.5-VL-424B-A47B-PT","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-06-30T16:28:23.022047+00:00","hf_updated_at":null,"name":"Baidu: ERNIE 4.5 VL 424B A47B ","short_name":"ERNIE 4.5 VL 424B A47B ","author":"baidu","author_display_name":"baidu","author_icon_uri":null,"description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"baidu/ernie-4.5-vl-424b-a47b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"baidu/ernie-4.5-vl-424b-a47b","model_variant_permaslug":"baidu/ernie-4.5-vl-424b-a47b","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp16","provider_model_id":"baidu/ernie-4.5-vl-424b-a47b","quantization":"fp16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000042","completion":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000042","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000042","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000042","openai:completion_tokens":"0.00000125"},"pricing_version_id":"e58a9bae-ceb6-44a8-be53-c128c4e5511c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":false,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-08-14T18:56:13.455Z","status":0}},{"slug":"mistralai/mistral-small-3.2-24b-instruct","hf_slug":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-06-20T18:10:16.960Z","hf_updated_at":null,"name":"Mistral: Mistral Small 3.2 24B","short_name":"Mistral Small 3.2 24B","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\n\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).","model_version_group_id":null,"context_length":131072,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-3.2-24b-instruct-2506","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0ebc91cd-74bd-44ab-9c9a-c1f17d19f128","name":"DeepInfra | mistralai/mistral-small-3.2-24b-instruct-2506","context_length":128000,"model":{"slug":"mistralai/mistral-small-3.2-24b-instruct","hf_slug":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-06-20T18:10:16.960494+00:00","hf_updated_at":null,"name":"Mistral: Mistral Small 3.2 24B","short_name":"Mistral Small 3.2 24B","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\n\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).","model_version_group_id":null,"context_length":128000,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-3.2-24b-instruct-2506","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-small-3.2-24b-instruct","model_variant_permaslug":"mistralai/mistral-small-3.2-24b-instruct-2506","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.000000075","completion":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000075","openai:completion_tokens":"0.0000002"},"pricing_version_id":"d9d28093-2a0d-4b7e-8060-98be5d27d410","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-24T18:32:23.628Z","status":0}},{"slug":"minimax/minimax-m1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-06-17T22:46:54.257Z","hf_updated_at":null,"name":"MiniMax: MiniMax M1","short_name":"MiniMax M1","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks.\n\nTrained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"dd5bc8d5-68a7-48a7-a680-db37579d5c14","name":"Minimax | minimax/minimax-m1","context_length":1000000,"model":{"slug":"minimax/minimax-m1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-06-17T22:46:54.257159+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax M1","short_name":"MiniMax M1","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks.\n\nTrained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-m1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-m1","model_variant_permaslug":"minimax/minimax-m1","adapter_name":"MinimaxAdapter","provider_name":"Minimax","provider_info":{"name":"Minimax","displayName":"MiniMax","slug":"minimax","baseUrl":"https://api.minimaxi.chat/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MinimaxAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://minimaxi.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"MiniMax","provider_slug":"minimax","provider_model_id":"MiniMax-M1","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":40000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy"},"pricing":{"prompt":"0.0000004","completion":"0.0000022","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000022","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000004","openai:completion_tokens":"0.0000022"},"pricing_version_id":"d2ebea9d-b5f6-47a1-b558-f6b325f0a9cc","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":false,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-17T22:48:15.242Z","status":0}},{"slug":"google/gemini-2.5-flash","hf_slug":"","updated_at":"2026-05-26T20:25:56.298Z","created_at":"2025-06-17T15:01:28.103Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash (batch)","short_name":"Gemini 2.5 Flash (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).","model_version_group_id":null,"context_length":1048576,"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-vertex","google-vertex/eu","google-ai-studio"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"73dc8ca7-10c2-4e6f-9766-83c24dbf657a","name":"Google | google/gemini-2.5-flash:batch","context_length":1048576,"model":{"slug":"google/gemini-2.5-flash","hf_slug":"","updated_at":"2026-05-26T20:25:56.298412+00:00","created_at":"2025-06-17T15:01:28.103313+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash","short_name":"Gemini 2.5 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).","model_version_group_id":null,"context_length":1048576,"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-vertex","google-vertex/eu","google-ai-studio"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-flash:batch","model_variant_permaslug":"google/gemini-2.5-flash:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (Global)","slug":"google-vertex/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex (Global)","provider_slug":"google-vertex/global","provider_model_id":"gemini-2.5-flash","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65535,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","audio":"0.0000005","input_audio_cache":"0.0000001","input_cache_read":"0.00000003","web_search":"0.014","internal_reasoning":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":1.5e-7,"gemini:reasoning_tokens":0.00000125,"gemini:cache_read_tokens":3e-8,"gemini:completion_tokens":0.00000125,"gemini:text_input_tokens":1.5e-7,"gemini:audio_input_tokens":5e-7,"gemini:image_input_tokens":1.5e-7,"gemini:video_input_tokens":1.5e-7,"gemini:cache_read_text_tokens":3e-8,"gemini:cache_read_audio_tokens":1e-7,"gemini:cache_read_image_tokens":3e-8,"gemini:cache_read_video_tokens":3e-8,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"300bd2c0-0093-4a2a-aef1-3ea8406f6c4c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_native_web_search":false,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:12:06.198Z","status":0}},{"slug":"google/gemini-2.5-flash","hf_slug":"","updated_at":"2026-05-26T20:25:56.298Z","created_at":"2025-06-17T15:01:28.103Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash","short_name":"Gemini 2.5 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).","model_version_group_id":null,"context_length":1048576,"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-vertex","google-vertex/eu","google-ai-studio"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":{"id":"b9b095f0-6448-46bb-8e4c-0111ba2bf1b0","name":"Google | google/gemini-2.5-flash","context_length":1048576,"model":{"slug":"google/gemini-2.5-flash","hf_slug":"","updated_at":"2026-05-26T20:25:56.298412+00:00","created_at":"2025-06-17T15:01:28.103313+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Flash","short_name":"Gemini 2.5 Flash","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).","model_version_group_id":null,"context_length":1048576,"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-flash","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["google-vertex/global","google-vertex","google-vertex/eu","google-ai-studio"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-flash","model_variant_permaslug":"google/gemini-2.5-flash","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (Global)","slug":"google-vertex/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex (Global)","provider_slug":"google-vertex/global","provider_model_id":"gemini-2.5-flash","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65535,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","web_search":"0.014","internal_reasoning":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"8.333333333333334e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio Cache","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"gemini:prompt_tokens":3e-7,"gemini:reasoning_tokens":0.0000025,"gemini:cache_read_tokens":3e-8,"gemini:completion_tokens":0.0000025,"gemini:text_input_tokens":3e-7,"gemini:audio_input_tokens":0.000001,"gemini:image_input_tokens":3e-7,"gemini:video_input_tokens":3e-7,"gemini:cache_read_text_tokens":3e-8,"gemini:cache_read_audio_tokens":1e-7,"gemini:cache_read_image_tokens":3e-8,"gemini:cache_read_video_tokens":3e-8,"gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":0.000001,"gemini:cache_read_tokens_high_context":1e-7,"gemini:cache_read_text_tokens_high_context":1e-7,"gemini:cache_read_audio_tokens_high_context":2e-7,"gemini:cache_read_image_tokens_high_context":1e-7,"gemini:cache_read_video_tokens_high_context":1e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"ab3df835-fc2c-44b3-95e4-435381459579","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_base64_video_input":true,"supports_video_urls":false,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-18T23:26:15.655Z","status":0}},{"slug":"google/gemini-2.5-pro","hf_slug":"","updated_at":"2026-04-27T03:32:06.603Z","created_at":"2025-06-17T14:12:24.000Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro (batch)","short_name":"Gemini 2.5 Pro (batch)","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b135c1e4-1ee2-41c7-beb2-a13cd023f1e5","name":"Google | google/gemini-2.5-pro:batch","context_length":1048576,"model":{"slug":"google/gemini-2.5-pro","hf_slug":"","updated_at":"2026-04-27T03:32:06.603628+00:00","created_at":"2025-06-17T14:12:24+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro","short_name":"Gemini 2.5 Pro","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-pro:batch","model_variant_permaslug":"google/gemini-2.5-pro:batch","adapter_name":"VertexGeminiBatchAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (Global)","slug":"google-vertex/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"VertexGeminiBatchAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex (Global)","provider_slug":"google-vertex/global","provider_model_id":"gemini-2.5-pro","quantization":"unknown","variant":"batch","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","audio":"0.000000625","input_audio_cache":"0.000000125","input_cache_read":"0.000000125","web_search":"0.014","internal_reasoning":"0.000005","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.00000125","completion":"0.0000075","audio":"0.00000125","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"6.25e-7"},{"sku_label":">200K","price":"0.00000125"}]},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000005"},{"sku_label":">200K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Image Input","price":"6.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"6.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"6.25e-7"},{"sku_label":">200K","price":"0.00000125"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"6.25e-7"},{"sku_label":">200K","price":"0.00000125"}]},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000005"},{"sku_label":">200K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Image Input","price":"6.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"6.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"6.25e-7"},{"sku_label":">200K","price":"0.00000125"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}],"pricing_json":{"gemini:prompt_tokens":6.25e-7,"gemini:reasoning_tokens":0.000005,"gemini:cache_read_tokens":1.25e-7,"gemini:completion_tokens":0.000005,"gemini:text_input_tokens":6.25e-7,"gemini:audio_input_tokens":6.25e-7,"gemini:image_input_tokens":6.25e-7,"gemini:video_input_tokens":6.25e-7,"gemini:cache_read_text_tokens":1.25e-7,"gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":1.25e-7,"gemini:cache_read_image_tokens":1.25e-7,"gemini:cache_read_video_tokens":1.25e-7,"gemini:prompt_tokens_high_context":0.00000125,"gemini:reasoning_tokens_high_context":0.0000075,"gemini:cache_read_tokens_high_context":2.5e-7,"gemini:completion_tokens_high_context":0.0000075,"gemini:cache_read_text_tokens_high_context":2.5e-7,"gemini:cache_read_audio_tokens_high_context":2.5e-7,"gemini:cache_read_image_tokens_high_context":2.5e-7,"gemini:cache_read_video_tokens_high_context":2.5e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"71d86315-dbe4-4883-86ea-9610aaa6cdac","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":false,"supports_native_web_search":false,"supports_base64_video_input":false,"supports_video_urls":false,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-17T19:12:04.934Z","status":0}},{"slug":"google/gemini-2.5-pro","hf_slug":"","updated_at":"2026-04-27T03:32:06.603Z","created_at":"2025-06-17T14:12:24.000Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro","short_name":"Gemini 2.5 Pro","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"43106252-bd69-498f-84f5-1fde678783f7","name":"Google | google/gemini-2.5-pro","context_length":1048576,"model":{"slug":"google/gemini-2.5-pro","hf_slug":"","updated_at":"2026-04-27T03:32:06.603628+00:00","created_at":"2025-06-17T14:12:24+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro","short_name":"Gemini 2.5 Pro","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":null,"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-pro","model_variant_permaslug":"google/gemini-2.5-pro","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (Global)","slug":"google-vertex/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex (Global)","provider_slug":"google-vertex/global","provider_model_id":"gemini-2.5-pro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.00001","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00001"},{"sku_label":">200K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00001"},{"sku_label":">200K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}],"pricing_json":{"gemini:prompt_tokens":0.00000125,"gemini:reasoning_tokens":0.00001,"gemini:cache_read_tokens":1.25e-7,"gemini:completion_tokens":0.00001,"gemini:text_input_tokens":0.00000125,"gemini:audio_input_tokens":0.00000125,"gemini:image_input_tokens":0.00000125,"gemini:video_input_tokens":0.00000125,"gemini:flex_tier_multiplier":"0.5","gemini:cache_read_text_tokens":1.25e-7,"gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":1.25e-7,"gemini:cache_read_image_tokens":1.25e-7,"gemini:cache_read_video_tokens":1.25e-7,"gemini:priority_tier_multiplier":"1.8","gemini:cache_write_storage_hours":0.0000045,"gemini:prompt_tokens_high_context":0.0000025,"gemini:reasoning_tokens_high_context":0.000015,"gemini:cache_read_tokens_high_context":2.5e-7,"gemini:completion_tokens_high_context":0.000015,"gemini:cache_read_text_tokens_high_context":2.5e-7,"gemini:cache_read_audio_tokens_high_context":2.5e-7,"gemini:cache_read_image_tokens_high_context":2.5e-7,"gemini:cache_read_video_tokens_high_context":2.5e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"43a124d8-6343-4b27-87f7-72759d335101","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":200,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_base64_video_input":true,"supports_video_urls":false,"supports_input_audio":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-02T21:38:14.935Z","status":0}},{"slug":"openai/o3-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-06-10T23:32:32.266Z","hf_updated_at":null,"name":"OpenAI: o3 Pro (batch)","short_name":"o3 Pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-pro-2025-06-10","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a876cd96-8f4d-4e5d-a3b5-c756ddea2578","name":"OpenAI | openai/o3-pro-2025-06-10:batch","context_length":200000,"model":{"slug":"openai/o3-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-06-10T23:32:32.266087+00:00","hf_updated_at":null,"name":"OpenAI: o3 Pro","short_name":"o3 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-pro-2025-06-10","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3-pro:batch","model_variant_permaslug":"openai/o3-pro-2025-06-10:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-pro-2025-06-10","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00004","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.000000e-5","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"4.000000e-5"},"pricing_version_id":"feff34ab-c402-4c94-bb56-4a030b6ed15c","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:33.498Z","status":0}},{"slug":"openai/o3-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-06-10T23:32:32.266Z","hf_updated_at":null,"name":"OpenAI: o3 Pro","short_name":"o3 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-pro-2025-06-10","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b8222376-66ee-4b89-a7c9-e627ba35db79","name":"OpenAI | openai/o3-pro-2025-06-10","context_length":200000,"model":{"slug":"openai/o3-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-06-10T23:32:32.266087+00:00","hf_updated_at":null,"name":"OpenAI: o3 Pro","short_name":"o3 Pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-pro-2025-06-10","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3-pro","model_variant_permaslug":"openai/o3-pro-2025-06-10","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-pro-2025-06-10","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00002","completion":"0.00008","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.00002,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.00008},"pricing_version_id":"1f6bd1f8-e039-4a39-818c-0c098678cc9b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-10T23:35:38.715Z","status":0}},{"slug":"google/gemini-2.5-pro-preview","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-06-05T15:27:37.538Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro Preview 06-05","short_name":"Gemini 2.5 Pro Preview 06-05","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.\n","model_version_group_id":null,"context_length":1048576,"input_modalities":["file","image","text","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro-preview-06-05","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"018040ae-9cda-43cd-8813-d8ca83f6c7ed","name":"Google | google/gemini-2.5-pro-preview-06-05","context_length":1048576,"model":{"slug":"google/gemini-2.5-pro-preview","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-06-05T15:27:37.538116+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro Preview 06-05","short_name":"Gemini 2.5 Pro Preview 06-05","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.\n","model_version_group_id":null,"context_length":1048576,"input_modalities":["file","image","text","audio"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro-preview-06-05","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-pro-preview","model_variant_permaslug":"google/gemini-2.5-pro-preview-06-05","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex/global","provider_model_id":"gemini-2.5-pro-preview-06-05","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.00001","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00001"},{"sku_label":">200K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00001"},{"sku_label":">200K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}],"pricing_json":{"gemini:prompt_tokens":0.00000125,"gemini:reasoning_tokens":0.00001,"gemini:cache_read_tokens":1.25e-7,"gemini:completion_tokens":0.00001,"gemini:text_input_tokens":0.00000125,"gemini:audio_input_tokens":0.00000125,"gemini:image_input_tokens":0.00000125,"gemini:video_input_tokens":0.00000125,"gemini:cache_read_text_tokens":1.25e-7,"gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":1.25e-7,"gemini:cache_read_image_tokens":1.25e-7,"gemini:cache_read_video_tokens":1.25e-7,"gemini:cache_write_storage_hours":0.0000045,"gemini:prompt_tokens_high_context":0.0000025,"gemini:reasoning_tokens_high_context":0.000015,"gemini:cache_read_tokens_high_context":2.5e-7,"gemini:completion_tokens_high_context":0.000015,"gemini:cache_read_text_tokens_high_context":2.5e-7,"gemini:cache_read_audio_tokens_high_context":2.5e-7,"gemini:cache_read_image_tokens_high_context":2.5e-7,"gemini:cache_read_video_tokens_high_context":2.5e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"d7a51386-558d-43c2-bab2-de8273d8cee6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-05T15:28:11.248Z","status":0}},{"slug":"deepseek/deepseek-r1-0528","hf_slug":"deepseek-ai/DeepSeek-R1-0528","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-05-28T17:59:30.833Z","hf_updated_at":null,"name":"DeepSeek: R1 0528","short_name":"R1 0528","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nFully open-source model.","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-r1-0528","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0f47837d-9d06-4c68-a93c-29b0c7cd9027","name":"DeepInfra | deepseek/deepseek-r1-0528","context_length":163840,"model":{"slug":"deepseek/deepseek-r1-0528","hf_slug":"deepseek-ai/DeepSeek-R1-0528","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-05-28T17:59:30.833128+00:00","hf_updated_at":null,"name":"DeepSeek: R1 0528","short_name":"R1 0528","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nFully open-source model.","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-r1-0528","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-r1-0528","model_variant_permaslug":"deepseek/deepseek-r1-0528","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"deepseek-ai/DeepSeek-R1-0528","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","structured_outputs","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000005","completion":"0.00000215","input_cache_read":"0.00000035","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000215","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000215","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000035","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000005","openai:completion_tokens":"0.00000215","openai:cached_prompt_tokens":"0.00000035"},"pricing_version_id":"04e0df54-8a60-4afe-8627-8a010900a5bf","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-05-28T23:01:22.780Z","status":0}},{"slug":"anthropic/claude-opus-4","hf_slug":"","updated_at":"2026-04-13T15:02:44.845Z","created_at":"2025-05-22T16:27:25.029Z","hf_updated_at":null,"name":"Anthropic: Claude Opus 4","short_name":"Claude Opus 4","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4-opus-20250522","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"02160c8a-a3b3-4958-bbb4-47c83f0376d5","name":"Google | anthropic/claude-4-opus-20250522","context_length":200000,"model":{"slug":"anthropic/claude-opus-4","hf_slug":"","updated_at":"2026-04-13T15:02:44.845601+00:00","created_at":"2025-05-22T16:27:25.029961+00:00","hf_updated_at":null,"name":"Anthropic: Claude Opus 4","short_name":"Claude Opus 4","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4-opus-20250522","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-opus-4","model_variant_permaslug":"anthropic/claude-4-opus-20250522","adapter_name":"InternalStreamGoogleVertexAnthropicAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex","provider_model_id":"claude-opus-4@20250514","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000015","completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","input_cache_write_1h":"0.00003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":"0.00001875","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":0.000015,"anthropic:web_search_calls":0.01,"anthropic:cache_read_tokens":0.0000015,"anthropic:completion_tokens":0.000075,"anthropic:cache_write_1h_tokens":0.00003,"anthropic:cache_write_5m_tokens":0.00001875},"pricing_version_id":"7c84671d-07cc-4e9f-82a6-a85f26689966","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":{"supported_sizes":null},"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-05-22T16:28:02.253Z","status":0}},{"slug":"anthropic/claude-sonnet-4","hf_slug":"","updated_at":"2026-04-11T05:40:18.450Z","created_at":"2025-05-22T16:12:51.381Z","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4","short_name":"Claude Sonnet 4","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)","model_version_group_id":null,"context_length":1000000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4-sonnet-20250522","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3a66dd68-b711-4d75-bbea-56012edd68bb","name":"Google | anthropic/claude-4-sonnet-20250522","context_length":1000000,"model":{"slug":"anthropic/claude-sonnet-4","hf_slug":"","updated_at":"2026-04-11T05:40:18.450777+00:00","created_at":"2025-05-22T16:12:51.381897+00:00","hf_updated_at":null,"name":"Anthropic: Claude Sonnet 4","short_name":"Claude Sonnet 4","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)","model_version_group_id":null,"context_length":1000000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-4-sonnet-20250522","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["amazon-bedrock","google-vertex","anthropic"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-sonnet-4","model_variant_permaslug":"anthropic/claude-4-sonnet-20250522","adapter_name":"InternalStreamGoogleVertexAnthropicAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex (Global)","slug":"google-vertex/global","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Google Vertex (Global)","provider_slug":"google-vertex/global","provider_model_id":"claude-sonnet-4@20250514","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","top_p","temperature","stop","reasoning","include_reasoning","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006","web_search":"0.01","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006","input_cache_write":"0.0000075","input_cache_write_1h":"0.000012"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000003"},{"sku_label":">200K","price":"0.000006"}]},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000015"},{"sku_label":">200K","price":"0.0000225"}]},{"kind":"token","sku_label":"Cache Read","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"3e-7"},{"sku_label":">200K","price":"6e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000375"},{"sku_label":">200K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000003"},{"sku_label":">200K","price":"0.000006"}]},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000015"},{"sku_label":">200K","price":"0.0000225"}]},{"kind":"token","sku_label":"Cache Read","price":"3e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"3e-7"},{"sku_label":">200K","price":"6e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"0.00000375","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000375"},{"sku_label":">200K","price":"0.0000075"}]},{"kind":"token","sku_label":"Cache Write (1h)","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.000006"},{"sku_label":">200K","price":"0.000012"}]}],"pricing_json":{"anthropic:prompt_tokens":0.000003,"anthropic:web_search_calls":0.01,"anthropic:cache_read_tokens":3e-7,"anthropic:completion_tokens":0.000015,"anthropic:cache_write_1h_tokens":0.000006,"anthropic:cache_write_5m_tokens":0.00000375,"anthropic:long_context_threshold":200000,"anthropic:prompt_tokens_long_context":0.000006,"anthropic:cache_read_tokens_long_context":6e-7,"anthropic:completion_tokens_long_context":0.0000225,"anthropic:cache_write_1h_tokens_long_context":0.000012,"anthropic:cache_write_5m_tokens_long_context":0.0000075},"pricing_version_id":"2ad46cf1-4c57-4b65-8d67-94ef93c7be00","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":{"supported_sizes":null},"supported_image_parameters":null,"provider_region":"global","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":25000000,"created_at":"2025-06-18T19:37:15.830Z","status":0}},{"slug":"google/gemma-3n-e4b-it","hf_slug":"google/gemma-3n-E4B-it","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-05-20T21:33:44.157Z","hf_updated_at":null,"name":"Google: Gemma 3n 4B","short_name":"Gemma 3n 4B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements.\n\nThis model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3n-e4b-it","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2fbebc5f-9439-4d6d-af69-0c7aec1c4392","name":"Together | google/gemma-3n-e4b-it","context_length":32768,"model":{"slug":"google/gemma-3n-e4b-it","hf_slug":"google/gemma-3n-E4B-it","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-05-20T21:33:44.157973+00:00","hf_updated_at":null,"name":"Google: Gemma 3n 4B","short_name":"Gemma 3n 4B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements.\n\nThis model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)","model_version_group_id":null,"context_length":32000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3n-e4b-it","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-3n-e4b-it","model_variant_permaslug":"google/gemma-3n-e4b-it","adapter_name":"TogetherAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"google/gemma-3n-E4B-it","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.00000006","completion":"0.00000012","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000006","openai:completion_tokens":"0.00000012"},"pricing_version_id":"49d78dbc-8ae1-49a3-874d-da3598db13d7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-26T17:01:34.638Z","status":0}},{"slug":"mistralai/mistral-medium-3","hf_slug":"","updated_at":"2026-05-14T22:39:41.572Z","created_at":"2025-05-07T14:15:41.980Z","hf_updated_at":null,"name":"Mistral: Mistral Medium 3","short_name":"Mistral Medium 3","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-medium-3","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a61ba147-e35a-4e10-a76a-0c2327f52a94","name":"Mistral | mistralai/mistral-medium-3","context_length":131072,"model":{"slug":"mistralai/mistral-medium-3","hf_slug":"","updated_at":"2026-05-14T22:39:41.572848+00:00","created_at":"2025-05-07T14:15:41.980763+00:00","hf_updated_at":null,"name":"Mistral: Mistral Medium 3","short_name":"Mistral Medium 3","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\n\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-medium-3","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-medium-3","model_variant_permaslug":"mistralai/mistral-medium-3","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral/zdr","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral (ZDR)","provider_slug":"mistral/zdr","provider_model_id":"mistral-medium-2505","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":4e-7,"mistral:completion_tokens":0.000002,"mistral:cached_prompt_tokens":"0.00000004"},"pricing_version_id":"28fe91fc-1672-4376-ac51-1e48ed4d44f6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-18T16:05:08.987Z","status":0}},{"slug":"google/gemini-2.5-pro-preview-05-06","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-05-07T00:41:53.000Z","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro Preview 05-06","short_name":"Gemini 2.5 Pro Preview 05-06","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro-preview-03-25","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9d2cac4d-81d4-4e67-ac7a-6c73040655ee","name":"Google | google/gemini-2.5-pro-preview-03-25","context_length":1048576,"model":{"slug":"google/gemini-2.5-pro-preview-05-06","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-05-07T00:41:53+00:00","hf_updated_at":null,"name":"Google: Gemini 2.5 Pro Preview 05-06","short_name":"Gemini 2.5 Pro Preview 05-06","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemini-2.5-pro-preview-03-25","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemini-2.5-pro-preview-05-06","model_variant_permaslug":"google/gemini-2.5-pro-preview-03-25","adapter_name":"GoogleVertexGeminiAdapter","provider_name":"Google","provider_info":{"name":"Google","displayName":"Google Vertex","slug":"google-vertex","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"GoogleVertexGeminiAdapter","statusPageUrl":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","byokEnabled":true,"icon":{"url":"/images/icons/GoogleVertex.svg"},"sendClientIp":false,"pricingStrategy":"gemini"},"provider_display_name":"Google Vertex","provider_slug":"google-vertex","provider_model_id":"gemini-2.5-pro-preview-05-06","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":65535,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://cloud.google.com/terms/","privacyPolicyURL":"https://cloud.google.com/terms/cloud-privacy-notice","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","audio":"0.00000125","input_audio_cache":"0.000000125","input_cache_read":"0.000000125","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.00001","discount":0,"overrides":[{"min_prompt_tokens":200000,"prompt":"0.0000025","completion":"0.000015","audio":"0.0000025","input_audio_cache":"0.00000025","input_cache_read":"0.00000025"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00001"},{"sku_label":">200K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00001"},{"sku_label":">200K","price":"0.000015"}]},{"kind":"token","sku_label":"Cache Read","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]},{"kind":"token","sku_label":"Cache Write","price":"3.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Image Input","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Input Audio","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"0.00000125"},{"sku_label":">200K","price":"0.0000025"}]},{"kind":"token","sku_label":"Input Audio Cache","price":"1.25e-7","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤200K","price":"1.25e-7"},{"sku_label":">200K","price":"2.5e-7"}]}],"pricing_json":{"gemini:prompt_tokens":0.00000125,"gemini:reasoning_tokens":0.00001,"gemini:cache_read_tokens":1.25e-7,"gemini:completion_tokens":0.00001,"gemini:text_input_tokens":0.00000125,"gemini:audio_input_tokens":0.00000125,"gemini:image_input_tokens":0.00000125,"gemini:video_input_tokens":0.00000125,"gemini:cache_read_text_tokens":1.25e-7,"gemini:long_context_threshold":"200000","gemini:cache_read_audio_tokens":1.25e-7,"gemini:cache_read_image_tokens":1.25e-7,"gemini:cache_read_video_tokens":1.25e-7,"gemini:cache_write_storage_hours":0.0000045,"gemini:prompt_tokens_high_context":0.0000025,"gemini:reasoning_tokens_high_context":0.000015,"gemini:cache_read_tokens_high_context":2.5e-7,"gemini:completion_tokens_high_context":0.000015,"gemini:cache_read_text_tokens_high_context":2.5e-7,"gemini:cache_read_audio_tokens_high_context":2.5e-7,"gemini:cache_read_image_tokens_high_context":2.5e-7,"gemini:cache_read_video_tokens_high_context":2.5e-7,"gemini:informational_cache_write_tokens_count":0},"pricing_version_id":"d59f968c-51d4-43e9-93ea-276703a18f2e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":true,"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true},"is_mandatory_reasoning":true},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-08T14:58:08.299Z","status":0}},{"slug":"arcee-ai/virtuoso-large","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-05-05T21:01:25.294Z","hf_updated_at":null,"name":"Arcee AI: Virtuoso Large","short_name":"Virtuoso Large","author":"arcee-ai","author_display_name":"arcee-ai","author_icon_uri":null,"description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k context inherited from Qwen 2.5, letting it ingest books, codebases or financial filings wholesale. Training blended DeepSeek R1 distillation, multi‑epoch supervised fine‑tuning and a final DPO/RLHF alignment stage, yielding strong performance on BIG‑Bench‑Hard, GSM‑8K and long‑context Needle‑In‑Haystack tests. Enterprises use Virtuoso‑Large as the \"fallback\" brain in Conductor pipelines when other SLMs flag low confidence. Despite its size, aggressive KV‑cache optimizations keep first‑token latency in the low‑second range on 8× H100 nodes, making it a practical production‑grade powerhouse.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"arcee-ai/virtuoso-large","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6ea266fd-81e1-4ad2-ba62-2f09c5762435","name":"Together | arcee-ai/virtuoso-large","context_length":131072,"model":{"slug":"arcee-ai/virtuoso-large","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-05-05T21:01:25.294732+00:00","hf_updated_at":null,"name":"Arcee AI: Virtuoso Large","short_name":"Virtuoso Large","author":"arcee-ai","author_display_name":"arcee-ai","author_icon_uri":null,"description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k context inherited from Qwen 2.5, letting it ingest books, codebases or financial filings wholesale. Training blended DeepSeek R1 distillation, multi‑epoch supervised fine‑tuning and a final DPO/RLHF alignment stage, yielding strong performance on BIG‑Bench‑Hard, GSM‑8K and long‑context Needle‑In‑Haystack tests. Enterprises use Virtuoso‑Large as the \"fallback\" brain in Conductor pipelines when other SLMs flag low confidence. Despite its size, aggressive KV‑cache optimizations keep first‑token latency in the low‑second range on 8× H100 nodes, making it a practical production‑grade powerhouse.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"arcee-ai/virtuoso-large","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"arcee-ai/virtuoso-large","model_variant_permaslug":"arcee-ai/virtuoso-large","adapter_name":"TogetherAdapter","provider_name":"Together","provider_info":{"name":"Together","displayName":"Together","slug":"together","baseUrl":"https://api.together.xyz/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"TogetherAdapter","statusPageUrl":"https://status.together.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.together.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Together","provider_slug":"together","provider_model_id":"arcee-ai/virtuoso-large","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":64000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.together.ai/terms-of-service","privacyPolicyURL":"https://www.together.ai/privacy"},"pricing":{"prompt":"0.00000075","completion":"0.0000012","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000012","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000075","openai:completion_tokens":"0.0000012"},"pricing_version_id":"9c0bc773-7c67-4276-889c-9543e6a5d6b5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-05-05T21:04:11.750Z","status":0}},{"slug":"meta-llama/llama-guard-4-12b","hf_slug":"meta-llama/Llama-Guard-4-12B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-30T01:06:33.531Z","hf_updated_at":null,"name":"Meta: Llama Guard 4 12B","short_name":"Llama Guard 4 12B","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\n\nLlama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.","model_version_group_id":null,"context_length":1048576,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-guard-4-12b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"850b84c3-42a7-4cec-99c0-b5582d0da66b","name":"DeepInfra | meta-llama/llama-guard-4-12b","context_length":163840,"model":{"slug":"meta-llama/llama-guard-4-12b","hf_slug":"meta-llama/Llama-Guard-4-12B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-30T01:06:33.531556+00:00","hf_updated_at":null,"name":"Meta: Llama Guard 4 12B","short_name":"Llama Guard 4 12B","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\n\nLlama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.","model_version_group_id":null,"context_length":163840,"input_modalities":["image","text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-guard-4-12b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-guard-4-12b","model_variant_permaslug":"meta-llama/llama-guard-4-12b","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"meta-llama/Llama-Guard-4-12B","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000018","completion":"0.00000018","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000018","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000018","openai:completion_tokens":"0.00000018"},"pricing_version_id":"48e5a11b-06e3-4455-a22f-3a3af4cea914","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-30T01:08:17.980Z","status":0}},{"slug":"qwen/qwen3-30b-a3b","hf_slug":"Qwen/Qwen3-30B-A3B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-28T22:16:44.177Z","hf_updated_at":null,"name":"Qwen: Qwen3 30B A3B","short_name":"Qwen3 30B A3B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-30b-a3b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"efdfff77-9574-4695-8e08-32d968a43376","name":"DeepInfra | qwen/qwen3-30b-a3b-04-28","context_length":40960,"model":{"slug":"qwen/qwen3-30b-a3b","hf_slug":"Qwen/Qwen3-30B-A3B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-28T22:16:44.177326+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 30B A3B","short_name":"Qwen3 30B A3B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-30b-a3b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-30b-a3b","model_variant_permaslug":"qwen/qwen3-30b-a3b-04-28","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Qwen/Qwen3-30B-A3B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000012","completion":"0.0000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000012","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000012","openai:completion_tokens":"0.0000005"},"pricing_version_id":"defb497f-25ae-43e2-a4bb-8cfe2cc1055d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false},"supported_parameters":{"response_format":true,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-29T01:12:34.634Z","status":0}},{"slug":"qwen/qwen3-8b","hf_slug":"Qwen/Qwen3-8B","updated_at":"2026-04-27T03:32:06.132Z","created_at":"2025-04-28T21:43:52.421Z","hf_updated_at":null,"name":"Qwen: Qwen3 8B","short_name":"Qwen3 8B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math, coding, and logical inference, and \"non-thinking\" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-8b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"633e82ca-271e-48a2-a8b3-9b69db4e2311","name":"Alibaba | qwen/qwen3-8b-04-28","context_length":131072,"model":{"slug":"qwen/qwen3-8b","hf_slug":"Qwen/Qwen3-8B","updated_at":"2026-04-27T03:32:06.132312+00:00","created_at":"2025-04-28T21:43:52.421936+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 8B","short_name":"Qwen3 8B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math, coding, and logical inference, and \"non-thinking\" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-8b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","system_prompt":null,"default_reasoning_enabled":true},"chat_template_config":{}},"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-8b","model_variant_permaslug":"qwen/qwen3-8b-04-28","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-8b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":98304,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000117","completion":"0.000000455","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000117","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000455","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000117","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000455","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000000117","alibaba:completion_tokens":"0.000000455"},"pricing_version_id":"e22641eb-99e7-4a68-af4d-fa2d4475e405","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:18:59.249Z","status":0}},{"slug":"qwen/qwen3-14b","hf_slug":"Qwen/Qwen3-14B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-28T21:41:18.320Z","hf_updated_at":null,"name":"Qwen: Qwen3 14B","short_name":"Qwen3 14B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, programming, and logical inference, and a \"non-thinking\" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-14b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c399a914-434e-4f21-b11b-8f4b3b2ec72c","name":"NextBit | qwen/qwen3-14b-04-28","context_length":40960,"model":{"slug":"qwen/qwen3-14b","hf_slug":"Qwen/Qwen3-14B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-28T21:41:18.320017+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 14B","short_name":"Qwen3 14B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, programming, and logical inference, and a \"non-thinking\" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.","model_version_group_id":null,"context_length":131702,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-14b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-14b","model_variant_permaslug":"qwen/qwen3-14b-04-28","adapter_name":"NextBitAdapter","provider_name":"NextBit","provider_info":{"name":"NextBit","displayName":"NextBit","slug":"nextbit","baseUrl":"https://api.nextbit256.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy","requiresUserIDs":false},"headquarters":"ES","datacenters":["ES"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NextBitAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nextbit256.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NextBit","provider_slug":"nextbit/int4","provider_model_id":"qwen3:14b","quantization":"int4","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":40960,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.00000022","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000022","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.00000022"},"pricing_version_id":"223de13c-b07e-4eb9-878d-555b0629c623","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-24T15:26:14.352Z","status":0}},{"slug":"qwen/qwen3-32b","hf_slug":"Qwen/Qwen3-32B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-28T21:32:25.189Z","hf_updated_at":null,"name":"Qwen: Qwen3 32B","short_name":"Qwen3 32B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, coding, and logical inference, and a \"non-thinking\" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling. ","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-32b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6b8c829d-3094-45e7-8139-0a67e09060c3","name":"DeepInfra | qwen/qwen3-32b-04-28","context_length":40960,"model":{"slug":"qwen/qwen3-32b","hf_slug":"Qwen/Qwen3-32B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-28T21:32:25.189881+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 32B","short_name":"Qwen3 32B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, coding, and logical inference, and a \"non-thinking\" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling. ","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-32b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-32b","model_variant_permaslug":"qwen/qwen3-32b-04-28","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Qwen/Qwen3-32B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","structured_outputs","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000008","completion":"0.00000028","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000028","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000028","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000008","openai:completion_tokens":"0.00000028"},"pricing_version_id":"8851c041-3d6d-4c4b-be75-918c4da47c52","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-29T01:10:08.780Z","status":0}},{"slug":"qwen/qwen3-235b-a22b","hf_slug":"Qwen/Qwen3-235B-A22B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-28T21:29:17.256Z","hf_updated_at":null,"name":"Qwen: Qwen3 235B A22B","short_name":"Qwen3 235B A22B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and code tasks, and a \"non-thinking\" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-235b-a22b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6f60fa24-0b39-42e2-a3ce-b524504c5cfa","name":"Alibaba | qwen/qwen3-235b-a22b-04-28","context_length":131072,"model":{"slug":"qwen/qwen3-235b-a22b","hf_slug":"Qwen/Qwen3-235B-A22B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-28T21:29:17.25671+00:00","hf_updated_at":null,"name":"Qwen: Qwen3 235B A22B","short_name":"Qwen3 235B A22B","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and code tasks, and a \"non-thinking\" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen3","instruct_type":"qwen3","default_system":null,"default_stops":["<|im_start|>","<|im_end|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen3-235b-a22b-04-28","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen3-235b-a22b","model_variant_permaslug":"qwen/qwen3-235b-a22b-04-28","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen3-235b-a22b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":98304,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.000000455","completion":"0.00000182","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000455","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000182","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000455","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000182","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"alibaba:prompt_tokens":"0.000000455","alibaba:completion_tokens":"0.00000182"},"pricing_version_id":"f0d25f49-2503-4c69-acef-e8e7d549827b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-12T14:17:32.817Z","status":0}},{"slug":"openai/o4-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-16T17:23:32.042Z","hf_updated_at":null,"name":"OpenAI: o4 Mini High (batch)","short_name":"o4 Mini High (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-high-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7e48fa58-df53-4093-935c-593cccf82a04","name":"OpenAI | openai/o4-mini-high-2025-04-16:batch","context_length":200000,"model":{"slug":"openai/o4-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-16T17:23:32.042157+00:00","hf_updated_at":null,"name":"OpenAI: o4 Mini High","short_name":"o4 Mini High","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-high-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o4-mini-high:batch","model_variant_permaslug":"openai/o4-mini-high-2025-04-16:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o4-mini-2025-04-16","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000055","completion":"0.0000022","input_cache_read":"0.0000001375","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.375000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.375000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"5.500000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"2.200000e-6","openai_responses:cached_prompt_tokens":"1.375000e-7"},"pricing_version_id":"28e374cc-a878-4aad-8321-9d749b9d50ea","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:35.162Z","status":0}},{"slug":"openai/o4-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-16T17:23:32.042Z","hf_updated_at":null,"name":"OpenAI: o4 Mini High","short_name":"o4 Mini High","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-high-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"60020533-2fb2-4aa1-9454-181029fd52de","name":"OpenAI | openai/o4-mini-high-2025-04-16","context_length":200000,"model":{"slug":"openai/o4-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-16T17:23:32.042157+00:00","hf_updated_at":null,"name":"OpenAI: o4 Mini High","short_name":"o4 Mini High","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. \n\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-high-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supported_reasoning_efforts":["high"]},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o4-mini-high","model_variant_permaslug":"openai/o4-mini-high-2025-04-16","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o4-mini-2025-04-16","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000011","completion":"0.0000044","input_cache_read":"0.000000275","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.0000011,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.0000044,"openai_responses:cached_prompt_tokens":2.75e-7},"pricing_version_id":"4bc59a87-2c2a-4682-809b-e495ce4af791","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-16T17:24:46.458Z","status":0}},{"slug":"openai/o3","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-16T17:10:57.049Z","hf_updated_at":null,"name":"OpenAI: o3 (batch)","short_name":"o3 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2f5700a6-f81a-4a92-8f27-5f13bb3bf301","name":"OpenAI | openai/o3-2025-04-16:batch","context_length":200000,"model":{"slug":"openai/o3","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-16T17:10:57.049467+00:00","hf_updated_at":null,"name":"OpenAI: o3","short_name":"o3","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3:batch","model_variant_permaslug":"openai/o3-2025-04-16:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-2025-04-16","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000004","input_cache_read":"0.00000025","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.000000e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"4.000000e-6","openai_responses:cached_prompt_tokens":"2.500000e-7"},"pricing_version_id":"6f8845df-0864-4edf-92c5-791659b0ddd8","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:59.864Z","status":0}},{"slug":"openai/o3","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-16T17:10:57.049Z","hf_updated_at":null,"name":"OpenAI: o3","short_name":"o3","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"42e72619-d01c-411c-a201-f991644768b7","name":"OpenAI | openai/o3-2025-04-16","context_length":200000,"model":{"slug":"openai/o3","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-16T17:10:57.049467+00:00","hf_updated_at":null,"name":"OpenAI: o3","short_name":"o3","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3","model_variant_permaslug":"openai/o3-2025-04-16","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-2025-04-16","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000008","input_cache_read":"0.0000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.000002,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.000008,"openai_responses:cached_prompt_tokens":5e-7},"pricing_version_id":"a6ec168c-ce39-40e5-82e9-5847d89c27dd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-16T17:11:55.903Z","status":0}},{"slug":"openai/o4-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-16T16:29:02.980Z","hf_updated_at":null,"name":"OpenAI: o4 Mini (batch)","short_name":"o4 Mini (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c34ab2fb-a9a3-4449-ad68-675e66d9667b","name":"OpenAI | openai/o4-mini-2025-04-16:batch","context_length":200000,"model":{"slug":"openai/o4-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-16T16:29:02.980764+00:00","hf_updated_at":null,"name":"OpenAI: o4 Mini","short_name":"o4 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o4-mini:batch","model_variant_permaslug":"openai/o4-mini-2025-04-16:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o4-mini-2025-04-16","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000055","completion":"0.0000022","input_cache_read":"0.0000001375","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.375000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.375000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"5.500000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"2.200000e-6","openai_responses:cached_prompt_tokens":"1.375000e-7"},"pricing_version_id":"5c00d9cd-c920-41b4-95c8-6ce831347dc1","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:09:00.589Z","status":0}},{"slug":"openai/o4-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-16T16:29:02.980Z","hf_updated_at":null,"name":"OpenAI: o4 Mini","short_name":"o4 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"bd121898-b27c-4e2c-bc92-278627465a54","name":"OpenAI | openai/o4-mini-2025-04-16","context_length":200000,"model":{"slug":"openai/o4-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-16T16:29:02.980764+00:00","hf_updated_at":null,"name":"OpenAI: o4 Mini","short_name":"o4 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_version_group_id":null,"context_length":200000,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o4-mini-2025-04-16","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o4-mini","model_variant_permaslug":"openai/o4-mini-2025-04-16","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o4-mini-2025-04-16","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000011","completion":"0.0000044","input_cache_read":"0.000000275","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.75e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.0000011,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.0000044,"openai_responses:cached_prompt_tokens":2.75e-7},"pricing_version_id":"b9791ed2-0245-490a-9ba2-eb793e43b0ec","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-16T16:30:03.632Z","status":0}},{"slug":"openai/gpt-4.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-14T17:23:05.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4.1 (batch)","short_name":"GPT-4.1 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"41e72505-ba5c-4ab6-b55f-620e033a284a","name":"OpenAI | openai/gpt-4.1-2025-04-14:batch","context_length":1047576,"model":{"slug":"openai/gpt-4.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-14T17:23:05+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4.1","short_name":"GPT-4.1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4.1:batch","model_variant_permaslug":"openai/gpt-4.1-2025-04-14:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4.1-2025-04-14","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000001","completion":"0.000004","input_cache_read":"0.00000025","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"1.000000e-6","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"4.000000e-6","openai_responses:cached_prompt_tokens":"2.500000e-7"},"pricing_version_id":"e8e73d48-b3b8-42d9-933d-93ace97c3515","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:56.141Z","status":0}},{"slug":"openai/gpt-4.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-14T17:23:05.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4.1","short_name":"GPT-4.1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c235abe8-11cc-42d3-95ad-72f4d198287a","name":"OpenAI | openai/gpt-4.1-2025-04-14","context_length":1047576,"model":{"slug":"openai/gpt-4.1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-14T17:23:05+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4.1","short_name":"GPT-4.1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4.1","model_variant_permaslug":"openai/gpt-4.1-2025-04-14","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4.1-2025-04-14","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000002","completion":"0.000008","input_cache_read":"0.0000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":0.000002,"openai_responses:web_search_calls":0.01,"openai_responses:completion_tokens":0.000008,"openai_responses:cached_prompt_tokens":5e-7},"pricing_version_id":"ca78388e-e63c-4cea-a999-e421ab69bfe9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-14T13:27:58.426Z","status":0}},{"slug":"openai/gpt-4.1-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-14T17:23:01.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Mini (batch)","short_name":"GPT-4.1 Mini (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-mini-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"fe95eb82-a92a-4886-8492-7a138b2afc5f","name":"OpenAI | openai/gpt-4.1-mini-2025-04-14:batch","context_length":1047576,"model":{"slug":"openai/gpt-4.1-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-14T17:23:01+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Mini","short_name":"GPT-4.1 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-mini-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4.1-mini:batch","model_variant_permaslug":"openai/gpt-4.1-mini-2025-04-14:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4.1-mini-2025-04-14","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"8.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5.000000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"8.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5.000000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"2.000000e-7","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"8.000000e-7","openai_responses:cached_prompt_tokens":"5.000000e-8"},"pricing_version_id":"38246116-d4ab-44f6-8570-88095ecceac8","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:56.858Z","status":0}},{"slug":"openai/gpt-4.1-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-14T17:23:01.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Mini","short_name":"GPT-4.1 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-mini-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1551aa56-4221-448a-b280-f862f73c27de","name":"Azure | openai/gpt-4.1-mini-2025-04-14","context_length":1047576,"model":{"slug":"openai/gpt-4.1-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-14T17:23:01+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Mini","short_name":"GPT-4.1 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-mini-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4.1-mini","model_variant_permaslug":"openai/gpt-4.1-mini-2025-04-14","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-4.1-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.0000004","completion":"0.0000016","input_cache_read":"0.0000001","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000016","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000016","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":4e-7,"openai_responses:completion_tokens":0.0000016,"openai_responses:cached_prompt_tokens":1e-7},"pricing_version_id":"37491dbb-652e-4176-a6e2-a206ee5c6722","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_implicit_caching":true,"supports_file_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-23T15:48:18.902Z","status":0}},{"slug":"openai/gpt-4.1-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-14T17:22:49.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Nano (batch)","short_name":"GPT-4.1 Nano (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-nano-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b2ebb058-b93f-48a0-8545-ef25b8bbb27f","name":"OpenAI | openai/gpt-4.1-nano-2025-04-14:batch","context_length":1047576,"model":{"slug":"openai/gpt-4.1-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-14T17:22:49+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Nano","short_name":"GPT-4.1 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-nano-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4.1-nano:batch","model_variant_permaslug":"openai/gpt-4.1-nano-2025-04-14:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4.1-nano-2025-04-14","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000005","completion":"0.0000002","input_cache_read":"0.0000000125","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.000000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.000000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"1.250000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.01","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"openai_responses:prompt_tokens":"5.000000e-8","openai_responses:web_search_calls":"0.01","openai_responses:completion_tokens":"2.000000e-7","openai_responses:cached_prompt_tokens":"1.250000e-8"},"pricing_version_id":"44bab90f-9d39-4526-8582-a79f34ad0d1a","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_native_web_search":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:57.614Z","status":0}},{"slug":"openai/gpt-4.1-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-04-14T17:22:49.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Nano","short_name":"GPT-4.1 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-nano-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1826e686-ee39-4fdd-af2b-6e0c6fb2e6da","name":"Azure | openai/gpt-4.1-nano-2025-04-14","context_length":1047576,"model":{"slug":"openai/gpt-4.1-nano","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-04-14T17:22:49+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4.1 Nano","short_name":"GPT-4.1 Nano","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","model_version_group_id":null,"context_length":1047576,"input_modalities":["image","text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4.1-nano-2025-04-14","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4.1-nano","model_variant_permaslug":"openai/gpt-4.1-nano-2025-04-14","adapter_name":"InternalStreamAzureOpenAIResponsesAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-4.1-nano","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","seed","response_format","structured_outputs","tool_choice","tools","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":1e-7,"openai_responses:completion_tokens":4e-7,"openai_responses:cached_prompt_tokens":3e-8},"pricing_version_id":"1aef04c8-bb99-4e64-8f76-56b44341f640","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_implicit_caching":true,"supports_file_urls":true,"supports_input_audio":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-10-23T15:52:48.031Z","status":0}},{"slug":"meta-llama/llama-4-maverick","hf_slug":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-05T19:37:02.129Z","hf_updated_at":null,"name":"Meta: Llama 4 Maverick","short_name":"Llama 4 Maverick","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\n\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Llama4","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-4-maverick-17b-128e-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"caa850a1-e628-41bd-8585-9b3076efea90","name":"DigitalOcean | meta-llama/llama-4-maverick-17b-128e-instruct","context_length":128000,"model":{"slug":"meta-llama/llama-4-maverick","hf_slug":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-05T19:37:02.129674+00:00","hf_updated_at":null,"name":"Meta: Llama 4 Maverick","short_name":"Llama 4 Maverick","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\n\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.","model_version_group_id":null,"context_length":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Llama4","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-4-maverick-17b-128e-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-4-maverick","model_variant_permaslug":"meta-llama/llama-4-maverick-17b-128e-instruct","adapter_name":"DigitalOceanAdapter","provider_name":"DigitalOcean","provider_info":{"name":"DigitalOcean","displayName":"DigitalOcean","slug":"digitalocean","baseUrl":"https://inference.do-ai.run/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.digitalocean.com/legal/terms-of-service-agreement","privacyPolicyURL":"https://www.digitalocean.com/legal/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"DigitalOceanAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.digitalocean.com&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DigitalOcean","provider_slug":"digitalocean","provider_model_id":"llama-4-maverick","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.digitalocean.com/legal/terms-of-service-agreement","privacyPolicyURL":"https://www.digitalocean.com/legal/privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.000000696","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000696","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000696","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000002","openai:completion_tokens":"0.000000696"},"pricing_version_id":"b433f022-436c-4382-9280-eeedf40fba3b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-06-23T15:12:14.901Z","status":0}},{"slug":"meta-llama/llama-4-scout","hf_slug":"meta-llama/Llama-4-Scout-17B-16E-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-04-05T19:31:59.735Z","hf_updated_at":null,"name":"Meta: Llama 4 Scout","short_name":"Llama 4 Scout","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\n\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.","model_version_group_id":null,"context_length":1310720,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Llama4","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-4-scout-17b-16e-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"9cf05ded-eefe-41b4-8c08-0c6460feffea","name":"DeepInfra | meta-llama/llama-4-scout-17b-16e-instruct","context_length":327680,"model":{"slug":"meta-llama/llama-4-scout","hf_slug":"meta-llama/Llama-4-Scout-17B-16E-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-04-05T19:31:59.735804+00:00","hf_updated_at":null,"name":"Meta: Llama 4 Scout","short_name":"Llama 4 Scout","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\n\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.","model_version_group_id":null,"context_length":10000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Llama4","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-4-scout-17b-16e-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-4-scout","model_variant_permaslug":"meta-llama/llama-4-scout-17b-16e-instruct","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":3342,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000001","completion":"0.0000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000003"},"pricing_version_id":"fdcca743-6436-498e-9da4-cb68208a4733","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-06T00:32:07.526Z","status":0}},{"slug":"deepseek/deepseek-chat-v3-0324","hf_slug":"deepseek-ai/DeepSeek-V3-0324","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-24T13:59:15.252Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3 0324","short_name":"DeepSeek V3 0324","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.\n\nIt succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.","model_version_group_id":"be67b3ba-9d99-440c-ae90-6514d99b93ed","context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-chat-v3-0324","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"820376cb-f110-4d56-ab52-5bd6ca269420","name":"DeepInfra | deepseek/deepseek-chat-v3-0324","context_length":163840,"model":{"slug":"deepseek/deepseek-chat-v3-0324","hf_slug":"deepseek-ai/DeepSeek-V3-0324","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-24T13:59:15.252028+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3 0324","short_name":"DeepSeek V3 0324","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.\n\nIt succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.","model_version_group_id":"be67b3ba-9d99-440c-ae90-6514d99b93ed","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-chat-v3-0324","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-chat-v3-0324","model_variant_permaslug":"deepseek/deepseek-chat-v3-0324","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp4","provider_model_id":"deepseek-ai/DeepSeek-V3-0324","quantization":"fp4","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","tools","tool_choice","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000024","completion":"0.0000009","input_cache_read":"0.000000135","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000024","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000135","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000024","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000009","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.000000135","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000024","openai:completion_tokens":"0.0000009","openai:cached_prompt_tokens":"0.000000135"},"pricing_version_id":"21de7f5d-3924-46e5-944f-26bfc07c67fe","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-24T20:02:59.576Z","status":-2}},{"slug":"openai/o1-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-03-19T22:26:51.610Z","hf_updated_at":null,"name":"OpenAI: o1-pro (batch)","short_name":"o1-pro (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5e913525-d102-4fba-b5b0-36d4db044c3f","name":"OpenAI | openai/o1-pro:batch","context_length":200000,"model":{"slug":"openai/o1-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-03-19T22:26:51.610039+00:00","hf_updated_at":null,"name":"OpenAI: o1-pro","short_name":"o1-pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o1-pro:batch","model_variant_permaslug":"openai/o1-pro:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o1-pro","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000075","completion":"0.0003","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3.000000e-4","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3.000000e-4","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"7.500000e-5","openai_responses:completion_tokens":"3.000000e-4"},"pricing_version_id":"a7bf29a1-520e-41be-b8e4-cef8c183e39d","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:32.712Z","status":0}},{"slug":"openai/o1-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-03-19T22:26:51.610Z","hf_updated_at":null,"name":"OpenAI: o1-pro","short_name":"o1-pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"046ae30d-fe99-44b4-b020-21127e4342c7","name":"OpenAI | openai/o1-pro","context_length":200000,"model":{"slug":"openai/o1-pro","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-03-19T22:26:51.610039+00:00","hf_updated_at":null,"name":"OpenAI: o1-pro","short_name":"o1-pro","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-pro","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o1-pro","model_variant_permaslug":"openai/o1-pro","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o1-pro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00015","completion":"0.0006","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.00015,"openai_responses:completion_tokens":0.0006},"pricing_version_id":"af47ffe6-72c7-4a72-8bf4-1922ed5d6d65","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-20T04:20:01.507Z","status":0}},{"slug":"mistralai/mistral-small-3.1-24b-instruct","hf_slug":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-17T19:15:37.004Z","hf_updated_at":null,"name":"Mistral: Mistral Small 3.1 24B","short_name":"Mistral Small 3.1 24B","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-3.1-24b-instruct-2503","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"35a93f0c-ce8f-4475-a6db-a383cc128360","name":"Cloudflare | mistralai/mistral-small-3.1-24b-instruct-2503","context_length":128000,"model":{"slug":"mistralai/mistral-small-3.1-24b-instruct","hf_slug":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-17T19:15:37.00423+00:00","hf_updated_at":null,"name":"Mistral: Mistral Small 3.1 24B","short_name":"Mistral Small 3.1 24B","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-3.1-24b-instruct-2503","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-small-3.1-24b-instruct","model_variant_permaslug":"mistralai/mistral-small-3.1-24b-instruct-2503","adapter_name":"CloudflareAdapter","provider_name":"Cloudflare","provider_info":{"name":"Cloudflare","displayName":"Cloudflare","slug":"cloudflare","baseUrl":"https://api.cloudflare.com/client/v4/accounts/{accountId}/ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"CloudflareAdapter","statusPageUrl":"https://www.cloudflarestatus.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.cloudflare.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Cloudflare","provider_slug":"cloudflare","provider_model_id":"@cf/mistralai/mistral-small-3.1-24b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":128000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy"},"pricing":{"prompt":"0.000000351","completion":"0.000000555","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000351","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000555","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000351","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000555","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000351","openai:completion_tokens":"0.000000555"},"pricing_version_id":"b763a5a0-d493-4340-9038-5313b8d835b1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-25T13:49:59.831Z","status":0}},{"slug":"google/gemma-3-4b-it","hf_slug":"google/gemma-3-4b-it","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-13T22:38:30.653Z","hf_updated_at":null,"name":"Google: Gemma 3 4B","short_name":"Gemma 3 4B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.","model_version_group_id":"c99b277a-cfaf-4e93-9360-8a79cfa2b2c4","context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3-4b-it","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d3de3bd4-81bc-48fb-924f-2a87b2a36e75","name":"DeepInfra | google/gemma-3-4b-it","context_length":131072,"model":{"slug":"google/gemma-3-4b-it","hf_slug":"google/gemma-3-4b-it","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-13T22:38:30.653142+00:00","hf_updated_at":null,"name":"Google: Gemma 3 4B","short_name":"Gemma 3 4B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.","model_version_group_id":"c99b277a-cfaf-4e93-9360-8a79cfa2b2c4","context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3-4b-it","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-3-4b-it","model_variant_permaslug":"google/gemma-3-4b-it","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"google/gemma-3-4b-it","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000005","completion":"0.0000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000005","openai:completion_tokens":"0.0000001"},"pricing_version_id":"ee31c6ba-a5af-4e72-8260-0e8925544d5a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-28T21:18:06.858Z","status":0}},{"slug":"google/gemma-3-12b-it","hf_slug":"google/gemma-3-12b-it","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-13T21:50:25.140Z","hf_updated_at":null,"name":"Google: Gemma 3 12B","short_name":"Gemma 3 12B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)","model_version_group_id":"c99b277a-cfaf-4e93-9360-8a79cfa2b2c4","context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3-12b-it","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"eb06dc92-5a16-47ec-a776-6ef956457c47","name":"DeepInfra | google/gemma-3-12b-it","context_length":131072,"model":{"slug":"google/gemma-3-12b-it","hf_slug":"google/gemma-3-12b-it","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-13T21:50:25.140801+00:00","hf_updated_at":null,"name":"Google: Gemma 3 12B","short_name":"Gemma 3 12B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)","model_version_group_id":"c99b277a-cfaf-4e93-9360-8a79cfa2b2c4","context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3-12b-it","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-3-12b-it","model_variant_permaslug":"google/gemma-3-12b-it","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"google/gemma-3-12b-it","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000005","completion":"0.00000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000005","openai:completion_tokens":"0.00000015"},"pricing_version_id":"4b94cf11-535d-4302-9f10-6be74ed5e027","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-28T21:17:19.181Z","status":0}},{"slug":"cohere/command-a","hf_slug":"CohereForAI/c4ai-command-a-03-2025","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-13T19:32:22.069Z","hf_updated_at":null,"name":"Cohere: Command A","short_name":"Command A","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.\nCompared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-a-03-2025","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2e152629-dac1-41b0-8f4f-f8c449d2d504","name":"Cohere | cohere/command-a-03-2025","context_length":256000,"model":{"slug":"cohere/command-a","hf_slug":"CohereForAI/c4ai-command-a-03-2025","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-13T19:32:22.069645+00:00","hf_updated_at":null,"name":"Cohere: Command A","short_name":"Command A","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.\nCompared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.","model_version_group_id":null,"context_length":256000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-a-03-2025","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"cohere/command-a","model_variant_permaslug":"cohere/command-a-03-2025","adapter_name":"CohereV2Adapter","provider_name":"Cohere","provider_info":{"name":"Cohere","displayName":"Cohere","slug":"cohere","baseUrl":"https://api.cohere.com/v2","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"CohereV2Adapter","statusPageUrl":"https://status.cohere.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Cohere.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Cohere","provider_slug":"cohere","provider_model_id":"command-a-03-2025","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy"},"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000025","openai:completion_tokens":"0.00001"},"pricing_version_id":"133055c2-628b-4f51-9005-a82689896854","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-13T19:34:00.700Z","status":0}},{"slug":"rekaai/reka-flash-3","hf_slug":"RekaAI/reka-flash-3","updated_at":"2026-04-01T13:25:49.414Z","created_at":"2025-03-12T20:53:33.296Z","hf_updated_at":null,"name":"Reka Flash 3","short_name":"Reka Flash 3","author":"rekaai","author_display_name":"rekaai","author_icon_uri":null,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags (\"<reasoning>\") to indicate its internal thought process.\n\nReka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"rekaai/reka-flash-3","supports_reasoning":true,"reasoning_config":{"start_token":"<reasoning>","end_token":"</reasoning>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<reasoning>","end_token":"</reasoning>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5b2eb40d-677c-4fb3-a8bc-340b1bacc417","name":"Reka | rekaai/reka-flash-3","context_length":65536,"model":{"slug":"rekaai/reka-flash-3","hf_slug":"RekaAI/reka-flash-3","updated_at":"2026-04-01T13:25:49.414372+00:00","created_at":"2025-03-12T20:53:33.296745+00:00","hf_updated_at":null,"name":"Reka Flash 3","short_name":"Reka Flash 3","author":"rekaai","author_display_name":"rekaai","author_icon_uri":null,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags (\"<reasoning>\") to indicate its internal thought process.\n\nReka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.","model_version_group_id":null,"context_length":32000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":"","routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"rekaai/reka-flash-3","supports_reasoning":true,"reasoning_config":{"start_token":"<reasoning>","end_token":"</reasoning>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"features":{"reasoning_config":{"start_token":"<reasoning>","end_token":"</reasoning>","is_mandatory_reasoning":true,"reasoning_return_mechanism":"content-string"},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2025-01-31T00:00:00+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"rekaai/reka-flash-3","model_variant_permaslug":"rekaai/reka-flash-3","adapter_name":"OpenAIAdapter","provider_name":"Reka","provider_info":{"name":"Reka","displayName":"Reka AI","slug":"reka","baseUrl":"https://api.reka.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://reka.ai/legal/terms-of-use","privacyPolicyURL":"https://reka.ai/legal/privacy-policy","requiresUserIDs":false},"datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://reka.ai&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Reka AI","provider_slug":"reka/fp8","provider_model_id":"reka-flash-3","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://reka.ai/legal/terms-of-use","privacyPolicyURL":"https://reka.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000001","completion":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000002"},"pricing_version_id":"377bd8d1-6d45-4488-a45f-83f2ce6662e7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_base64_video_input":false,"supports_video_urls":false,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-29T17:10:45.659Z","status":0}},{"slug":"google/gemma-3-27b-it","hf_slug":"google/gemma-3-27b-it","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-12T05:12:39.645Z","hf_updated_at":null,"name":"Google: Gemma 3 27B","short_name":"Gemma 3 27B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)","model_version_group_id":"c99b277a-cfaf-4e93-9360-8a79cfa2b2c4","context_length":262144,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3-27b-it","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8f22002c-c045-446f-a1b9-9896133536b8","name":"DeepInfra | google/gemma-3-27b-it","context_length":131072,"model":{"slug":"google/gemma-3-27b-it","hf_slug":"google/gemma-3-27b-it","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-12T05:12:39.645813+00:00","hf_updated_at":null,"name":"Google: Gemma 3 27B","short_name":"Gemma 3 27B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)","model_version_group_id":"c99b277a-cfaf-4e93-9360-8a79cfa2b2c4","context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-3-27b-it","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-3-27b-it","model_variant_permaslug":"google/gemma-3-27b-it","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"google/gemma-3-27b-it","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000008","completion":"0.00000016","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000016","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000016","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000008","openai:completion_tokens":"0.00000016"},"pricing_version_id":"7a7d5757-1cfc-4228-a381-3cbfab62b468","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":80,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-14T13:28:27.176Z","status":0}},{"slug":"thedrummer/skyfall-36b-v2","hf_slug":"TheDrummer/Skyfall-36B-v2","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-03-10T19:56:06.007Z","hf_updated_at":null,"name":"TheDrummer: Skyfall 36B V2","short_name":"Skyfall 36B V2","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/skyfall-36b-v2","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"1eb01ded-ae11-49e6-8aa6-3067584070bd","name":"Parasail | thedrummer/skyfall-36b-v2","context_length":32768,"model":{"slug":"thedrummer/skyfall-36b-v2","hf_slug":"TheDrummer/Skyfall-36B-v2","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-03-10T19:56:06.00791+00:00","hf_updated_at":null,"name":"TheDrummer: Skyfall 36B V2","short_name":"Skyfall 36B V2","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/skyfall-36b-v2","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"thedrummer/skyfall-36b-v2","model_variant_permaslug":"thedrummer/skyfall-36b-v2","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/fp8","provider_model_id":"parasail-skyfall-36b-v2-fp8","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000055","completion":"0.0000008","input_cache_read":"0.00000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000055","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000055","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000055","openai:completion_tokens":"0.0000008","openai:cached_prompt_tokens":"0.00000025"},"pricing_version_id":"d73253aa-7323-4f61-acb2-75a988feb8ae","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-10T19:56:28.966Z","status":0}},{"slug":"perplexity/sonar-reasoning-pro","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-03-07T02:08:28.125Z","hf_updated_at":null,"name":"Perplexity: Sonar Reasoning Pro","short_name":"Sonar Reasoning Pro","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nSonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-reasoning-pro","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0d28660e-435a-4853-a2c6-9d916df28fc7","name":"Perplexity | perplexity/sonar-reasoning-pro","context_length":128000,"model":{"slug":"perplexity/sonar-reasoning-pro","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-03-07T02:08:28.125446+00:00","hf_updated_at":null,"name":"Perplexity: Sonar Reasoning Pro","short_name":"Sonar Reasoning Pro","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nSonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-reasoning-pro","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"perplexity/sonar-reasoning-pro","model_variant_permaslug":"perplexity/sonar-reasoning-pro","adapter_name":"PerplexityAdapter","provider_name":"Perplexity","provider_info":{"name":"Perplexity","displayName":"Perplexity","slug":"perplexity","baseUrl":"https://api.perplexity.ai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"PerplexityAdapter","statusPageUrl":"https://status.perplexity.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Perplexity.svg"},"sendClientIp":false,"pricingStrategy":"perplexity"},"provider_display_name":"Perplexity","provider_slug":"perplexity","provider_model_id":"sonar-reasoning-pro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy"},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"perplexity:prompt_tokens":0.000002,"perplexity:web_search_calls":0.005,"perplexity:completion_tokens":0.000008},"pricing_version_id":"0b0e7da7-61f8-49cf-a9f1-c23bbfd16e19","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-07T02:09:48.740Z","status":0}},{"slug":"perplexity/sonar-pro","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-03-07T01:53:43.000Z","hf_updated_at":null,"name":"Perplexity: Sonar Pro","short_name":"Sonar Pro","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nFor enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions. ","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-pro","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e19b1036-fab9-4f97-9579-8ea67959cc9b","name":"Perplexity | perplexity/sonar-pro","context_length":200000,"model":{"slug":"perplexity/sonar-pro","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-03-07T01:53:43+00:00","hf_updated_at":null,"name":"Perplexity: Sonar Pro","short_name":"Sonar Pro","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\n\nFor enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions. ","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-pro","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"perplexity/sonar-pro","model_variant_permaslug":"perplexity/sonar-pro","adapter_name":"PerplexityAdapter","provider_name":"Perplexity","provider_info":{"name":"Perplexity","displayName":"Perplexity","slug":"perplexity","baseUrl":"https://api.perplexity.ai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"PerplexityAdapter","statusPageUrl":"https://status.perplexity.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Perplexity.svg"},"sendClientIp":false,"pricingStrategy":"perplexity"},"provider_display_name":"Perplexity","provider_slug":"perplexity","provider_model_id":"sonar-pro","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":8000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy"},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"perplexity:prompt_tokens":0.000003,"perplexity:web_search_calls":0.005,"perplexity:completion_tokens":0.000015},"pricing_version_id":"f3c0cb5b-c71c-4f8a-bd65-3c576775f879","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_multipart":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-01-28T14:40:08.507Z","status":0}},{"slug":"perplexity/sonar-deep-research","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-03-07T01:34:06.000Z","hf_updated_at":null,"name":"Perplexity: Sonar Deep Research","short_name":"Sonar Deep Research","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events.\n\nNotes on Pricing ([Source](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-deep-research)) \n- Input tokens comprise of Prompt tokens (user prompt) + Citation tokens (these are processed tokens from running searches)\n- Deep Research runs multiple searches to conduct exhaustive research. Searches are priced at $5/1000 searches. A request that does 30 searches will cost $0.15 in this step.\n- Reasoning is a distinct step in Deep Research since it does extensive automated reasoning through all the material it gathers during its research phase. Reasoning tokens here are a bit different than the CoTs in the answer - these are tokens that we use to reason through the research material prior to generating the outputs via the CoTs. Reasoning tokens are priced at $3/1M tokens","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-deep-research","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"47dadaf5-a2e7-4c17-ac4b-e4811f3c0a28","name":"Perplexity | perplexity/sonar-deep-research","context_length":128000,"model":{"slug":"perplexity/sonar-deep-research","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-03-07T01:34:06+00:00","hf_updated_at":null,"name":"Perplexity: Sonar Deep Research","short_name":"Sonar Deep Research","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events.\n\nNotes on Pricing ([Source](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-deep-research)) \n- Input tokens comprise of Prompt tokens (user prompt) + Citation tokens (these are processed tokens from running searches)\n- Deep Research runs multiple searches to conduct exhaustive research. Searches are priced at $5/1000 searches. A request that does 30 searches will cost $0.15 in this step.\n- Reasoning is a distinct step in Deep Research since it does extensive automated reasoning through all the material it gathers during its research phase. Reasoning tokens here are a bit different than the CoTs in the answer - these are tokens that we use to reason through the research material prior to generating the outputs via the CoTs. Reasoning tokens are priced at $3/1M tokens","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar-deep-research","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"perplexity/sonar-deep-research","model_variant_permaslug":"perplexity/sonar-deep-research","adapter_name":"PerplexityAdapter","provider_name":"Perplexity","provider_info":{"name":"Perplexity","displayName":"Perplexity","slug":"perplexity","baseUrl":"https://api.perplexity.ai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"PerplexityAdapter","statusPageUrl":"https://status.perplexity.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Perplexity.svg"},"sendClientIp":false,"pricingStrategy":"perplexity"},"provider_display_name":"Perplexity","provider_slug":"perplexity","provider_model_id":"sonar-deep-research","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy"},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","internal_reasoning":"0.000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"perplexity:prompt_tokens":0.000002,"perplexity:web_search_calls":0.005,"perplexity:completion_tokens":0.000008,"perplexity:internal_reasoning_tokens":0.000003},"pricing_version_id":"f1580a65-37ab-4ec8-8a3c-31b3a9d626eb","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-06T04:47:48.021Z","status":0}},{"slug":"mistralai/mistral-saba","hf_slug":"","updated_at":"2026-05-14T22:39:42.152Z","created_at":"2025-02-17T14:40:39.116Z","hf_updated_at":null,"name":"Mistral: Saba","short_name":"Saba","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post [here](https://mistral.ai/en/news/mistral-saba)","model_version_group_id":null,"context_length":32768,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-saba-2502","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c5a8bebe-8564-47ed-9d05-4151aa3c6e3a","name":"Mistral | mistralai/mistral-saba-2502","context_length":32768,"model":{"slug":"mistralai/mistral-saba","hf_slug":"","updated_at":"2026-05-14T22:39:42.152651+00:00","created_at":"2025-02-17T14:40:39.116446+00:00","hf_updated_at":null,"name":"Mistral: Saba","short_name":"Saba","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post [here](https://mistral.ai/en/news/mistral-saba)","model_version_group_id":null,"context_length":32000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-saba-2502","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-saba","model_variant_permaslug":"mistralai/mistral-saba-2502","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"mistral-saba-2502","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.0000006","input_cache_read":"0.00000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":2e-7,"mistral:completion_tokens":6e-7,"mistral:cached_prompt_tokens":"2e-8"},"pricing_version_id":"27c1ea75-e219-46b8-9b76-824ad6ba5ec2","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-17T15:45:06.399Z","status":0}},{"slug":"openai/o3-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-02-12T15:03:31.504Z","hf_updated_at":null,"name":"OpenAI: o3 Mini High (batch)","short_name":"o3 Mini High (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. \n\no3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-high-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a83f2cdf-6a2e-477a-95bc-40abbed882e6","name":"OpenAI | openai/o3-mini-high-2025-01-31:batch","context_length":200000,"model":{"slug":"openai/o3-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-02-12T15:03:31.504126+00:00","hf_updated_at":null,"name":"OpenAI: o3 Mini High","short_name":"o3 Mini High","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. \n\no3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-high-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3-mini-high:batch","model_variant_permaslug":"openai/o3-mini-high-2025-01-31:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-mini-2025-01-31","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000055","completion":"0.0000022","input_cache_read":"0.000000275","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"5.500000e-7","openai_responses:completion_tokens":"2.200000e-6","openai_responses:cached_prompt_tokens":"2.750000e-7"},"pricing_version_id":"f97a46c5-2bb7-4339-b352-64f665fa49c4","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:34.370Z","status":0}},{"slug":"openai/o3-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-02-12T15:03:31.504Z","hf_updated_at":null,"name":"OpenAI: o3 Mini High","short_name":"o3 Mini High","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. \n\no3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-high-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4a8663f2-89f3-40e9-9b50-e4838fff0155","name":"OpenAI | openai/o3-mini-high-2025-01-31","context_length":200000,"model":{"slug":"openai/o3-mini-high","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-02-12T15:03:31.504126+00:00","hf_updated_at":null,"name":"OpenAI: o3 Mini High","short_name":"o3 Mini High","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. \n\no3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-high-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null,"is_mandatory_reasoning":true,"supports_reasoning_effort":true,"supports_reasoning_max_tokens":null,"supported_reasoning_efforts":["high"],"default_reasoning_effort":null,"default_reasoning_enabled":null},"chat_template_config":{"should_hoist_and_merge_system_messages":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3-mini-high","model_variant_permaslug":"openai/o3-mini-high-2025-01-31","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-mini-2025-01-31","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000011","completion":"0.0000044","input_cache_read":"0.00000055","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.0000011,"openai_responses:completion_tokens":0.0000044,"openai_responses:cached_prompt_tokens":5.5e-7},"pricing_version_id":"ee560516-0eb0-42c2-9a61-6922364568a4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-12T15:04:19.481Z","status":0}},{"slug":"aion-labs/aion-rp-llama-3.1-8b","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-02-04T19:18:38.521Z","hf_updated_at":null,"name":"AionLabs: Aion-RP 1.0 (8B)","short_name":"Aion-RP 1.0 (8B)","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-rp-llama-3.1-8b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"fd456f92-a506-4249-8527-988e9c1d84b3","name":"AionLabs | aion-labs/aion-rp-llama-3.1-8b","context_length":32768,"model":{"slug":"aion-labs/aion-rp-llama-3.1-8b","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-02-04T19:18:38.521648+00:00","hf_updated_at":null,"name":"AionLabs: Aion-RP 1.0 (8B)","short_name":"Aion-RP 1.0 (8B)","author":"aion-labs","author_display_name":"Aion Labs","author_icon_uri":null,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"aion-labs/aion-rp-llama-3.1-8b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"aion-labs/aion-rp-llama-3.1-8b","model_variant_permaslug":"aion-labs/aion-rp-llama-3.1-8b","adapter_name":"OpenAIAdapter","provider_name":"AionLabs","provider_info":{"name":"AionLabs","displayName":"AionLabs","slug":"aion-labs","baseUrl":"https://api.aionlabs.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/","requiresUserIDs":false},"headquarters":"IL","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"OpenAIAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.aionlabs.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"AionLabs","provider_slug":"aion-labs","provider_model_id":"aion-labs/aion-rp-llama-3.1-8b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://www.aionlabs.ai/terms/","privacyPolicyURL":"https://www.aionlabs.ai/privacy-policy/"},"pricing":{"prompt":"0.0000008","completion":"0.0000016","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"8e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000016","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"8e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000016","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":8e-7,"openai:completion_tokens":0.0000016},"pricing_version_id":"09878d6b-5be5-48cb-bc3e-5a3c1a00618c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-04T19:22:02.609Z","status":0}},{"slug":"qwen/qwen2.5-vl-72b-instruct","hf_slug":"Qwen/Qwen2.5-VL-72B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-02-01T11:45:11.997Z","hf_updated_at":null,"name":"Qwen: Qwen2.5 VL 72B Instruct","short_name":"Qwen2.5 VL 72B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen2.5-vl-72b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c61ab1c0-3660-4391-8385-773c7a3d1de8","name":"Nebius | qwen/qwen2.5-vl-72b-instruct","context_length":32000,"model":{"slug":"qwen/qwen2.5-vl-72b-instruct","hf_slug":"Qwen/Qwen2.5-VL-72B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-02-01T11:45:11.997326+00:00","hf_updated_at":null,"name":"Qwen: Qwen2.5 VL 72B Instruct","short_name":"Qwen2.5 VL 72B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","model_version_group_id":null,"context_length":131072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen2.5-vl-72b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen2.5-vl-72b-instruct","model_variant_permaslug":"qwen/qwen2.5-vl-72b-instruct","adapter_name":"NebiusAdapter","provider_name":"Nebius","provider_info":{"name":"Nebius","displayName":"Nebius Token Factory","slug":"nebius","baseUrl":"https://api.studio.nebius.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.nebius.com/legal/studio/terms-of-use/","privacyPolicyURL":"https://docs.nebius.com/legal/studio/privacy/","requiresUserIDs":false},"headquarters":"NL","hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NebiusAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://docs.nebius.com/&size=256","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Nebius Token Factory","provider_slug":"nebius/fp8","provider_model_id":"Qwen/Qwen2.5-VL-72B-Instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://docs.nebius.com/legal/studio/terms-of-use/","privacyPolicyURL":"https://docs.nebius.com/legal/studio/privacy/"},"pricing":{"prompt":"0.00000025","completion":"0.00000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000025","openai:completion_tokens":"0.00000075"},"pricing_version_id":"3604eace-252c-4b44-b301-a063b439bc3d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-12T02:21:41.369Z","status":-2}},{"slug":"qwen/qwen-plus","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-02-01T11:37:20.886Z","hf_updated_at":null,"name":"Qwen: Qwen-Plus","short_name":"Qwen-Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","model_version_group_id":null,"context_length":1000000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-plus-2025-01-25","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"47e88ae3-94ed-4d6a-96bb-a150dd354853","name":"Alibaba | qwen/qwen-plus-2025-01-25","context_length":1000000,"model":{"slug":"qwen/qwen-plus","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-02-01T11:37:20.886831+00:00","hf_updated_at":null,"name":"Qwen: Qwen-Plus","short_name":"Qwen-Plus","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-plus-2025-01-25","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2025-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen-plus","model_variant_permaslug":"qwen/qwen-plus-2025-01-25","adapter_name":"AlibabaAdapter","provider_name":"Alibaba","provider_info":{"name":"Alibaba","displayName":"Alibaba Cloud Int.","slug":"alibaba","baseUrl":"https://llm-6nbyml54yaaqvdb9.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["SG","CN"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"AlibabaAdapter","statusPageUrl":"https://status.alibabacloud.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.alibabacloud.com/&size=256"},"sendClientIp":false,"pricingStrategy":"alibaba"},"provider_display_name":"Alibaba Cloud Int.","provider_slug":"alibaba","provider_model_id":"qwen-plus","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":995904,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","privacyPolicyURL":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy"},"pricing":{"prompt":"0.00000026","completion":"0.00000078","input_cache_read":"0.000000052","input_cache_write":"0.000000325","discount":0,"overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234","input_cache_read":"0.000000156","input_cache_write":"0.000000975"}],"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.00000078"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000078"},{"sku_label":">256K","price":"0.00000234"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000052","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000052"},{"sku_label":">256K","price":"0.000000156"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000325"},{"sku_label":">256K","price":"0.000000975"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000026"},{"sku_label":">256K","price":"0.000000078"}]}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000026"},{"sku_label":">256K","price":"0.00000078"}]},{"kind":"token","sku_label":"Output Price","price":"0.00000078","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.00000078"},{"sku_label":">256K","price":"0.00000234"}]},{"kind":"token","sku_label":"Cache Read","price":"0.000000052","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000052"},{"sku_label":">256K","price":"0.000000156"}]},{"kind":"token","sku_label":"Cache Creation (5min)","price":"0.000000325","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000325"},{"sku_label":">256K","price":"0.000000975"}]},{"kind":"token","sku_label":"Cache Read (5min)","price":"0.000000026","displayMultiplier":1000000,"unitLabel":"/M tokens","tiers":[{"sku_label":"≤256K","price":"0.000000026"},{"sku_label":">256K","price":"0.000000078"}]}],"pricing_json":{"alibaba:prompt_tokens":"0.00000026","alibaba:tier2_threshold":"256000","alibaba:completion_tokens":"0.00000078","alibaba:prompt_tokens_tier2":"0.00000078","alibaba:cached_prompt_tokens":"0.000000052","alibaba:cache_creation_tokens":"0.000000325","alibaba:completion_tokens_tier2":"0.00000234","alibaba:cached_prompt_tokens_tier2":"0.000000156","alibaba:cache_creation_tokens_tier2":"0.000000975","alibaba:explicit_cached_prompt_tokens":"0.000000026","alibaba:explicit_cached_prompt_tokens_tier2":"0.000000078"},"pricing_version_id":"bce4d93d-0060-45e9-aaa9-bb87a7ff5de5","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-01T11:39:07.039Z","status":0}},{"slug":"openai/o3-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-01-31T19:28:41.132Z","hf_updated_at":null,"name":"OpenAI: o3 Mini (batch)","short_name":"o3 Mini (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\n\nThis model supports the `reasoning_effort` parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to \"high\".\n\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"af1c0e88-eeb7-4255-9767-28ac87cbb2c8","name":"OpenAI | openai/o3-mini-2025-01-31:batch","context_length":200000,"model":{"slug":"openai/o3-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-01-31T19:28:41.132151+00:00","hf_updated_at":null,"name":"OpenAI: o3 Mini","short_name":"o3 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\n\nThis model supports the `reasoning_effort` parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to \"high\".\n\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3-mini:batch","model_variant_permaslug":"openai/o3-mini-2025-01-31:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-mini-2025-01-31","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000055","completion":"0.0000022","input_cache_read":"0.000000275","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"2.200000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"2.750000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"5.500000e-7","openai_responses:completion_tokens":"2.200000e-6","openai_responses:cached_prompt_tokens":"2.750000e-7"},"pricing_version_id":"5346ef5c-9dbf-46b9-a129-7f08289ba4ea","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:09:01.324Z","status":0}},{"slug":"openai/o3-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2025-01-31T19:28:41.132Z","hf_updated_at":null,"name":"OpenAI: o3 Mini","short_name":"o3 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\n\nThis model supports the `reasoning_effort` parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to \"high\".\n\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e93c942e-7f8f-410d-8478-21ec37bc6b0d","name":"OpenAI | openai/o3-mini-2025-01-31","context_length":200000,"model":{"slug":"openai/o3-mini","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2025-01-31T19:28:41.132151+00:00","hf_updated_at":null,"name":"OpenAI: o3 Mini","short_name":"o3 Mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\n\nThis model supports the `reasoning_effort` parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to \"high\".\n\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_version_group_id":null,"context_length":200000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o3-mini-2025-01-31","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o3-mini","model_variant_permaslug":"openai/o3-mini-2025-01-31","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o3-mini-2025-01-31","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000011","completion":"0.0000044","input_cache_read":"0.00000055","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000044","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"5.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.0000011,"openai_responses:completion_tokens":0.0000044,"openai_responses:cached_prompt_tokens":5.5e-7},"pricing_version_id":"4ac49c66-ad86-4d44-b4f9-bf7c11b1a86c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-01-31T19:30:05.479Z","status":0}},{"slug":"mistralai/mistral-small-24b-instruct-2501","hf_slug":"mistralai/Mistral-Small-24B-Instruct-2501","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-01-30T16:43:29.335Z","hf_updated_at":null,"name":"Mistral: Mistral Small 3","short_name":"Mistral Small 3","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.\n\nThe model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-24b-instruct-2501","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a911739a-dc2e-424d-a221-5c776f1552f0","name":"DeepInfra | mistralai/mistral-small-24b-instruct-2501","context_length":32768,"model":{"slug":"mistralai/mistral-small-24b-instruct-2501","hf_slug":"mistralai/Mistral-Small-24B-Instruct-2501","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-01-30T16:43:29.33592+00:00","hf_updated_at":null,"name":"Mistral: Mistral Small 3","short_name":"Mistral Small 3","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.\n\nThe model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-small-24b-instruct-2501","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-small-24b-instruct-2501","model_variant_permaslug":"mistralai/mistral-small-24b-instruct-2501","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"mistralai/Mistral-Small-24B-Instruct-2501","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000005","completion":"0.00000008","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000005","openai:completion_tokens":"0.00000008"},"pricing_version_id":"bc7c1548-b7f7-4d31-bb37-1523ef1115e9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-01T00:57:07.046Z","status":0}},{"slug":"perplexity/sonar","hf_slug":"","updated_at":"2025-11-10T16:00:38.246Z","created_at":"2025-01-27T21:36:48.666Z","hf_updated_at":null,"name":"Perplexity: Sonar","short_name":"Sonar","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.","model_version_group_id":null,"context_length":127072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"5f831e7a-c555-4d3a-b228-88286347558a","name":"Perplexity | perplexity/sonar","context_length":127072,"model":{"slug":"perplexity/sonar","hf_slug":"","updated_at":"2025-11-10T16:00:38.246665+00:00","created_at":"2025-01-27T21:36:48.666939+00:00","hf_updated_at":null,"name":"Perplexity: Sonar","short_name":"Sonar","author":"perplexity","author_display_name":"Perplexity","author_icon_uri":null,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.","model_version_group_id":null,"context_length":127072,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"perplexity/sonar","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"perplexity/sonar","model_variant_permaslug":"perplexity/sonar","adapter_name":"PerplexityAdapter","provider_name":"Perplexity","provider_info":{"name":"Perplexity","displayName":"Perplexity","slug":"perplexity","baseUrl":"https://api.perplexity.ai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"PerplexityAdapter","statusPageUrl":"https://status.perplexity.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Perplexity.svg"},"sendClientIp":false,"pricingStrategy":"perplexity"},"provider_display_name":"Perplexity","provider_slug":"perplexity","provider_model_id":"sonar","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","privacyPolicyURL":"https://www.perplexity.ai/hub/legal/privacy-policy"},"pricing":{"prompt":"0.000001","completion":"0.000001","web_search":"0.005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"unit","sku_label":"Web Search","price":"0.005","displayMultiplier":1000,"unitLabel":"/1K calls","isServerTool":true}],"pricing_json":{"perplexity:prompt_tokens":0.000001,"perplexity:web_search_calls":0.005,"perplexity:completion_tokens":0.000001},"pricing_version_id":"5d62ac7f-188c-48b0-9061-8a3018af86a4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-01-28T14:37:22.960Z","status":0}},{"slug":"deepseek/deepseek-r1-distill-llama-70b","hf_slug":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-01-23T20:12:49.780Z","hf_updated_at":null,"name":"DeepSeek: R1 Distill Llama 70B","short_name":"R1 Distill Llama 70B","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:\n\n- AIME 2024 pass@1: 70.0\n- MATH-500 pass@1: 94.5\n- CodeForces Rating: 1633\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.","model_version_group_id":"92d90d33-1fa7-4537-b283-b8199ac69987","context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-r1-distill-llama-70b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"797ebc09-6e53-4795-9d9e-2669ce7aee03","name":"Novita | deepseek/deepseek-r1-distill-llama-70b","context_length":8192,"model":{"slug":"deepseek/deepseek-r1-distill-llama-70b","hf_slug":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-01-23T20:12:49.780212+00:00","hf_updated_at":null,"name":"DeepSeek: R1 Distill Llama 70B","short_name":"R1 Distill Llama 70B","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:\n\n- AIME 2024 pass@1: 70.0\n- MATH-500 pass@1: 94.5\n- CodeForces Rating: 1633\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.","model_version_group_id":"92d90d33-1fa7-4537-b283-b8199ac69987","context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-r1-distill-llama-70b","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>"},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>"}},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-r1-distill-llama-70b","model_variant_permaslug":"deepseek/deepseek-r1-distill-llama-70b","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/bf16","provider_model_id":"deepseek/deepseek-r1-distill-llama-70b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000008","completion":"0.0000008","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000008","openai:completion_tokens":"0.0000008"},"pricing_version_id":"1d65ae70-0a0e-4dd5-af9a-3be1d8a9143b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":false,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-01-27T15:47:09.576Z","status":0}},{"slug":"deepseek/deepseek-r1","hf_slug":"deepseek-ai/DeepSeek-R1","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-01-20T13:51:35.969Z","hf_updated_at":null,"name":"DeepSeek: R1","short_name":"R1","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nFully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120).\n\nMIT licensed: Distill & commercialize freely!","model_version_group_id":"92d90d33-1fa7-4537-b283-b8199ac69987","context_length":64000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-r1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"cca51d1b-db1d-44d2-bc90-268311214746","name":"Novita | deepseek/deepseek-r1","context_length":64000,"model":{"slug":"deepseek/deepseek-r1","hf_slug":"deepseek-ai/DeepSeek-R1","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-01-20T13:51:35.96912+00:00","hf_updated_at":null,"name":"DeepSeek: R1","short_name":"R1","author":"deepseek","author_display_name":"DeepSeek","author_icon_uri":null,"description":"DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nFully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120).\n\nMIT licensed: Distill & commercialize freely!","model_version_group_id":"92d90d33-1fa7-4537-b283-b8199ac69987","context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":"deepseek-r1","default_system":null,"default_stops":["<｜User｜>","<｜end▁of▁sentence｜>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-r1","supports_reasoning":true,"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"features":{"reasoning_config":{"start_token":"<think>","end_token":"</think>","is_mandatory_reasoning":true},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-r1","model_variant_permaslug":"deepseek/deepseek-r1","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/fp8","provider_model_id":"deepseek/deepseek-r1-turbo","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.0000007","completion":"0.0000025","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000007","openai:completion_tokens":"0.0000025"},"pricing_version_id":"a3d47c1d-44b5-46be-8c2e-e2f273301746","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-03-06T16:34:52.488Z","status":0}},{"slug":"minimax/minimax-01","hf_slug":"MiniMaxAI/MiniMax-Text-01","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-01-15T04:31:02.677Z","hf_updated_at":null,"name":"MiniMax: MiniMax-01","short_name":"MiniMax-01","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens.\n\nThe text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model.\n\nTo read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2","model_version_group_id":null,"context_length":1000192,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-01","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"352546d2-3758-4aa1-9e98-e1a83748aa4e","name":"Minimax | minimax/minimax-01","context_length":1000192,"model":{"slug":"minimax/minimax-01","hf_slug":"MiniMaxAI/MiniMax-Text-01","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-01-15T04:31:02.677929+00:00","hf_updated_at":null,"name":"MiniMax: MiniMax-01","short_name":"MiniMax-01","author":"minimax","author_display_name":"MiniMax","author_icon_uri":null,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens.\n\nThe text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model.\n\nTo read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2","model_version_group_id":null,"context_length":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"minimax/minimax-01","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null},"features":{"reasoning_config":{"start_token":null,"end_token":null},"chat_template_config":{"should_hoist_and_merge_system_messages":true}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"minimax/minimax-01","model_variant_permaslug":"minimax/minimax-01","adapter_name":"MinimaxAdapter","provider_name":"Minimax","provider_info":{"name":"Minimax","displayName":"MiniMax","slug":"minimax","baseUrl":"https://api.minimaxi.chat/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy","requiresUserIDs":false},"headquarters":"SG","datacenters":["US"],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MinimaxAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://minimaxi.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"MiniMax","provider_slug":"minimax","provider_model_id":"MiniMax-Text-01","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":1000192,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.minimax.io/platform/protocol/terms-of-service","privacyPolicyURL":"https://www.minimax.io/platform/protocol/privacy-policy"},"pricing":{"prompt":"0.0000002","completion":"0.0000011","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000002","openai:completion_tokens":"0.0000011"},"pricing_version_id":"6bea1ceb-8249-4f88-b48c-f90eb7df1ab0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-01-15T04:48:09.375Z","status":0}},{"slug":"microsoft/phi-4","hf_slug":"microsoft/phi-4","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2025-01-10T06:17:52.163Z","hf_updated_at":null,"name":"Microsoft: Phi 4","short_name":"Phi 4","author":"microsoft","author_display_name":"Microsoft","author_icon_uri":null,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. \n\nAt 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs.\n\nFor more information, please see [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)\n","model_version_group_id":null,"context_length":16384,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"microsoft/phi-4","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8e48942d-17fc-4d00-a234-4723034fd971","name":"DeepInfra | microsoft/phi-4","context_length":16384,"model":{"slug":"microsoft/phi-4","hf_slug":"microsoft/phi-4","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2025-01-10T06:17:52.16346+00:00","hf_updated_at":null,"name":"Microsoft: Phi 4","short_name":"Phi 4","author":"microsoft","author_display_name":"Microsoft","author_icon_uri":null,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. \n\nAt 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs.\n\nFor more information, please see [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)\n","model_version_group_id":null,"context_length":16384,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Other","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"microsoft/phi-4","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"microsoft/phi-4","model_variant_permaslug":"microsoft/phi-4","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/bf16","provider_model_id":"microsoft/phi-4","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":4096,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000007","completion":"0.00000014","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000007","openai:completion_tokens":"0.00000014"},"pricing_version_id":"ab04b4f2-afae-4ea2-a903-6b6847982e09","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-01-10T06:19:23.674Z","status":0}},{"slug":"deepseek/deepseek-chat","hf_slug":"deepseek-ai/DeepSeek-V3","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-26T19:28:40.559Z","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3","short_name":"DeepSeek V3","author":"deepseek-ai","author_display_name":"deepseek-ai","author_icon_uri":null,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.\n\nFor model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).","model_version_group_id":null,"context_length":163840,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-chat-v3","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"511ddb79-1d9e-4f5f-9863-c12b0f9b80ba","name":"StreamLake | deepseek/deepseek-chat-v3","context_length":128000,"model":{"slug":"deepseek/deepseek-chat","hf_slug":"deepseek-ai/DeepSeek-V3","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-26T19:28:40.559917+00:00","hf_updated_at":null,"name":"DeepSeek: DeepSeek V3","short_name":"DeepSeek V3","author":"deepseek-ai","author_display_name":"deepseek-ai","author_icon_uri":null,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.\n\nFor model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"DeepSeek","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"deepseek/deepseek-chat-v3","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-07-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"deepseek/deepseek-chat","model_variant_permaslug":"deepseek/deepseek-chat-v3","adapter_name":"StreamLakeAdapter","provider_name":"StreamLake","provider_info":{"name":"StreamLake","displayName":"StreamLake","slug":"streamlake","baseUrl":"https://vanchin.streamlake.ai/api/gateway/v1/endpoints","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54","requiresUserIDs":false},"headquarters":"CN","datacenters":[],"hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"StreamLakeAdapter","statusPageUrl":"https://status.streamlake.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.streamlake.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"StreamLake","provider_slug":"streamlake","provider_model_id":"deepseek-v3","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16000,"max_tokens_per_image":null,"supported_parameters":["response_format","structured_outputs","tools","tool_choice","max_tokens","temperature","top_p","stop","presence_penalty"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","privacyPolicyURL":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54"},"pricing":{"prompt":"0.0000002574","completion":"0.0000010287","discount":0.1,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002574","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000010287","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000002574","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000010287","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000286","openai:completion_tokens":"0.000001143"},"pricing_version_id":"1fafbe01-f304-4bc7-9491-becc6df20ac0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-05-25T12:58:22.835Z","status":0}},{"slug":"sao10k/l3.3-euryale-70b","hf_slug":"Sao10K/L3.3-70B-Euryale-v2.3","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-18T15:32:08.468Z","hf_updated_at":null,"name":"Sao10K: Llama 3.3 Euryale 70B","short_name":"Llama 3.3 Euryale 70B","author":"sao10k","author_display_name":"Sao10K","author_icon_uri":null,"description":"Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sao10k/l3.3-euryale-70b-v2.3","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"fde3788e-a185-4487-93a7-10fb4412d412","name":"NextBit | sao10k/l3.3-euryale-70b-v2.3","context_length":131072,"model":{"slug":"sao10k/l3.3-euryale-70b","hf_slug":"Sao10K/L3.3-70B-Euryale-v2.3","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-18T15:32:08.468786+00:00","hf_updated_at":null,"name":"Sao10K: Llama 3.3 Euryale 70B","short_name":"Llama 3.3 Euryale 70B","author":"sao10k","author_display_name":"Sao10K","author_icon_uri":null,"description":"Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sao10k/l3.3-euryale-70b-v2.3","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"sao10k/l3.3-euryale-70b","model_variant_permaslug":"sao10k/l3.3-euryale-70b-v2.3","adapter_name":"NextBitAdapter","provider_name":"NextBit","provider_info":{"name":"NextBit","displayName":"NextBit","slug":"nextbit","baseUrl":"https://api.nextbit256.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy","requiresUserIDs":false},"headquarters":"ES","datacenters":["ES"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NextBitAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nextbit256.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NextBit","provider_slug":"nextbit/bf16","provider_model_id":"euryale:33-70b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","logprobs","top_logprobs","repetition_penalty","seed"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy"},"pricing":{"prompt":"0.00000065","completion":"0.00000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":6.5e-7,"openai:completion_tokens":7.5e-7},"pricing_version_id":"54ef3789-a185-4b35-98af-45899859a712","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-25T02:31:34.227Z","status":0}},{"slug":"openai/o1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2024-12-17T18:26:39.576Z","hf_updated_at":null,"name":"OpenAI: o1 (batch)","short_name":"o1 (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-2024-12-17","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"de532b26-3bce-4709-958b-f629318b5ec4","name":"OpenAI | openai/o1-2024-12-17:batch","context_length":200000,"model":{"slug":"openai/o1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2024-12-17T18:26:39.576639+00:00","hf_updated_at":null,"name":"OpenAI: o1","short_name":"o1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-2024-12-17","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o1:batch","model_variant_permaslug":"openai/o1-2024-12-17:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o1-2024-12-17","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000075","completion":"0.00003","input_cache_read":"0.00000375","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3.750000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3.000000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3.750000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"7.500000e-6","openai_responses:completion_tokens":"3.000000e-5","openai_responses:cached_prompt_tokens":"3.750000e-6"},"pricing_version_id":"4953daf2-8025-486a-b331-b3f0529292d5","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-08T18:46:31.686Z","status":0}},{"slug":"openai/o1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2024-12-17T18:26:39.576Z","hf_updated_at":null,"name":"OpenAI: o1","short_name":"o1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-2024-12-17","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"82738f61-f3cb-44a5-b5d1-e6787ae64e3b","name":"OpenAI | openai/o1-2024-12-17","context_length":200000,"model":{"slug":"openai/o1","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2024-12-17T18:26:39.576639+00:00","hf_updated_at":null,"name":"OpenAI: o1","short_name":"o1","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. \n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).\n","model_version_group_id":null,"context_length":200000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/o1-2024-12-17","supports_reasoning":true,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/o1","model_variant_permaslug":"openai/o1-2024-12-17","adapter_name":"OpenAIResponsesAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIResponsesAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"o1-2024-12-17","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":100000,"max_tokens_per_image":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000015","completion":"0.00006","input_cache_read":"0.0000075","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":0.000015,"openai_responses:completion_tokens":0.00006,"openai_responses:cached_prompt_tokens":0.0000075},"pricing_version_id":"c7fe5d08-4ae8-494a-80a6-7452307c6540","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":true,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-17T18:28:09.014Z","status":0}},{"slug":"cohere/command-r7b-12-2024","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-14T06:35:52.905Z","hf_updated_at":null,"name":"Cohere: Command R7B (12-2024)","short_name":"Command R7B (12-2024)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.\n\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-r7b-12-2024","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d4a57205-8124-413a-ab4e-5ae94eb7aa9d","name":"Cohere | cohere/command-r7b-12-2024","context_length":128000,"model":{"slug":"cohere/command-r7b-12-2024","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-14T06:35:52.905418+00:00","hf_updated_at":null,"name":"Cohere: Command R7B (12-2024)","short_name":"Command R7B (12-2024)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.\n\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-r7b-12-2024","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"cohere/command-r7b-12-2024","model_variant_permaslug":"cohere/command-r7b-12-2024","adapter_name":"CohereV2Adapter","provider_name":"Cohere","provider_info":{"name":"Cohere","displayName":"Cohere","slug":"cohere","baseUrl":"https://api.cohere.com/v2","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"CohereV2Adapter","statusPageUrl":"https://status.cohere.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Cohere.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Cohere","provider_slug":"cohere","provider_model_id":"command-r7b-12-2024","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy"},"pricing":{"prompt":"0.0000000375","completion":"0.00000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000000375","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000000375","openai:completion_tokens":"0.00000015"},"pricing_version_id":"e3cc62af-464a-4c8e-9d0c-a42eca39f8de","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-14T06:39:43.517Z","status":0}},{"slug":"meta-llama/llama-3.3-70b-instruct","hf_slug":"meta-llama/Llama-3.3-70B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-06T17:28:57.828Z","hf_updated_at":null,"name":"Meta: Llama 3.3 70B Instruct","short_name":"Llama 3.3 70B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.\n\n[Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)","model_version_group_id":"397604e2-45fa-454e-a85d-9921f5138747","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.3-70b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e3b0a527-44d6-4ea6-9ec2-6a6416a84c7c","name":"DeepInfra | meta-llama/llama-3.3-70b-instruct","context_length":131072,"model":{"slug":"meta-llama/llama-3.3-70b-instruct","hf_slug":"meta-llama/Llama-3.3-70B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-06T17:28:57.828422+00:00","hf_updated_at":null,"name":"Meta: Llama 3.3 70B Instruct","short_name":"Llama 3.3 70B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.\n\n[Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)","model_version_group_id":"397604e2-45fa-454e-a85d-9921f5138747","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.3-70b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-3.3-70b-instruct","model_variant_permaslug":"meta-llama/llama-3.3-70b-instruct","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra (Turbo)","slug":"deepinfra/turbo","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra (Turbo)","provider_slug":"deepinfra/turbo","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000001","completion":"0.00000032","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000032","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000032","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.00000032"},"pricing_version_id":"6fc8a8ef-7f84-4c52-8c87-80c189a40c73","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-06T20:17:34.263Z","status":0}},{"slug":"amazon/nova-lite-v1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-05T22:22:43.403Z","hf_updated_at":null,"name":"Amazon: Nova Lite 1.0","short_name":"Nova Lite 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.\n\nWith an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.","model_version_group_id":null,"context_length":300000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-lite-v1","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"72eda073-d180-4482-8e4f-81051cb66f7e","name":"Amazon Bedrock | amazon/nova-lite-v1","context_length":300000,"model":{"slug":"amazon/nova-lite-v1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-05T22:22:43.403315+00:00","hf_updated_at":null,"name":"Amazon: Nova Lite 1.0","short_name":"Nova Lite 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.\n\nWith an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.","model_version_group_id":null,"context_length":300000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-lite-v1","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"amazon/nova-lite-v1","model_variant_permaslug":"amazon/nova-lite-v1","adapter_name":"AmazonBedrockConverseAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"bedrock_converse"},"provider_display_name":"Amazon Bedrock (ZDR)","provider_slug":"amazon-bedrock","provider_model_id":"us.amazon.nova-lite-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":5120,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00000006","completion":"0.00000024","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000024","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"bedrock_converse:prompt_tokens":"0.00000006","bedrock_converse:completion_tokens":"0.00000024"},"pricing_version_id":"4b6c2c39-f5dd-47b0-8967-d156ba537662","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-05T22:27:13.891Z","status":0}},{"slug":"amazon/nova-micro-v1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-05T22:20:37.903Z","hf_updated_at":null,"name":"Amazon: Nova Micro 1.0","short_name":"Nova Micro 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has  simple mathematical reasoning and coding abilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-micro-v1","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"474f0074-66f9-42f0-a866-81a2ffebb001","name":"Amazon Bedrock | amazon/nova-micro-v1","context_length":128000,"model":{"slug":"amazon/nova-micro-v1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-05T22:20:37.90344+00:00","hf_updated_at":null,"name":"Amazon: Nova Micro 1.0","short_name":"Nova Micro 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has  simple mathematical reasoning and coding abilities.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-micro-v1","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"amazon/nova-micro-v1","model_variant_permaslug":"amazon/nova-micro-v1","adapter_name":"AmazonBedrockConverseAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"bedrock_converse"},"provider_display_name":"Amazon Bedrock (ZDR)","provider_slug":"amazon-bedrock","provider_model_id":"us.amazon.nova-micro-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":5120,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.000000035","completion":"0.00000014","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000035","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000014","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"bedrock_converse:prompt_tokens":"0.000000035","bedrock_converse:completion_tokens":"0.00000014"},"pricing_version_id":"7589b27d-dc47-415e-93ca-66a4ea561ef0","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-05T22:30:25.576Z","status":-2}},{"slug":"amazon/nova-pro-v1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-12-05T22:05:03.587Z","hf_updated_at":null,"name":"Amazon: Nova Pro 1.0","short_name":"Nova Pro 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\n\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.\n\n**NOTE**: Video input is not supported at this time.","model_version_group_id":null,"context_length":300000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-pro-v1","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"959381a4-8054-450f-9daf-5fcab64ba9aa","name":"Amazon Bedrock | amazon/nova-pro-v1","context_length":300000,"model":{"slug":"amazon/nova-pro-v1","hf_slug":"","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-12-05T22:05:03.587216+00:00","hf_updated_at":null,"name":"Amazon: Nova Pro 1.0","short_name":"Nova Pro 1.0","author":"amazon","author_display_name":"Amazon","author_icon_uri":null,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\n\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.\n\n**NOTE**: Video input is not supported at this time.","model_version_group_id":null,"context_length":300000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Nova","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"amazon/nova-pro-v1","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"amazon/nova-pro-v1","model_variant_permaslug":"amazon/nova-pro-v1","adapter_name":"AmazonBedrockConverseAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"bedrock_converse"},"provider_display_name":"Amazon Bedrock (ZDR)","provider_slug":"amazon-bedrock","provider_model_id":"us.amazon.nova-pro-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":5120,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.0000008","completion":"0.0000032","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000032","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000008","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000032","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"bedrock_converse:prompt_tokens":"0.0000008","bedrock_converse:completion_tokens":"0.0000032"},"pricing_version_id":"33de5013-47c1-4e1a-9544-ed42d9ecaa82","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-05T22:08:13.840Z","status":0}},{"slug":"openai/gpt-4o-2024-11-20","hf_slug":"","updated_at":"2026-04-11T05:55:25.761Z","created_at":"2024-11-20T18:33:14.771Z","hf_updated_at":null,"name":"OpenAI: GPT-4o (2024-11-20)","short_name":"GPT-4o (2024-11-20)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-2024-11-20","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3e86b7c5-bffe-4b60-a3dd-b36451978775","name":"OpenAI | openai/gpt-4o-2024-11-20","context_length":128000,"model":{"slug":"openai/gpt-4o-2024-11-20","hf_slug":"","updated_at":"2026-04-11T05:55:25.761505+00:00","created_at":"2024-11-20T18:33:14.771895+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o (2024-11-20)","short_name":"GPT-4o (2024-11-20)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-2024-11-20","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":["openai","azure"],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o-2024-11-20","model_variant_permaslug":"openai/gpt-4o-2024-11-20","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4o-2024-11-20","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.0000025,"openai:completion_tokens":0.00001,"openai:cached_prompt_tokens":0.00000125},"pricing_version_id":"8359b48b-204e-47a6-aea1-737dba83e20c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-20T18:34:39.762Z","status":0}},{"slug":"mistralai/mistral-large-2407","hf_slug":"","updated_at":"2026-05-14T22:39:43.392Z","created_at":"2024-11-19T01:06:55.274Z","hf_updated_at":null,"name":"Mistral Large 2407","short_name":"Mistral Large 2407","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).\n\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.\n","model_version_group_id":"83129748-0564-4485-982a-d7a37a1ef3ec","context_length":131072,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-large-2407","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"4a128170-b056-42d7-8462-a5cea647f9ad","name":"Mistral | mistralai/mistral-large-2407","context_length":131072,"model":{"slug":"mistralai/mistral-large-2407","hf_slug":"","updated_at":"2026-05-14T22:39:43.392636+00:00","created_at":"2024-11-19T01:06:55.27469+00:00","hf_updated_at":null,"name":"Mistral Large 2407","short_name":"Mistral Large 2407","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).\n\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.\n","model_version_group_id":"83129748-0564-4485-982a-d7a37a1ef3ec","context_length":128000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-large-2407","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-large-2407","model_variant_permaslug":"mistralai/mistral-large-2407","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"mistral-large-2407","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.000002","mistral:completion_tokens":0.000006,"mistral:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"af0a1f36-618d-4aba-9cd1-8edf06ca3d48","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-19T01:08:22.651Z","status":0}},{"slug":"qwen/qwen-2.5-coder-32b-instruct","hf_slug":"Qwen/Qwen2.5-Coder-32B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-11-11T23:40:00.276Z","hf_updated_at":null,"name":"Qwen2.5 Coder 32B Instruct","short_name":"Qwen2.5 Coder 32B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:\n\n- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. \n- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.\n\nTo read more about its evaluation results, check out [Qwen 2.5 Coder's blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-2.5-coder-32b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3ad816a5-5e65-4f9a-8d4b-da3c1ddb20fe","name":"Cloudflare | qwen/qwen-2.5-coder-32b-instruct","context_length":32768,"model":{"slug":"qwen/qwen-2.5-coder-32b-instruct","hf_slug":"Qwen/Qwen2.5-Coder-32B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-11-11T23:40:00.276653+00:00","hf_updated_at":null,"name":"Qwen2.5 Coder 32B Instruct","short_name":"Qwen2.5 Coder 32B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:\n\n- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. \n- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.\n\nTo read more about its evaluation results, check out [Qwen 2.5 Coder's blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-2.5-coder-32b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen-2.5-coder-32b-instruct","model_variant_permaslug":"qwen/qwen-2.5-coder-32b-instruct","adapter_name":"CloudflareAdapter","provider_name":"Cloudflare","provider_info":{"name":"Cloudflare","displayName":"Cloudflare","slug":"cloudflare","baseUrl":"https://api.cloudflare.com/client/v4/accounts/{accountId}/ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"CloudflareAdapter","statusPageUrl":"https://www.cloudflarestatus.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.cloudflare.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Cloudflare","provider_slug":"cloudflare","provider_model_id":"@cf/qwen/qwen2.5-coder-32b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy"},"pricing":{"prompt":"0.00000066","completion":"0.000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000066","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000066","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000066","openai:completion_tokens":"0.000001"},"pricing_version_id":"e07baf8a-915e-4c0d-aeec-3b8b2bdf0ff6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-04-25T13:48:10.216Z","status":0}},{"slug":"thedrummer/unslopnemo-12b","hf_slug":"TheDrummer/UnslopNemo-12B-v4.1","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-11-08T22:04:08.359Z","hf_updated_at":null,"name":"TheDrummer: UnslopNemo 12B","short_name":"UnslopNemo 12B","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","model_version_group_id":null,"context_length":1024000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"mistral","default_system":null,"default_stops":["[INST]","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/unslopnemo-12b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"08cb2fef-fad6-4a41-b292-b2d79f782a08","name":"NextBit | thedrummer/unslopnemo-12b","context_length":32768,"model":{"slug":"thedrummer/unslopnemo-12b","hf_slug":"TheDrummer/UnslopNemo-12B-v4.1","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-11-08T22:04:08.359811+00:00","hf_updated_at":null,"name":"TheDrummer: UnslopNemo 12B","short_name":"UnslopNemo 12B","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","model_version_group_id":null,"context_length":32000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"mistral","default_system":null,"default_stops":["[INST]","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/unslopnemo-12b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"thedrummer/unslopnemo-12b","model_variant_permaslug":"thedrummer/unslopnemo-12b","adapter_name":"NextBitAdapter","provider_name":"NextBit","provider_info":{"name":"NextBit","displayName":"NextBit","slug":"nextbit","baseUrl":"https://api.nextbit256.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy","requiresUserIDs":false},"headquarters":"ES","datacenters":["ES"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NextBitAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nextbit256.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NextBit","provider_slug":"nextbit/fp8","provider_model_id":"unslopnemo:12b","quantization":"fp8","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy"},"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"4e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":4e-7,"openai:completion_tokens":4e-7},"pricing_version_id":"13085bfe-e054-4fd8-8955-03ca161cc67e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-06-24T03:26:09.625Z","status":0}},{"slug":"anthracite-org/magnum-v4-72b","hf_slug":"anthracite-org/magnum-v4-72b","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-10-22T00:00:00.000Z","hf_updated_at":null,"name":"Magnum v4 72B","short_name":"Magnum v4 72B","author":"anthracite-org","author_display_name":"anthracite-org","author_icon_uri":null,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthracite-org/magnum-v4-72b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7f8d0c76-0eab-4606-9f4c-d0b4414e2cf1","name":"Mancer 2 | anthracite-org/magnum-v4-72b","context_length":32768,"model":{"slug":"anthracite-org/magnum-v4-72b","hf_slug":"anthracite-org/magnum-v4-72b","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-10-22T00:00:00+00:00","hf_updated_at":null,"name":"Magnum v4 72B","short_name":"Magnum v4 72B","author":"anthracite-org","author_display_name":"anthracite-org","author_icon_uri":null,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthracite-org/magnum-v4-72b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthracite-org/magnum-v4-72b","model_variant_permaslug":"anthracite-org/magnum-v4-72b","adapter_name":"MancerAdapter","provider_name":"Mancer 2","provider_info":{"name":"Mancer 2","displayName":"Mancer","slug":"mancer","baseUrl":"https://neuro.mancer.tech/oai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://mancer.tech/terms","privacyPolicyURL":"https://mancer.tech/privacy","requiresUserIDs":false},"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"MancerAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://mancer.tech/&size=256"},"sendClientIp":false,"pricingStrategy":"mancer"},"provider_display_name":"Mancer","provider_slug":"mancer/fp8","provider_model_id":"magnum-72b-v4","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://mancer.tech/terms","privacyPolicyURL":"https://mancer.tech/privacy"},"pricing":{"prompt":"0.000003","completion":"0.000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mancer:prompt_tokens":"0.000003","mancer:completion_tokens":"0.000005","mancer:upstream_cost_credits":"1"},"pricing_version_id":"18f58619-5934-47ad-b3cf-49b2b91673fc","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:09.275Z","status":0}},{"slug":"mistralai/ministral-8b","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-10-17T00:00:00.000Z","hf_updated_at":null,"name":"Mistral: Ministral 8B","short_name":"Ministral 8B","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-8b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"0a62b246-7f44-4b1f-ba77-fafbe88d2f37","name":"Mistral | mistralai/ministral-8b","context_length":128000,"model":{"slug":"mistralai/ministral-8b","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-10-17T00:00:00+00:00","hf_updated_at":null,"name":"Mistral: Ministral 8B","short_name":"Ministral 8B","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/ministral-8b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/ministral-8b","model_variant_permaslug":"mistralai/ministral-8b","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.us.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral/us","provider_model_id":"ministral-8b-2410","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.00000011","completion":"0.00000011","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000011","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.00000011","mistral:completion_tokens":"0.00000011"},"pricing_version_id":"c3e631e4-1b7d-4473-8c09-2718a52e2915","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":"us","deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-08-19T19:01:07.202Z","status":0}},{"slug":"qwen/qwen-2.5-7b-instruct","hf_slug":"Qwen/Qwen2.5-7B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-10-16T00:00:00.000Z","hf_updated_at":null,"name":"Qwen: Qwen2.5 7B Instruct","short_name":"Qwen2.5 7B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n\n- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n\n- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n\n- Long-context Support up to 128K tokens and can generate up to 8K tokens.\n\n- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-2.5-7b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3a6186c9-0ece-4797-9f97-45d7fab8c546","name":"Phala | qwen/qwen-2.5-7b-instruct","context_length":32768,"model":{"slug":"qwen/qwen-2.5-7b-instruct","hf_slug":"Qwen/Qwen2.5-7B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-10-16T00:00:00+00:00","hf_updated_at":null,"name":"Qwen: Qwen2.5 7B Instruct","short_name":"Qwen2.5 7B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n\n- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n\n- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n\n- Long-context Support up to 128K tokens and can generate up to 8K tokens.\n\n- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-2.5-7b-instruct","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null}},"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen-2.5-7b-instruct","model_variant_permaslug":"qwen/qwen-2.5-7b-instruct","adapter_name":"PhalaAdapter","provider_name":"Phala","provider_info":{"name":"Phala","displayName":"Phala","slug":"phala","baseUrl":"https://api.redpill.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://redpill.ai/terms","privacyPolicyURL":"https://redpill.ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"PhalaAdapter","statusPageUrl":"https://status.phala.network/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://phala.network/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Phala","provider_slug":"phala","provider_model_id":"phala/qwen-2.5-7b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":32768,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":["logprobs","top_logprobs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://redpill.ai/terms","privacyPolicyURL":"https://redpill.ai/privacy"},"pricing":{"prompt":"0.0000001","completion":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000001","openai:completion_tokens":"0.0000002"},"pricing_version_id":"97d7b182-9912-410a-8ceb-e2718836fcaa","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":false,"literal_auto":true,"literal_required":false,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-05-19T15:32:27.582Z","status":0}},{"slug":"thedrummer/rocinante-12b","hf_slug":"TheDrummer/Rocinante-12B-v1.1","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-09-30T00:00:00.000Z","hf_updated_at":null,"name":"TheDrummer: Rocinante 12B","short_name":"Rocinante 12B","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"Rocinante 12B is designed for engaging storytelling and rich prose.\n\nEarly testers have reported:\n- Expanded vocabulary with unique and expressive word choices\n- Enhanced creativity for vivid narratives\n- Adventure-filled and captivating stories","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/rocinante-12b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"b3f948bb-397c-4d34-bceb-188ac77c5d81","name":"Parasail | thedrummer/rocinante-12b","context_length":65536,"model":{"slug":"thedrummer/rocinante-12b","hf_slug":"TheDrummer/Rocinante-12B-v1.1","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-09-30T00:00:00+00:00","hf_updated_at":null,"name":"TheDrummer: Rocinante 12B","short_name":"Rocinante 12B","author":"thedrummer","author_display_name":"Drummer","author_icon_uri":null,"description":"Rocinante 12B is designed for engaging storytelling and rich prose.\n\nEarly testers have reported:\n- Expanded vocabulary with unique and expressive word choices\n- Enhanced creativity for vivid narratives\n- Adventure-filled and captivating stories","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"thedrummer/rocinante-12b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"thedrummer/rocinante-12b","model_variant_permaslug":"thedrummer/rocinante-12b","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-rocinante-12b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":65536,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000025","completion":"0.0000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000025","openai:completion_tokens":"0.0000005"},"pricing_version_id":"b1afb512-0f99-440d-a782-e5284dd81871","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T01:16:46.240Z","status":0}},{"slug":"meta-llama/llama-3.2-1b-instruct","hf_slug":"meta-llama/Llama-3.2-1B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-09-25T00:00:00.000Z","hf_updated_at":null,"name":"Meta: Llama 3.2 1B Instruct","short_name":"Llama 3.2 1B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance.\n\nSupporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","model_version_group_id":null,"context_length":60000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.2-1b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"6a1461d2-2074-404f-8202-bd5d52971983","name":"Cloudflare | meta-llama/llama-3.2-1b-instruct","context_length":60000,"model":{"slug":"meta-llama/llama-3.2-1b-instruct","hf_slug":"meta-llama/Llama-3.2-1B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-09-25T00:00:00+00:00","hf_updated_at":null,"name":"Meta: Llama 3.2 1B Instruct","short_name":"Llama 3.2 1B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance.\n\nSupporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.2-1b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-3.2-1b-instruct","model_variant_permaslug":"meta-llama/llama-3.2-1b-instruct","adapter_name":"CloudflareAdapter","provider_name":"Cloudflare","provider_info":{"name":"Cloudflare","displayName":"Cloudflare","slug":"cloudflare","baseUrl":"https://api.cloudflare.com/client/v4/accounts/{accountId}/ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"CloudflareAdapter","statusPageUrl":"https://www.cloudflarestatus.com/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.cloudflare.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_extended"},"provider_display_name":"Cloudflare","provider_slug":"cloudflare","provider_model_id":"@cf/meta/llama-3.2-1b-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":60000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","privacyPolicyURL":"https://developers.cloudflare.com/workers-ai/privacy"},"pricing":{"prompt":"0.000000027","completion":"0.000000201","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000201","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000027","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000000201","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000027","openai:completion_tokens":"0.000000201"},"pricing_version_id":"8ff3e2d4-b45a-4568-9ccc-23069662b1d4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-03T19:00:09.858Z","status":0}},{"slug":"meta-llama/llama-3.2-3b-instruct","hf_slug":"meta-llama/Llama-3.2-3B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-09-25T00:00:00.000Z","hf_updated_at":null,"name":"Meta: Llama 3.2 3B Instruct","short_name":"Llama 3.2 3B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.\n\nTrained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.2-3b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"87c79cad-7b66-421b-82a0-b6026faef55f","name":"Parasail | meta-llama/llama-3.2-3b-instruct","context_length":131072,"model":{"slug":"meta-llama/llama-3.2-3b-instruct","hf_slug":"meta-llama/Llama-3.2-3B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-09-25T00:00:00+00:00","hf_updated_at":null,"name":"Meta: Llama 3.2 3B Instruct","short_name":"Llama 3.2 3B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.\n\nTrained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.2-3b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-3.2-3b-instruct","model_variant_permaslug":"meta-llama/llama-3.2-3b-instruct","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-llama-32-3b-instruct","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":131072,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000005","completion":"0.00000033","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000033","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000033","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000005","openai:completion_tokens":"0.00000033"},"pricing_version_id":"5a5b7f5c-a4fc-4b83-bb81-5b63e85ce546","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-06T19:02:47.296Z","status":0}},{"slug":"qwen/qwen-2.5-72b-instruct","hf_slug":"Qwen/Qwen2.5-72B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-09-19T00:00:00.000Z","hf_updated_at":null,"name":"Qwen2.5 72B Instruct","short_name":"Qwen2.5 72B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n\n- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n\n- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n\n- Long-context Support up to 128K tokens and can generate up to 8K tokens.\n\n- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).","model_version_group_id":null,"context_length":32768,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-2.5-72b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8b6b26e9-621a-4b31-b55a-c9aaa7482ede","name":"DeepInfra | qwen/qwen-2.5-72b-instruct","context_length":32768,"model":{"slug":"qwen/qwen-2.5-72b-instruct","hf_slug":"Qwen/Qwen2.5-72B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-09-19T00:00:00+00:00","hf_updated_at":null,"name":"Qwen2.5 72B Instruct","short_name":"Qwen2.5 72B Instruct","author":"qwen","author_display_name":"Qwen","author_icon_uri":null,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n\n- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n\n- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n\n- Long-context Support up to 128K tokens and can generate up to 8K tokens.\n\n- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\n\nUsage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Qwen","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"qwen/qwen-2.5-72b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"qwen/qwen-2.5-72b-instruct","model_variant_permaslug":"qwen/qwen-2.5-72b-instruct","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Qwen/Qwen2.5-72B-Instruct","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","tools","tool_choice","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000036","completion":"0.0000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000036","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000036","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000036","openai:completion_tokens":"0.0000004"},"pricing_version_id":"7159c2d9-5db5-498c-820f-18088cec50dd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:02.568Z","status":0}},{"slug":"cohere/command-r-08-2024","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-30T00:00:00.000Z","hf_updated_at":null,"name":"Cohere: Command R (08-2024)","short_name":"Command R (08-2024)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and is competitive with the previous version of the larger Command R+ model.\n\nRead the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed).\n\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-r-08-2024","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3d8c4986-1fc9-4ce1-b07d-d379bb75eb36","name":"Cohere | cohere/command-r-08-2024","context_length":128000,"model":{"slug":"cohere/command-r-08-2024","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-30T00:00:00+00:00","hf_updated_at":null,"name":"Cohere: Command R (08-2024)","short_name":"Command R (08-2024)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and is competitive with the previous version of the larger Command R+ model.\n\nRead the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed).\n\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-r-08-2024","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"cohere/command-r-08-2024","model_variant_permaslug":"cohere/command-r-08-2024","adapter_name":"CohereV2Adapter","provider_name":"Cohere","provider_info":{"name":"Cohere","displayName":"Cohere","slug":"cohere","baseUrl":"https://api.cohere.com/v2","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"CohereV2Adapter","statusPageUrl":"https://status.cohere.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Cohere.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Cohere","provider_slug":"cohere","provider_model_id":"command-r-08-2024","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy"},"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000015","openai:completion_tokens":"0.0000006"},"pricing_version_id":"17aa7365-5afa-4d90-aa4e-7e88cafb0185","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:58.219Z","status":0}},{"slug":"cohere/command-r-plus-08-2024","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-30T00:00:00.000Z","hf_updated_at":null,"name":"Cohere: Command R+ (08-2024)","short_name":"Command R+ (08-2024)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same.\n\nRead the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed).\n\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-r-plus-08-2024","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"cd63714a-d459-4806-bdf2-0dfea4f6614c","name":"Cohere | cohere/command-r-plus-08-2024","context_length":128000,"model":{"slug":"cohere/command-r-plus-08-2024","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-30T00:00:00+00:00","hf_updated_at":null,"name":"Cohere: Command R+ (08-2024)","short_name":"Command R+ (08-2024)","author":"cohere","author_display_name":"Cohere","author_icon_uri":null,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same.\n\nRead the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed).\n\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Cohere","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"cohere/command-r-plus-08-2024","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-03-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"cohere/command-r-plus-08-2024","model_variant_permaslug":"cohere/command-r-plus-08-2024","adapter_name":"CohereV2Adapter","provider_name":"Cohere","provider_info":{"name":"Cohere","displayName":"Cohere","slug":"cohere","baseUrl":"https://api.cohere.com/v2","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":true,"adapterName":"CohereV2Adapter","statusPageUrl":"https://status.cohere.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Cohere.png"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Cohere","provider_slug":"cohere","provider_model_id":"command-r-plus-08-2024","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://cohere.com/terms-of-use","privacyPolicyURL":"https://cohere.com/privacy"},"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000025","openai:completion_tokens":"0.00001"},"pricing_version_id":"d16ddf02-aac2-491c-836f-0ad0d6772cee","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:58.383Z","status":0}},{"slug":"sao10k/l3.1-euryale-70b","hf_slug":"Sao10K/L3.1-70B-Euryale-v2.2","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-28T00:00:00.000Z","hf_updated_at":null,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","short_name":"Llama 3.1 Euryale 70B v2.2","author":"sao10k","author_display_name":"Sao10K","author_icon_uri":null,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sao10k/l3.1-euryale-70b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"7ab4ba43-98eb-4842-9046-f7f1822ab3a2","name":"DeepInfra | sao10k/l3.1-euryale-70b","context_length":131072,"model":{"slug":"sao10k/l3.1-euryale-70b","hf_slug":"Sao10K/L3.1-70B-Euryale-v2.2","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-28T00:00:00+00:00","hf_updated_at":null,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","short_name":"Llama 3.1 Euryale 70B v2.2","author":"sao10k","author_display_name":"Sao10K","author_icon_uri":null,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sao10k/l3.1-euryale-70b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"sao10k/l3.1-euryale-70b","model_variant_permaslug":"sao10k/l3.1-euryale-70b","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"Sao10K/L3.1-70B-Euryale-v2.2","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000085","completion":"0.00000085","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000085","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000085","openai:completion_tokens":"0.00000085"},"pricing_version_id":"d5e82df3-ac6c-42c4-bbb1-4ca73425dcc7","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:02.136Z","status":0}},{"slug":"nousresearch/hermes-3-llama-3.1-70b","hf_slug":"NousResearch/Hermes-3-Llama-3.1-70B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-18T00:00:00.000Z","hf_updated_at":null,"name":"Nous: Hermes 3 70B Instruct","short_name":"Hermes 3 70B Instruct","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 70B is a competitive, if not superior finetune of the [Llama-3.1 70B foundation model](/models/meta-llama/llama-3.1-70b-instruct), focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-3-llama-3.1-70b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"2151651b-f4e9-4db7-b20d-8b91fb524bf8","name":"DeepInfra | nousresearch/hermes-3-llama-3.1-70b","context_length":131072,"model":{"slug":"nousresearch/hermes-3-llama-3.1-70b","hf_slug":"NousResearch/Hermes-3-Llama-3.1-70B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-18T00:00:00+00:00","hf_updated_at":null,"name":"Nous: Hermes 3 70B Instruct","short_name":"Hermes 3 70B Instruct","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 70B is a competitive, if not superior finetune of the [Llama-3.1 70B foundation model](/models/meta-llama/llama-3.1-70b-instruct), focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-3-llama-3.1-70b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"nousresearch/hermes-3-llama-3.1-70b","model_variant_permaslug":"nousresearch/hermes-3-llama-3.1-70b","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"NousResearch/Hermes-3-Llama-3.1-70B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000007","completion":"0.0000007","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000007","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000007","openai:completion_tokens":"0.0000007"},"pricing_version_id":"bd337f2f-b39a-4256-9853-ab9f0bd35f5d","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":false,"type_function":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-02T18:45:37.662Z","status":0}},{"slug":"nousresearch/hermes-3-llama-3.1-405b","hf_slug":"NousResearch/Hermes-3-Llama-3.1-405B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-16T00:00:00.000Z","hf_updated_at":null,"name":"Nous: Hermes 3 405B Instruct","short_name":"Hermes 3 405B Instruct","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 405B is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.\n\nHermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-3-llama-3.1-405b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3280e8f8-0960-400c-8284-2e03a0bcb446","name":"DeepInfra | nousresearch/hermes-3-llama-3.1-405b","context_length":131072,"model":{"slug":"nousresearch/hermes-3-llama-3.1-405b","hf_slug":"NousResearch/Hermes-3-Llama-3.1-405B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-16T00:00:00+00:00","hf_updated_at":null,"name":"Nous: Hermes 3 405B Instruct","short_name":"Hermes 3 405B Instruct","author":"nousresearch","author_display_name":"Nous Research","author_icon_uri":null,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 405B is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.\n\nHermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"nousresearch/hermes-3-llama-3.1-405b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"nousresearch/hermes-3-llama-3.1-405b","model_variant_permaslug":"nousresearch/hermes-3-llama-3.1-405b","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"NousResearch/Hermes-3-Llama-3.1-405B","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.000001","completion":"0.000001","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000001","openai:completion_tokens":"0.000001"},"pricing_version_id":"021cb9b8-e30e-4cdf-a54b-a8e1cddf9ad1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:02.508Z","status":0}},{"slug":"sao10k/l3-lunaris-8b","hf_slug":"Sao10K/L3-8B-Lunaris-v1","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-13T00:00:00.000Z","hf_updated_at":null,"name":"Sao10K: Llama 3 8B Lunaris","short_name":"Llama 3 8B Lunaris","author":"sao10k","author_display_name":"Sao10K","author_icon_uri":null,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge.\n\nCreated by [Sao10k](https://huggingface.co/Sao10k), this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning.\n\nFor best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sao10k/l3-lunaris-8b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"802c16d5-fb79-4761-93e1-b40d07fc7a1b","name":"Parasail | sao10k/l3-lunaris-8b","context_length":8192,"model":{"slug":"sao10k/l3-lunaris-8b","hf_slug":"Sao10K/L3-8B-Lunaris-v1","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-13T00:00:00+00:00","hf_updated_at":null,"name":"Sao10K: Llama 3 8B Lunaris","short_name":"Llama 3 8B Lunaris","author":"sao10k","author_display_name":"Sao10K","author_icon_uri":null,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge.\n\nCreated by [Sao10k](https://huggingface.co/Sao10k), this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning.\n\nFor best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"sao10k/l3-lunaris-8b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"sao10k/l3-lunaris-8b","model_variant_permaslug":"sao10k/l3-lunaris-8b","adapter_name":"ParasailAdapter","provider_name":"Parasail","provider_info":{"name":"Parasail","displayName":"Parasail","slug":"parasail","baseUrl":"https://api.parasail.io/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"ParasailAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://www.parasail.io/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Parasail","provider_slug":"parasail/bf16","provider_model_id":"parasail-sao10kl3-lunaris-8b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8192,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://parasail.io/legal/terms-of-service","privacyPolicyURL":"https://www.parasail.io/legal/privacy-policy"},"pricing":{"prompt":"0.00000004","completion":"0.00000005","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000005","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000004","openai:completion_tokens":"0.00000005"},"pricing_version_id":"42cb6b99-d934-41d5-872e-4edcd2d3805a","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-31T23:37:14.096Z","status":0}},{"slug":"openai/gpt-4o-2024-08-06","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-08-06T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o (2024-08-06)","short_name":"GPT-4o (2024-08-06)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-2024-08-06","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"59ea8d2a-1b1b-47f1-83de-a358a724caeb","name":"Azure | openai/gpt-4o-2024-08-06","context_length":128000,"model":{"slug":"openai/gpt-4o-2024-08-06","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-08-06T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o (2024-08-06)","short_name":"GPT-4o (2024-08-06)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).\n\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-2024-08-06","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o-2024-08-06","model_variant_permaslug":"openai/gpt-4o-2024-08-06","adapter_name":"AzureOpenAIAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-4o","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.0000025,"openai:completion_tokens":0.00001,"openai:cached_prompt_tokens":0.00000125},"pricing_version_id":"35fabd0d-b247-41ac-8e48-9f3ef3031f55","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-12-13T14:58:40.001Z","status":0}},{"slug":"meta-llama/llama-3.1-70b-instruct","hf_slug":"meta-llama/Meta-Llama-3.1-70B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-23T00:00:00.000Z","hf_updated_at":null,"name":"Meta: Llama 3.1 70B Instruct","short_name":"Llama 3.1 70B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).","model_version_group_id":"397604e2-45fa-454e-a85d-9921f5138747","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.1-70b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"036dfa0a-ebbb-4a51-aa90-091a75c2cadb","name":"DeepInfra | meta-llama/llama-3.1-70b-instruct","context_length":131072,"model":{"slug":"meta-llama/llama-3.1-70b-instruct","hf_slug":"meta-llama/Meta-Llama-3.1-70B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-23T00:00:00+00:00","hf_updated_at":null,"name":"Meta: Llama 3.1 70B Instruct","short_name":"Llama 3.1 70B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).","model_version_group_id":"397604e2-45fa-454e-a85d-9921f5138747","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.1-70b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-3.1-70b-instruct","model_variant_permaslug":"meta-llama/llama-3.1-70b-instruct","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra (Turbo)","slug":"deepinfra/turbo","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra (Turbo)","provider_slug":"deepinfra/turbo","provider_model_id":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.0000004","openai:completion_tokens":"0.0000004"},"pricing_version_id":"6b965571-9133-41ec-aedc-dec24eb7d99b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:02.383Z","status":0}},{"slug":"meta-llama/llama-3.1-8b-instruct","hf_slug":"meta-llama/Meta-Llama-3.1-8B-Instruct","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-23T00:00:00.000Z","hf_updated_at":null,"name":"Meta: Llama 3.1 8B Instruct","short_name":"Llama 3.1 8B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).","model_version_group_id":"803c32ed-9861-4abf-b5da-7d9c9e6dcf04","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.1-8b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"d7de0517-e8de-4f1b-b4bc-c5ebd29a0315","name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","context_length":131072,"model":{"slug":"meta-llama/llama-3.1-8b-instruct","hf_slug":"meta-llama/Meta-Llama-3.1-8B-Instruct","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-23T00:00:00+00:00","hf_updated_at":null,"name":"Meta: Llama 3.1 8B Instruct","short_name":"Llama 3.1 8B Instruct","author":"meta-llama","author_display_name":"Meta Llama","author_icon_uri":null,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).","model_version_group_id":"803c32ed-9861-4abf-b5da-7d9c9e6dcf04","context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama3","instruct_type":"llama3","default_system":null,"default_stops":["<|eot_id|>","<|end_of_text|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"meta-llama/llama-3.1-8b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"meta-llama/llama-3.1-8b-instruct","model_variant_permaslug":"meta-llama/llama-3.1-8b-instruct","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000002","openai:completion_tokens":"0.00000004"},"pricing_version_id":"eec97f56-2929-46db-8548-d908767ba0a9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-03-21T22:45:56.390Z","status":0}},{"slug":"mistralai/mistral-nemo","hf_slug":"mistralai/Mistral-Nemo-Instruct-2407","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-19T00:00:00.000Z","hf_updated_at":null,"name":"Mistral: Mistral Nemo","short_name":"Mistral Nemo","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.\n\nThe model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.\n\nIt supports function calling and is released under the Apache 2.0 license.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"mistral","default_system":null,"default_stops":["[INST]","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-nemo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3e0aa374-de51-4cd0-911b-29ae65067e21","name":"DeepInfra | mistralai/mistral-nemo","context_length":131072,"model":{"slug":"mistralai/mistral-nemo","hf_slug":"mistralai/Mistral-Nemo-Instruct-2407","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-19T00:00:00+00:00","hf_updated_at":null,"name":"Mistral: Mistral Nemo","short_name":"Mistral Nemo","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.\n\nThe model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.\n\nIt supports function calling and is released under the Apache 2.0 license.","model_version_group_id":null,"context_length":131072,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"mistral","default_system":null,"default_stops":["[INST]","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-nemo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-nemo","model_variant_permaslug":"mistralai/mistral-nemo","adapter_name":"DeepInfraAdapter","provider_name":"DeepInfra","provider_info":{"name":"DeepInfra","displayName":"DeepInfra","slug":"deepinfra","baseUrl":"https://api.deepinfra.com/v1/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"DeepInfraAdapter","statusPageUrl":"https://status.deepinfra.com/","byokEnabled":true,"icon":{"url":"/images/icons/DeepInfra.webp"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"DeepInfra","provider_slug":"deepinfra/fp8","provider_model_id":"mistralai/Mistral-Nemo-Instruct-2407","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","response_format","logit_bias"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://deepinfra.com/terms","privacyPolicyURL":"https://deepinfra.com/privacy"},"pricing":{"prompt":"0.000000019","completion":"0.00000003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000019","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000000019","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.000000019","openai:completion_tokens":"0.00000003"},"pricing_version_id":"152e0965-3545-4178-b30d-ee611decf22b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:01.596Z","status":0}},{"slug":"openai/gpt-4o-mini-2024-07-18","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-18T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o-mini (2024-07-18)","short_name":"GPT-4o-mini (2024-07-18)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-mini-2024-07-18","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15","name":"OpenAI | openai/gpt-4o-mini-2024-07-18","context_length":128000,"model":{"slug":"openai/gpt-4o-mini-2024-07-18","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-18T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o-mini (2024-07-18)","short_name":"GPT-4o-mini (2024-07-18)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-mini-2024-07-18","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o-mini-2024-07-18","model_variant_permaslug":"openai/gpt-4o-mini-2024-07-18","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4o-mini-2024-07-18","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":1.5e-7,"openai:completion_tokens":6e-7,"openai:cached_prompt_tokens":7.5e-8},"pricing_version_id":"bb978658-5598-4ad9-8224-e8e5d57794cd","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:55.200Z","status":0}},{"slug":"openai/gpt-4o-mini","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-18T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o-mini (batch)","short_name":"GPT-4o-mini (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-mini","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"548cbdaa-c3d2-43ef-81c4-62d65dca9063","name":"OpenAI | openai/gpt-4o-mini:batch","context_length":128000,"model":{"slug":"openai/gpt-4o-mini","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-18T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o-mini","short_name":"GPT-4o-mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-mini","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o-mini:batch","model_variant_permaslug":"openai/gpt-4o-mini:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4o-mini","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000375","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3.750000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"7.500000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"3.000000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"3.750000e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"7.500000e-8","openai_responses:completion_tokens":"3.000000e-7","openai_responses:cached_prompt_tokens":"3.750000e-8"},"pricing_version_id":"b64aa3dd-205a-4b74-bf78-7233ea1008f6","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:59.143Z","status":0}},{"slug":"openai/gpt-4o-mini","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-18T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o-mini","short_name":"GPT-4o-mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-mini","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"685e6cfb-ecef-4c83-8e2d-aa1ba667d744","name":"Azure | openai/gpt-4o-mini","context_length":128000,"model":{"slug":"openai/gpt-4o-mini","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-18T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o-mini","short_name":"GPT-4o-mini","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/).\n\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n\n#multimodal","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-mini","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o-mini","model_variant_permaslug":"openai/gpt-4o-mini","adapter_name":"AzureOpenAIAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"openai/gpt-4o-mini","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"7.5e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":1.5e-7,"openai:completion_tokens":6e-7,"openai:cached_prompt_tokens":7.5e-8},"pricing_version_id":"10ca8035-86ae-4868-b649-52f166f5ed7e","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-02-07T18:57:43.884Z","status":0}},{"slug":"google/gemma-2-27b-it","hf_slug":"google/gemma-2-27b-it","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-07-13T00:00:00.000Z","hf_updated_at":null,"name":"Google: Gemma 2 27B","short_name":"Gemma 2 27B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini).\n\nGemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning.\n\nSee the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-2-27b-it","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"03a23b91-c1f2-4a5e-891b-df7e13c87472","name":"NextBit | google/gemma-2-27b-it","context_length":8192,"model":{"slug":"google/gemma-2-27b-it","hf_slug":"google/gemma-2-27b-it","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-07-13T00:00:00+00:00","hf_updated_at":null,"name":"Google: Gemma 2 27B","short_name":"Gemma 2 27B","author":"google","author_display_name":"Google","author_icon_uri":null,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini).\n\nGemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning.\n\nSee the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Gemini","instruct_type":"gemma","default_system":null,"default_stops":["<start_of_turn>","<end_of_turn>","<eos>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"google/gemma-2-27b-it","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2024-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"google/gemma-2-27b-it","model_variant_permaslug":"google/gemma-2-27b-it","adapter_name":"NextBitAdapter","provider_name":"NextBit","provider_info":{"name":"NextBit","displayName":"NextBit","slug":"nextbit","baseUrl":"https://api.nextbit256.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy","requiresUserIDs":false},"headquarters":"ES","datacenters":["ES"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NextBitAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nextbit256.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NextBit","provider_slug":"nextbit/int4","provider_model_id":"gemma-2:27b-it","quantization":"int4","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":2048,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy"},"pricing":{"prompt":"0.00000065","completion":"0.00000065","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":6.5e-7,"openai:completion_tokens":6.5e-7},"pricing_version_id":"8daa9dd1-e970-4c68-921e-ebe211d913eb","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-24T15:28:44.393Z","status":0}},{"slug":"openai/gpt-4o","hf_slug":null,"updated_at":"2026-05-13T21:47:50.313Z","created_at":"2024-05-13T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o (batch)","short_name":"GPT-4o (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"35e5dca8-d246-411f-b281-f5e8500f7b8c","name":"OpenAI | openai/gpt-4o:batch","context_length":128000,"model":{"slug":"openai/gpt-4o","hf_slug":null,"updated_at":"2026-05-13T21:47:50.313061+00:00","created_at":"2024-05-13T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o","short_name":"GPT-4o","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o:batch","model_variant_permaslug":"openai/gpt-4o:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4o","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000125","completion":"0.000005","input_cache_read":"0.000000625","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.250000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"1.250000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"6.250000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"1.250000e-6","openai_responses:completion_tokens":"5.000000e-6","openai_responses:cached_prompt_tokens":"6.250000e-7"},"pricing_version_id":"fa29ff55-c29d-471c-a574-0d990e317a90","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:08:58.418Z","status":0}},{"slug":"openai/gpt-4o","hf_slug":null,"updated_at":"2026-05-13T21:47:50.313Z","created_at":"2024-05-13T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o","short_name":"GPT-4o","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"452a72a0-2c24-4e31-98cb-d6cc1084fb99","name":"OpenAI | openai/gpt-4o","context_length":128000,"model":{"slug":"openai/gpt-4o","hf_slug":null,"updated_at":"2026-05-13T21:47:50.313061+00:00","created_at":"2024-05-13T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o","short_name":"GPT-4o","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o","model_variant_permaslug":"openai/gpt-4o","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4o","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":16384,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000025","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.00000125","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.0000025,"openai:completion_tokens":0.00001,"openai:cached_prompt_tokens":0.00000125},"pricing_version_id":"9a09c5e1-25e5-4027-ac71-8ada7a7a80b9","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:54.988Z","status":0}},{"slug":"openai/gpt-4o-2024-05-13","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-05-13T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4o (2024-05-13)","short_name":"GPT-4o (2024-05-13)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-2024-05-13","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3d6584e7-a2bb-48d6-903d-24e3d90e7e55","name":"OpenAI | openai/gpt-4o-2024-05-13","context_length":128000,"model":{"slug":"openai/gpt-4o-2024-05-13","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-05-13T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4o (2024-05-13)","short_name":"GPT-4o (2024-05-13)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal","model_version_group_id":"76e36b33-358e-477a-be24-09f954fcea74","context_length":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4o-2024-05-13","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-10-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4o-2024-05-13","model_variant_permaslug":"openai/gpt-4o-2024-05-13","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4o-2024-05-13","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","web_search_options","logit_bias","logprobs","top_logprobs","prediction","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.000005,"openai:completion_tokens":0.000015},"pricing_version_id":"dab5f507-2c79-4281-bc39-5346d8549075","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:55.041Z","status":0}},{"slug":"mistralai/mixtral-8x22b-instruct","hf_slug":"mistralai/Mixtral-8x22B-Instruct-v0.1","updated_at":"2026-05-14T22:39:44.559Z","created_at":"2024-04-17T00:00:00.000Z","hf_updated_at":null,"name":"Mistral: Mixtral 8x22B Instruct","short_name":"Mixtral 8x22B Instruct","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:\n- strong math, coding, and reasoning\n- large context length (64k)\n- fluency in English, French, Italian, German, and Spanish\n\nSee benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/).\n#moe","model_version_group_id":null,"context_length":65536,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"mistral","default_system":null,"default_stops":["[INST]","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mixtral-8x22b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-01-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e55a0c16-08a0-4871-ae6a-97482cc3231a","name":"Mistral | mistralai/mixtral-8x22b-instruct","context_length":65536,"model":{"slug":"mistralai/mixtral-8x22b-instruct","hf_slug":"mistralai/Mixtral-8x22B-Instruct-v0.1","updated_at":"2026-05-14T22:39:44.559021+00:00","created_at":"2024-04-17T00:00:00+00:00","hf_updated_at":null,"name":"Mistral: Mixtral 8x22B Instruct","short_name":"Mixtral 8x22B Instruct","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:\n- strong math, coding, and reasoning\n- large context length (64k)\n- fluency in English, French, Italian, German, and Spanish\n\nSee benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/).\n#moe","model_version_group_id":null,"context_length":65536,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"mistral","default_system":null,"default_stops":["[INST]","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mixtral-8x22b-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-01-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mixtral-8x22b-instruct","model_variant_permaslug":"mistralai/mixtral-8x22b-instruct","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"open-mixtral-8x22b","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.000002","mistral:completion_tokens":0.000006,"mistral:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"06607651-4441-4e0f-afd1-2c0508452775","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:58.887Z","status":0}},{"slug":"microsoft/wizardlm-2-8x22b","hf_slug":"microsoft/WizardLM-2-8x22B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-04-16T00:00:00.000Z","hf_updated_at":null,"name":"WizardLM-2 8x22B","short_name":"WizardLM-2 8x22B","author":"microsoft","author_display_name":"Microsoft","author_icon_uri":null,"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.\n\nIt is an instruct finetune of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b).\n\nTo read more about the model release, [click here](https://wizardlm.github.io/WizardLM2/).\n\n#moe","model_version_group_id":null,"context_length":65535,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"vicuna","default_system":null,"default_stops":["USER:","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"microsoft/wizardlm-2-8x22b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"92d0658f-b48a-4746-96e7-75ea71d5e060","name":"Novita | microsoft/wizardlm-2-8x22b","context_length":65535,"model":{"slug":"microsoft/wizardlm-2-8x22b","hf_slug":"microsoft/WizardLM-2-8x22B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-04-16T00:00:00+00:00","hf_updated_at":null,"name":"WizardLM-2 8x22B","short_name":"WizardLM-2 8x22B","author":"microsoft","author_display_name":"Microsoft","author_icon_uri":null,"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.\n\nIt is an instruct finetune of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b).\n\nTo read more about the model release, [click here](https://wizardlm.github.io/WizardLM2/).\n\n#moe","model_version_group_id":null,"context_length":65536,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":"vicuna","default_system":null,"default_stops":["USER:","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"microsoft/wizardlm-2-8x22b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-04-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"microsoft/wizardlm-2-8x22b","model_variant_permaslug":"microsoft/wizardlm-2-8x22b","adapter_name":"NovitaAdapter","provider_name":"Novita","provider_info":{"name":"Novita","displayName":"NovitaAI","slug":"novita","baseUrl":"https://api.novita.ai/v3/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"NovitaAdapter","statusPageUrl":"https://status.novita.ai/","byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://novita.ai/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NovitaAI","provider_slug":"novita/bf16","provider_model_id":"microsoft/wizardlm-2-8x22b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":8000,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://novita.ai/legal/terms-of-service","privacyPolicyURL":"https://novita.ai/legal/privacy-policy"},"pricing":{"prompt":"0.00000062","completion":"0.00000062","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000062","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000062","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00000062","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000062","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":"0.00000062","openai:completion_tokens":"0.00000062"},"pricing_version_id":"da4eaaab-aa90-4011-a1b6-ec248370ba9b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:04.713Z","status":0}},{"slug":"openai/gpt-4-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-04-09T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4 Turbo (batch)","short_name":"GPT-4 Turbo (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"e19acbe0-a16a-4e1f-b854-b91dcaceae69","name":"OpenAI | openai/gpt-4-turbo:batch","context_length":128000,"model":{"slug":"openai/gpt-4-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-04-09T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4 Turbo","short_name":"GPT-4 Turbo","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4-turbo:batch","model_variant_permaslug":"openai/gpt-4-turbo:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4-turbo","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.000005","completion":"0.000015","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5.000000e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.500000e-5","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"5.000000e-6","openai_responses:completion_tokens":"1.500000e-5"},"pricing_version_id":"57a5a267-971c-4c6d-82c1-c6e2de261aa0","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:09:02.029Z","status":0}},{"slug":"openai/gpt-4-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-04-09T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4 Turbo","short_name":"GPT-4 Turbo","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"da16824f-3ba0-43a1-86f8-a6131837f457","name":"OpenAI | openai/gpt-4-turbo","context_length":128000,"model":{"slug":"openai/gpt-4-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-04-09T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4 Turbo","short_name":"GPT-4 Turbo","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","model_version_group_id":null,"context_length":128000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4-turbo","model_variant_permaslug":"openai/gpt-4-turbo","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4-turbo","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.00001,"openai:completion_tokens":0.00003},"pricing_version_id":"48751c0f-27b9-45d7-9b9a-ec343acdf97b","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:54.507Z","status":0}},{"slug":"anthropic/claude-3-haiku","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-03-13T00:00:00.000Z","hf_updated_at":null,"name":"Anthropic: Claude 3 Haiku","short_name":"Claude 3 Haiku","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal","model_version_group_id":"028ec497-a034-40fd-81fe-f51d0a0c640c","context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-3-haiku","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-08-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"401c6f0f-caeb-4c84-92b7-e163dbccf7c2","name":"Amazon Bedrock | anthropic/claude-3-haiku","context_length":200000,"model":{"slug":"anthropic/claude-3-haiku","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-03-13T00:00:00+00:00","hf_updated_at":null,"name":"Anthropic: Claude 3 Haiku","short_name":"Claude 3 Haiku","author":"anthropic","author_display_name":"Anthropic","author_icon_uri":null,"description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal","model_version_group_id":"028ec497-a034-40fd-81fe-f51d0a0c640c","context_length":200000,"input_modalities":["text","image"],"output_modalities":["text"],"has_text_output":true,"group":"Claude","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"anthropic/claude-3-haiku","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-08-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"anthropic/claude-3-haiku","model_variant_permaslug":"anthropic/claude-3-haiku","adapter_name":"InternalStreamAmazonBedrockInvokeAnthropicAdapter","provider_name":"Amazon Bedrock","provider_info":{"name":"Amazon Bedrock","displayName":"Amazon Bedrock","slug":"amazon-bedrock","baseUrl":"not_used","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":true,"adapterName":"AmazonBedrockConverseAdapter","statusPageUrl":"https://health.aws.amazon.com/health/status","byokEnabled":true,"icon":{"url":"/images/icons/Bedrock.svg"},"sendClientIp":false,"pricingStrategy":"anthropic"},"provider_display_name":"Amazon Bedrock","provider_slug":"amazon-bedrock","provider_model_id":"us.anthropic.claude-3-haiku-20240307-v1:0","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://aws.amazon.com/service-terms/","privacyPolicyURL":"https://aws.amazon.com/privacy","requiresUserIDs":true},"pricing":{"prompt":"0.00000025","completion":"0.00000125","input_cache_read":"0.00000003","input_cache_write":"0.0000003","input_cache_write_1h":"0.0000005","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".03e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":".30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"1.25e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":".03e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write","price":".30e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Write (1h)","price":".5e-6","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"anthropic:prompt_tokens":"0.25e-6","anthropic:cache_read_tokens":".03e-6","anthropic:completion_tokens":"1.25e-6","anthropic:cache_write_1h_tokens":".5e-6","anthropic:cache_write_5m_tokens":".30e-6"},"pricing_version_id":"4b5f500c-5593-4e08-9615-77d8ce06f469","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-02-14T23:00:52.780Z","status":0}},{"slug":"mistralai/mistral-large","hf_slug":null,"updated_at":"2026-05-14T22:39:45.131Z","created_at":"2024-02-26T00:00:00.000Z","hf_updated_at":null,"name":"Mistral Large","short_name":"Mistral Large","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).\n\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.","model_version_group_id":"83129748-0564-4485-982a-d7a37a1ef3ec","context_length":128000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-large","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-11-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f1a57233-f872-4fa0-ad37-66c9a6b00469","name":"Mistral | mistralai/mistral-large","context_length":128000,"model":{"slug":"mistralai/mistral-large","hf_slug":null,"updated_at":"2026-05-14T22:39:45.131702+00:00","created_at":"2024-02-26T00:00:00+00:00","hf_updated_at":null,"name":"Mistral Large","short_name":"Mistral Large","author":"mistralai","author_display_name":"Mistral AI","author_icon_uri":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).\n\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.","model_version_group_id":"83129748-0564-4485-982a-d7a37a1ef3ec","context_length":128000,"input_modalities":["text","file"],"output_modalities":["text"],"has_text_output":true,"group":"Mistral","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mistralai/mistral-large","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{"temperature":0.3},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":true,"is_trainable_image":null,"knowledge_cutoff":"2024-11-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mistralai/mistral-large","model_variant_permaslug":"mistralai/mistral-large","adapter_name":"MistralAdapter","provider_name":"Mistral","provider_info":{"name":"Mistral","displayName":"Mistral","slug":"mistral","baseUrl":"https://api.mistral.ai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy","requiresUserIDs":false},"headquarters":"FR","hasChatCompletions":true,"hasCompletions":false,"isAbortable":false,"moderationRequired":false,"adapterName":"MistralAdapter","statusPageUrl":"https://status.mistral.ai/","byokEnabled":true,"icon":{"url":"/images/icons/Mistral.png"},"sendClientIp":false,"pricingStrategy":"mistral"},"provider_display_name":"Mistral","provider_slug":"mistral","provider_model_id":"mistral-large-2407","quantization":"unknown","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":null,"max_tokens_per_image":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://mistral.ai/terms/#terms-of-use","privacyPolicyURL":"https://mistral.ai/terms/#privacy-policy"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000006","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Cache Read","price":"0.0000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mistral:prompt_tokens":"0.000002","mistral:completion_tokens":0.000006,"mistral:cached_prompt_tokens":"0.0000002"},"pricing_version_id":"d385f70a-db15-4927-a6b8-d92fe6093c68","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_file_urls":true,"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:58.584Z","status":0}},{"slug":"openai/gpt-4-turbo-preview","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-01-25T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4 Turbo Preview","short_name":"GPT-4 Turbo Preview","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023.\n\n**Note:** heavily rate limited by OpenAI while in preview.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4-turbo-preview","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"003933da-395a-48eb-86a3-0c4ec486d67f","name":"OpenAI | openai/gpt-4-turbo-preview","context_length":128000,"model":{"slug":"openai/gpt-4-turbo-preview","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-01-25T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4 Turbo Preview","short_name":"GPT-4 Turbo Preview","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023.\n\n**Note:** heavily rate limited by OpenAI while in preview.","model_version_group_id":null,"context_length":128000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4-turbo-preview","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-12-31T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4-turbo-preview","model_variant_permaslug":"openai/gpt-4-turbo-preview","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4-turbo-preview","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00001","completion":"0.00003","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.00001,"openai:completion_tokens":0.00003},"pricing_version_id":"dfe2e434-d9ea-412c-8e58-73bcad322ff1","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:54.569Z","status":0}},{"slug":"openai/gpt-3.5-turbo-0613","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2024-01-25T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","short_name":"GPT-3.5 Turbo (older v0613)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","model_version_group_id":null,"context_length":4095,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo-0613","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"f29e5bba-56f3-408a-a036-185e3dc20be3","name":"Azure | openai/gpt-3.5-turbo-0613","context_length":4095,"model":{"slug":"openai/gpt-3.5-turbo-0613","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2024-01-25T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","short_name":"GPT-3.5 Turbo (older v0613)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","model_version_group_id":null,"context_length":4095,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo-0613","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-3.5-turbo-0613","model_variant_permaslug":"openai/gpt-3.5-turbo-0613","adapter_name":"AzureOpenAIAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-35-turbo","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.000001","completion":"0.000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000001","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.000001,"openai:completion_tokens":0.000002},"pricing_version_id":"ae7dbbef-5731-4f96-ad57-c350851b9e31","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":false,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:05.881Z","status":0}},{"slug":"openrouter/auto","hf_slug":null,"updated_at":"2026-05-09T17:59:13.374Z","created_at":"2023-11-08T00:00:00.000Z","hf_updated_at":null,"name":"Auto Router","short_name":"Auto Router","author":"openrouter","author_display_name":"OpenRouter","author_icon_uri":null,"description":"Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.\n\nTo see which model was used, visit [Activity](/activity), or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model.\n\nLearn more, including how to customize the models for routing, in our [docs](/docs/guides/routing/routers/auto-router). For another way to route, see [Pareto Code](/openrouter/pareto-code).","model_version_group_id":null,"context_length":2000000,"input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"has_text_output":true,"group":"Router","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":"","promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openrouter/auto","supports_reasoning":false,"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"features":{"reasoning_config":{"start_token":null,"end_token":null,"system_prompt":null},"chat_template_config":{}},"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":null,"limit_rpm":0,"limit_rpd":0,"supported_tts_voices":null,"endpoint":null},{"slug":"openai/gpt-3.5-turbo-instruct","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-09-28T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo Instruct","short_name":"GPT-3.5 Turbo Instruct","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","model_version_group_id":null,"context_length":4095,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"39594b4d-6c7e-4ccd-aeed-79f9b3ca5819","name":"OpenAI | openai/gpt-3.5-turbo-instruct","context_length":4095,"model":{"slug":"openai/gpt-3.5-turbo-instruct","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-09-28T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo Instruct","short_name":"GPT-3.5 Turbo Instruct","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","model_version_group_id":null,"context_length":4095,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":"chatml","default_system":null,"default_stops":["<|im_start|>","<|im_end|>","<|endoftext|>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo-instruct","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-3.5-turbo-instruct","model_variant_permaslug":"openai/gpt-3.5-turbo-instruct","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-3.5-turbo-instruct","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000015","completion":"0.000002","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000002","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.0000015,"openai:completion_tokens":0.000002},"pricing_version_id":"c15e04ac-f17e-41f8-8bb7-190dd49c821c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:55.530Z","status":0}},{"slug":"openai/gpt-3.5-turbo-16k","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-08-28T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo 16k","short_name":"GPT-3.5 Turbo 16k","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.","model_version_group_id":null,"context_length":16385,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo-16k","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"8c793d52-3eea-429a-8524-bf4899ce050a","name":"Azure | openai/gpt-3.5-turbo-16k","context_length":16385,"model":{"slug":"openai/gpt-3.5-turbo-16k","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-08-28T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo 16k","short_name":"GPT-3.5 Turbo 16k","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.","model_version_group_id":null,"context_length":16385,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo-16k","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-3.5-turbo-16k","model_variant_permaslug":"openai/gpt-3.5-turbo-16k","adapter_name":"AzureOpenAIAdapter","provider_name":"Azure","provider_info":{"name":"Azure","displayName":"Azure","slug":"azure","baseUrl":"https://openrouter-east-us-2.openai.azure.com/openai","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement","requiresUserIDs":false},"headquarters":"US","hasChatCompletions":true,"hasCompletions":false,"isAbortable":true,"moderationRequired":false,"adapterName":"AzureOpenAIAdapter","statusPageUrl":"https://status.azure.com/","byokEnabled":true,"icon":{"url":"/images/icons/Azure.svg"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"Azure","provider_slug":"azure","provider_model_id":"gpt-35-turbo-16k","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["max_completion_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.microsoft.com/en-us/legal/terms-of-use?oneroute=true","privacyPolicyURL":"https://www.microsoft.com/en-us/privacy/privacystatement"},"pricing":{"prompt":"0.000003","completion":"0.000004","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.000003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.000004","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.000003,"openai:completion_tokens":0.000004},"pricing_version_id":"35300c7b-14bc-42d3-b3ea-81091aedd9e4","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":false,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:05.588Z","status":0}},{"slug":"mancer/weaver","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-08-02T00:00:00.000Z","hf_updated_at":null,"name":"Mancer: Weaver (alpha)","short_name":"Weaver (alpha)","author":"mancer","author_display_name":"Mancer","author_icon_uri":null,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","model_version_group_id":null,"context_length":8000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama2","instruct_type":"alpaca","default_system":null,"default_stops":["###","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mancer/weaver","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"c8fb1a1b-9f2c-4dc6-b2be-43b25f999502","name":"Mancer 2 | mancer/weaver","context_length":8000,"model":{"slug":"mancer/weaver","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-08-02T00:00:00+00:00","hf_updated_at":null,"name":"Mancer: Weaver (alpha)","short_name":"Weaver (alpha)","author":"mancer","author_display_name":"Mancer","author_icon_uri":null,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","model_version_group_id":null,"context_length":8000,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama2","instruct_type":"alpaca","default_system":null,"default_stops":["###","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"mancer/weaver","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"mancer/weaver","model_variant_permaslug":"mancer/weaver","adapter_name":"MancerAdapter","provider_name":"Mancer 2","provider_info":{"name":"Mancer 2","displayName":"Mancer","slug":"mancer","baseUrl":"https://neuro.mancer.tech/oai/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://mancer.tech/terms","privacyPolicyURL":"https://mancer.tech/privacy","requiresUserIDs":false},"hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":false,"adapterName":"MancerAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://mancer.tech/&size=256"},"sendClientIp":false,"pricingStrategy":"mancer"},"provider_display_name":"Mancer","provider_slug":"mancer/fp8","provider_model_id":"weaver-alpha","quantization":"fp8","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":6000,"max_tokens_per_image":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs"],"excluded_parameters":["structured_outputs"],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://mancer.tech/terms","privacyPolicyURL":"https://mancer.tech/privacy"},"pricing":{"prompt":"0.0000005","completion":"0.00000075","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.0000005","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00000075","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"mancer:prompt_tokens":"0.0000005","mancer:completion_tokens":"0.00000075","mancer:upstream_cost_credits":"1"},"pricing_version_id":"a171fe2c-612e-4684-90ce-f7b518683cef","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":false}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:19:08.716Z","status":0}},{"slug":"undi95/remm-slerp-l2-13b","hf_slug":"Undi95/ReMM-SLERP-L2-13B","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-07-22T00:00:00.000Z","hf_updated_at":null,"name":"ReMM SLERP 13B","short_name":"ReMM SLERP 13B","author":"undi95","author_display_name":"Undi","author_icon_uri":null,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","model_version_group_id":null,"context_length":6144,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama2","instruct_type":"alpaca","default_system":null,"default_stops":["###","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"undi95/remm-slerp-l2-13b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"061b3f45-8511-4ad9-8537-a5ac7aeeb163","name":"NextBit | undi95/remm-slerp-l2-13b","context_length":6144,"model":{"slug":"undi95/remm-slerp-l2-13b","hf_slug":"Undi95/ReMM-SLERP-L2-13B","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-07-22T00:00:00+00:00","hf_updated_at":null,"name":"ReMM SLERP 13B","short_name":"ReMM SLERP 13B","author":"undi95","author_display_name":"Undi","author_icon_uri":null,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","model_version_group_id":null,"context_length":4096,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama2","instruct_type":"alpaca","default_system":null,"default_stops":["###","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"undi95/remm-slerp-l2-13b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"undi95/remm-slerp-l2-13b","model_variant_permaslug":"undi95/remm-slerp-l2-13b","adapter_name":"NextBitAdapter","provider_name":"NextBit","provider_info":{"name":"NextBit","displayName":"NextBit","slug":"nextbit","baseUrl":"https://api.nextbit256.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy","requiresUserIDs":false},"headquarters":"ES","datacenters":["ES"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NextBitAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nextbit256.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NextBit","provider_slug":"nextbit/bf16","provider_model_id":"remm-slerp:l2-13b","quantization":"bf16","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","repetition_penalty","seed"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy"},"pricing":{"prompt":"0.00000045","completion":"0.00000065","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"4.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6.5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":4.5e-7,"openai:completion_tokens":6.5e-7},"pricing_version_id":"3d2d93eb-5000-49bd-a0be-dbcea2993fa6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-14T15:23:59.845Z","status":0}},{"slug":"gryphe/mythomax-l2-13b","hf_slug":"Gryphe/MythoMax-L2-13b","updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-07-02T00:00:00.000Z","hf_updated_at":null,"name":"MythoMax 13B","short_name":"MythoMax 13B","author":"gryphe","author_display_name":"Gryphe","author_icon_uri":null,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","model_version_group_id":null,"context_length":8192,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama2","instruct_type":"alpaca","default_system":null,"default_stops":["###","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"gryphe/mythomax-l2-13b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-06-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3a9bbd50-68e9-4ebf-92e4-faa0395a1229","name":"NextBit | gryphe/mythomax-l2-13b","context_length":4096,"model":{"slug":"gryphe/mythomax-l2-13b","hf_slug":"Gryphe/MythoMax-L2-13b","updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-07-02T00:00:00+00:00","hf_updated_at":null,"name":"MythoMax 13B","short_name":"MythoMax 13B","author":"gryphe","author_display_name":"Gryphe","author_icon_uri":null,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","model_version_group_id":null,"context_length":4096,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"Llama2","instruct_type":"alpaca","default_system":null,"default_stops":["###","</s>"],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"gryphe/mythomax-l2-13b","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2023-06-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"gryphe/mythomax-l2-13b","model_variant_permaslug":"gryphe/mythomax-l2-13b","adapter_name":"NextBitAdapter","provider_name":"NextBit","provider_info":{"name":"NextBit","displayName":"NextBit","slug":"nextbit","baseUrl":"https://api.nextbit256.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy","requiresUserIDs":false},"headquarters":"ES","datacenters":["ES"],"hasChatCompletions":true,"hasCompletions":true,"isAbortable":false,"moderationRequired":false,"adapterName":"NextBitAdapter","statusPageUrl":null,"byokEnabled":true,"icon":{"url":"https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=https://nextbit256.com/&size=256"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"NextBit","provider_slug":"nextbit/int4","provider_model_id":"mythomax:13b","quantization":"int4","variant":"standard","is_free":false,"can_abort":false,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","repetition_penalty","seed"],"excluded_parameters":[],"is_byok":false,"moderation_required":false,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":false,"canPublish":false,"termsOfServiceURL":"https://www.nextbit256.com/docs/terms-of-service","privacyPolicyURL":"https://www.nextbit256.com/docs/privacy-policy"},"pricing":{"prompt":"0.00000006","completion":"0.00000006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"6e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"6e-8","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":6e-8,"openai:completion_tokens":6e-8},"pricing_version_id":"c4467f4e-c436-400b-8398-5601e8a101c8","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":false,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true},"supported_parameters":{"response_format":true,"structured_outputs":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2025-07-14T15:23:39.502Z","status":0}},{"slug":"openai/gpt-3.5-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-05-28T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo (batch)","short_name":"GPT-3.5 Turbo (batch)","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","model_version_group_id":null,"context_length":16385,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"a6ba47d3-00d7-42da-9b9c-006beac11587","name":"OpenAI | openai/gpt-3.5-turbo:batch","context_length":16385,"model":{"slug":"openai/gpt-3.5-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-05-28T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo","short_name":"GPT-3.5 Turbo","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","model_version_group_id":null,"context_length":16385,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-3.5-turbo:batch","model_variant_permaslug":"openai/gpt-3.5-turbo:batch","adapter_name":"OpenAIBatchAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIBatchAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_responses"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-3.5-turbo","quantization":"unknown","variant":"batch","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"retentionDays":30,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00000025","completion":"0.00000075","web_search":"0.01","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"2.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"7.500000e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai_responses:prompt_tokens":"2.500000e-7","openai_responses:completion_tokens":"7.500000e-7"},"pricing_version_id":"ed5be54c-0e34-4c18-a76d-5d6513954b44","is_hidden":false,"is_private":false,"is_byok_only":true,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2026-07-07T17:09:02.754Z","status":0}},{"slug":"openai/gpt-3.5-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-05-28T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo","short_name":"GPT-3.5 Turbo","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","model_version_group_id":null,"context_length":16385,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"3a632f37-731d-4200-9e38-413a5f5dd39d","name":"OpenAI | openai/gpt-3.5-turbo","context_length":16385,"model":{"slug":"openai/gpt-3.5-turbo","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-05-28T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-3.5 Turbo","short_name":"GPT-3.5 Turbo","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","model_version_group_id":null,"context_length":16385,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-3.5-turbo","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-3.5-turbo","model_variant_permaslug":"openai/gpt-3.5-turbo","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-3.5-turbo","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.0000005","completion":"0.0000015","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"5e-7","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.0000015","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":5e-7,"openai:completion_tokens":0.0000015},"pricing_version_id":"815be22c-57e8-49e1-a40f-553e1a60610c","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:54.258Z","status":0}},{"slug":"openai/gpt-4","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801Z","created_at":"2023-05-28T00:00:00.000Z","hf_updated_at":null,"name":"OpenAI: GPT-4","short_name":"GPT-4","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.","model_version_group_id":null,"context_length":8191,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59.000Z","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null,"endpoint":{"id":"355b1df4-06c8-4c36-a091-3d50477095fb","name":"OpenAI | openai/gpt-4","context_length":8191,"model":{"slug":"openai/gpt-4","hf_slug":null,"updated_at":"2026-03-24T19:43:16.801719+00:00","created_at":"2023-05-28T00:00:00+00:00","hf_updated_at":null,"name":"OpenAI: GPT-4","short_name":"GPT-4","author":"openai","author_display_name":"OpenAI","author_icon_uri":null,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.","model_version_group_id":null,"context_length":8191,"input_modalities":["text"],"output_modalities":["text"],"has_text_output":true,"group":"GPT","instruct_type":null,"default_system":null,"default_stops":[],"hidden":false,"router":null,"warning_message":null,"promotion_message":null,"routing_error_message":null,"required_attestation_types":[],"is_private":false,"permaslug":"openai/gpt-4","supports_reasoning":false,"reasoning_config":null,"features":{},"default_parameters":{},"default_order":[],"quick_start_example_type":null,"previews_by_modality":{},"preview_thumbnail_url":null,"preview_audio":null,"author_flagship_modalities":[],"is_trainable_text":null,"is_trainable_image":null,"knowledge_cutoff":"2021-09-30T23:59:59+00:00","limit_rpm":null,"limit_rpd":null,"supported_tts_voices":null},"model_variant_slug":"openai/gpt-4","model_variant_permaslug":"openai/gpt-4","adapter_name":"OpenAIAdapter","provider_name":"OpenAI","provider_info":{"name":"OpenAI","displayName":"OpenAI","slug":"openai","baseUrl":"https://api.openai.com/v1","dataPolicy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"headquarters":"US","hasChatCompletions":true,"hasCompletions":true,"isAbortable":true,"moderationRequired":true,"adapterName":"OpenAIAdapter","statusPageUrl":"https://status.openai.com/","byokEnabled":true,"icon":{"url":"/images/icons/OpenAI.svg","className":"invert-0 dark:invert"},"sendClientIp":false,"pricingStrategy":"openai_chat_completions"},"provider_display_name":"OpenAI","provider_slug":"openai","provider_model_id":"gpt-4","quantization":"unknown","variant":"standard","is_free":false,"can_abort":true,"max_prompt_tokens":null,"max_completion_tokens":4096,"max_tokens_per_image":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","temperature","top_p","stop","frequency_penalty","presence_penalty","logit_bias","logprobs","top_logprobs","tools","tool_choice"],"excluded_parameters":[],"is_byok":false,"moderation_required":true,"data_policy":{"training":false,"trainingOpenRouter":false,"retainsPrompts":true,"canPublish":false,"termsOfServiceURL":"https://openai.com/policies/row-terms-of-use/","privacyPolicyURL":"https://openai.com/policies/privacy-policy/","requiresUserIDs":true},"pricing":{"prompt":"0.00003","completion":"0.00006","discount":0,"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00006","displayMultiplier":1000000,"unitLabel":"/M tokens"}]},"display_pricing":[{"kind":"token","sku_label":"Input Price","price":"0.00003","displayMultiplier":1000000,"unitLabel":"/M tokens"},{"kind":"token","sku_label":"Output Price","price":"0.00006","displayMultiplier":1000000,"unitLabel":"/M tokens"}],"pricing_json":{"openai:prompt_tokens":0.00003,"openai:completion_tokens":0.00006},"pricing_version_id":"db93c20d-8811-4f00-b739-e9890823b9f6","is_hidden":false,"is_private":false,"is_byok_only":false,"is_deranked":false,"is_disabled":false,"is_hipaa_eligible":false,"supports_tool_parameters":true,"supports_reasoning":false,"supports_multipart":true,"limit_rpm":null,"limit_rpd":null,"has_completions":true,"has_chat_completions":true,"features":{"supports_tool_choice":{"literal_none":true,"literal_auto":true,"literal_required":true,"type_function":true}},"supported_video_parameters":null,"supported_image_parameters":null,"provider_region":null,"deprecation_date":null,"allowed_passthrough_parameters":[],"capacity_tpm":null,"created_at":"2024-11-07T21:18:54.689Z","status":0}}],"analytics":{"anthropic/claude-3-haiku":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-3-haiku","variant":"standard","variant_permaslug":"anthropic/claude-3-haiku","count":1768240,"total_completion_tokens":252591917,"total_prompt_tokens":3189127691,"total_native_tokens_reasoning":0,"num_media_prompt":63496,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":70487,"requests_with_tool_call_errors":2434},"deepseek/deepseek-r1":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-r1","variant":"standard","variant_permaslug":"deepseek/deepseek-r1","count":410069,"total_completion_tokens":507343903,"total_prompt_tokens":2146104999,"total_native_tokens_reasoning":377049447,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1013569408,"total_tool_calls":7147,"requests_with_tool_call_errors":310},"qwen/qwen3-vl-8b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-8b-instruct","variant":"standard","variant_permaslug":"qwen/qwen3-vl-8b-instruct","count":15395336,"total_completion_tokens":894350120,"total_prompt_tokens":13020758746,"total_native_tokens_reasoning":0,"num_media_prompt":18736781,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":729461248,"total_tool_calls":35340,"requests_with_tool_call_errors":1435},"deepseek/deepseek-r1-distill-llama-70b":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-r1-distill-llama-70b","variant":"standard","variant_permaslug":"deepseek/deepseek-r1-distill-llama-70b","count":152664,"total_completion_tokens":161470393,"total_prompt_tokens":127088427,"total_native_tokens_reasoning":165397729,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":30593984,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3.6-35b-a3b-20260415":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.6-35b-a3b-20260415","variant":"standard","variant_permaslug":"qwen/qwen3.6-35b-a3b-20260415","count":12392775,"total_completion_tokens":8870537173,"total_prompt_tokens":92937915765,"total_native_tokens_reasoning":5614964447,"num_media_prompt":4417958,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":2716,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":40318553270,"total_tool_calls":1288358,"requests_with_tool_call_errors":39402},"voyageai/rerank-2.5-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/rerank-2.5-20260727","variant":"standard","variant_permaslug":"voyageai/rerank-2.5-20260727","count":2915027,"total_completion_tokens":0,"total_prompt_tokens":3551721324,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":40471056,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemma-2-27b-it":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-2-27b-it","variant":"standard","variant_permaslug":"google/gemma-2-27b-it","count":73877,"total_completion_tokens":10568525,"total_prompt_tokens":41941564,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"kwaivgi/kling-v3.0-std-20260429":{"date":"2026-08-17 00:00:00","model_permaslug":"kwaivgi/kling-v3.0-std-20260429","variant":"standard","variant_permaslug":"kwaivgi/kling-v3.0-std-20260429","count":3796,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":3732,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":24337,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"hexgrad/kokoro-82m":{"date":"2026-08-17 00:00:00","model_permaslug":"hexgrad/kokoro-82m","variant":"standard","variant_permaslug":"hexgrad/kokoro-82m","count":413596,"total_completion_tokens":0,"total_prompt_tokens":73902615,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3.1-flash-lite-image-20260630":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-lite-image-20260630","variant":"standard","variant_permaslug":"google/gemini-3.1-flash-lite-image-20260630","count":875320,"total_completion_tokens":1095163154,"total_prompt_tokens":878286591,"total_native_tokens_reasoning":7895650,"num_media_prompt":495424,"num_media_completion":803856,"image_output_requests":797060,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":56476250,"total_tool_calls":28,"requests_with_tool_call_errors":28},"qwen/qwen3.8-max-20260803":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.8-max-20260803","variant":"standard","variant_permaslug":"qwen/qwen3.8-max-20260803","count":5683779,"total_completion_tokens":9917154886,"total_prompt_tokens":350296935041,"total_native_tokens_reasoning":7113097553,"num_media_prompt":3731433,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":11171,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":298924656826,"total_tool_calls":3080448,"requests_with_tool_call_errors":121374},"microsoft/mai-voice-2":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/mai-voice-2","variant":"standard","variant_permaslug":"microsoft/mai-voice-2","count":55246,"total_completion_tokens":0,"total_prompt_tokens":2909681,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"perplexity/sonar-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/sonar-pro","variant":"standard","variant_permaslug":"perplexity/sonar-pro","count":947094,"total_completion_tokens":471067824,"total_prompt_tokens":730515364,"total_native_tokens_reasoning":0,"num_media_prompt":2278,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-sonnet-5-20260630:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-sonnet-5-20260630","variant":"batch","variant_permaslug":"anthropic/claude-sonnet-5-20260630:batch","count":196089,"total_completion_tokens":137711624,"total_prompt_tokens":524903623,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":201120674,"total_tool_calls":40,"requests_with_tool_call_errors":0},"rekaai/reka-flash-3":{"date":"2026-08-17 00:00:00","model_permaslug":"rekaai/reka-flash-3","variant":"standard","variant_permaslug":"rekaai/reka-flash-3","count":6080,"total_completion_tokens":29300254,"total_prompt_tokens":2837183,"total_native_tokens_reasoning":21376044,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":568496,"total_tool_calls":0,"requests_with_tool_call_errors":0},"deepseek/deepseek-chat-v3":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-chat-v3","variant":"standard","variant_permaslug":"deepseek/deepseek-chat-v3","count":11022193,"total_completion_tokens":2126571377,"total_prompt_tokens":25979686926,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":49084032,"total_tool_calls":391885,"requests_with_tool_call_errors":16029},"nousresearch/hermes-3-llama-3.1-405b":{"date":"2026-08-17 00:00:00","model_permaslug":"nousresearch/hermes-3-llama-3.1-405b","variant":"standard","variant_permaslug":"nousresearch/hermes-3-llama-3.1-405b","count":279659,"total_completion_tokens":32948070,"total_prompt_tokens":518362046,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mistral-medium-3":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-medium-3","variant":"standard","variant_permaslug":"mistralai/mistral-medium-3","count":124139,"total_completion_tokens":31654686,"total_prompt_tokens":285927049,"total_native_tokens_reasoning":0,"num_media_prompt":33140,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":102464951,"total_tool_calls":5968,"requests_with_tool_call_errors":37},"google/gemini-3.5-flash-20260519:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.5-flash-20260519","variant":"batch","variant_permaslug":"google/gemini-3.5-flash-20260519:batch","count":632432,"total_completion_tokens":850017220,"total_prompt_tokens":174426110,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1828707,"total_tool_calls":2,"requests_with_tool_call_errors":0},"qwen/qwen3-vl-235b-a22b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-235b-a22b-instruct","variant":"standard","variant_permaslug":"qwen/qwen3-vl-235b-a22b-instruct","count":4986549,"total_completion_tokens":1044413503,"total_prompt_tokens":16150374257,"total_native_tokens_reasoning":0,"num_media_prompt":7651420,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3696265936,"total_tool_calls":53943,"requests_with_tool_call_errors":2793},"openai/gpt-4.1-nano-2025-04-14":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4.1-nano-2025-04-14","variant":"standard","variant_permaslug":"openai/gpt-4.1-nano-2025-04-14","count":13091830,"total_completion_tokens":2234007043,"total_prompt_tokens":36877808084,"total_native_tokens_reasoning":0,"num_media_prompt":742187,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":17137038464,"total_tool_calls":261879,"requests_with_tool_call_errors":1557},"deepseek/deepseek-v4-pro-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v4-pro-20260813","variant":"standard","variant_permaslug":"deepseek/deepseek-v4-pro-20260813","count":19107987,"total_completion_tokens":28200468422,"total_prompt_tokens":1084070130643,"total_native_tokens_reasoning":16953436710,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":927893832715,"total_tool_calls":9022647,"requests_with_tool_call_errors":99737},"deepgram/flux-tts-20260812:free":{"date":"2026-08-17 00:00:00","model_permaslug":"deepgram/flux-tts-20260812","variant":"free","variant_permaslug":"deepgram/flux-tts-20260812:free","count":41708,"total_completion_tokens":0,"total_prompt_tokens":2587833,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openrouter/bodybuilder":{"date":"2026-08-17 00:00:00","model_permaslug":"openrouter/bodybuilder","variant":"standard","variant_permaslug":"openrouter/bodybuilder","count":13459,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-max":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-max","variant":"standard","variant_permaslug":"qwen/qwen3-max","count":549984,"total_completion_tokens":126962316,"total_prompt_tokens":4240729794,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2161346297,"total_tool_calls":43059,"requests_with_tool_call_errors":759},"qwen/qwen3.7-max-20260520":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.7-max-20260520","variant":"standard","variant_permaslug":"qwen/qwen3.7-max-20260520","count":1713076,"total_completion_tokens":2077323219,"total_prompt_tokens":65829176307,"total_native_tokens_reasoning":1302322330,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":56445316446,"total_tool_calls":894676,"requests_with_tool_call_errors":22754},"qwen/qwen3.5-27b-20260224":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-27b-20260224","variant":"standard","variant_permaslug":"qwen/qwen3.5-27b-20260224","count":2410836,"total_completion_tokens":580196418,"total_prompt_tokens":9399244978,"total_native_tokens_reasoning":277429407,"num_media_prompt":408625,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":648,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":365186929,"total_tool_calls":156578,"requests_with_tool_call_errors":4267},"openai/gpt-4.1-mini-2025-04-14":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4.1-mini-2025-04-14","variant":"standard","variant_permaslug":"openai/gpt-4.1-mini-2025-04-14","count":29561475,"total_completion_tokens":4257933764,"total_prompt_tokens":83359823530,"total_native_tokens_reasoning":0,"num_media_prompt":1210110,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":33377944248,"total_tool_calls":5502651,"requests_with_tool_call_errors":14162},"qwen/qwen3-next-80b-a3b-thinking-2509":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-next-80b-a3b-thinking-2509","variant":"standard","variant_permaslug":"qwen/qwen3-next-80b-a3b-thinking-2509","count":43972,"total_completion_tokens":118654957,"total_prompt_tokens":122805837,"total_native_tokens_reasoning":112410162,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":5773472,"total_tool_calls":1180,"requests_with_tool_call_errors":20},"deepseek/deepseek-chat-v3.1":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-chat-v3.1","variant":"standard","variant_permaslug":"deepseek/deepseek-chat-v3.1","count":11285794,"total_completion_tokens":1920594869,"total_prompt_tokens":47533693236,"total_native_tokens_reasoning":31597617,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":15710014376,"total_tool_calls":167378,"requests_with_tool_call_errors":2519},"bytedance-seed/seed-2.0-code-20260730":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seed-2.0-code-20260730","variant":"standard","variant_permaslug":"bytedance-seed/seed-2.0-code-20260730","count":23782,"total_completion_tokens":22604268,"total_prompt_tokens":684621752,"total_native_tokens_reasoning":14608248,"num_media_prompt":2251,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":6,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":595385344,"total_tool_calls":8300,"requests_with_tool_call_errors":184},"z-ai/glm-4.5":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.5","variant":"standard","variant_permaslug":"z-ai/glm-4.5","count":89100,"total_completion_tokens":200460506,"total_prompt_tokens":845083429,"total_native_tokens_reasoning":88715194,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":496080384,"total_tool_calls":15012,"requests_with_tool_call_errors":403},"ibm-granite/granite-4.1-8b-20260429":{"date":"2026-08-17 00:00:00","model_permaslug":"ibm-granite/granite-4.1-8b-20260429","variant":"standard","variant_permaslug":"ibm-granite/granite-4.1-8b-20260429","count":1185468,"total_completion_tokens":216926843,"total_prompt_tokens":1713326842,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":887082464,"total_tool_calls":40794,"requests_with_tool_call_errors":1778},"openai/gpt-4-turbo":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4-turbo","variant":"standard","variant_permaslug":"openai/gpt-4-turbo","count":78560,"total_completion_tokens":6875889,"total_prompt_tokens":60631082,"total_native_tokens_reasoning":0,"num_media_prompt":7284,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":692,"requests_with_tool_call_errors":18},"recraft/recraft-v4.1-utility-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4.1-utility-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4.1-utility-20260514","count":1643,"total_completion_tokens":6867875,"total_prompt_tokens":880867,"total_native_tokens_reasoning":0,"num_media_prompt":82,"num_media_completion":1645,"image_output_requests":1643,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3.6-flash-20260721":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.6-flash-20260721","variant":"standard","variant_permaslug":"google/gemini-3.6-flash-20260721","count":19849137,"total_completion_tokens":17172093560,"total_prompt_tokens":1043926597828,"total_native_tokens_reasoning":9695269601,"num_media_prompt":6611675,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":155448,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":128137,"total_native_tokens_cached":888794577342,"total_tool_calls":1910108,"requests_with_tool_call_errors":42075},"google/gemma-4-26b-a4b-it-20260403":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-4-26b-a4b-it-20260403","variant":"standard","variant_permaslug":"google/gemma-4-26b-a4b-it-20260403","count":98166981,"total_completion_tokens":22699909783,"total_prompt_tokens":371298797125,"total_native_tokens_reasoning":686296921,"num_media_prompt":9784548,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":8307,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":79703411599,"total_tool_calls":2200701,"requests_with_tool_call_errors":66487},"bytedance-seed/seedream-5-0-lite-20260812":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seedream-5-0-lite-20260812","variant":"standard","variant_permaslug":"bytedance-seed/seedream-5-0-lite-20260812","count":17012,"total_completion_tokens":328780419,"total_prompt_tokens":5484631,"total_native_tokens_reasoning":0,"num_media_prompt":12921,"num_media_completion":17044,"image_output_requests":17012,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-4.20-20260309":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-4.20-20260309","variant":"standard","variant_permaslug":"x-ai/grok-4.20-20260309","count":4169915,"total_completion_tokens":2103793120,"total_prompt_tokens":32376221137,"total_native_tokens_reasoning":461139042,"num_media_prompt":2216102,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":12861294448,"total_tool_calls":190692,"requests_with_tool_call_errors":8259},"qwen/qwen-audio-3.0-tts-plus-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-audio-3.0-tts-plus-20260723","variant":"standard","variant_permaslug":"qwen/qwen-audio-3.0-tts-plus-20260723","count":15420,"total_completion_tokens":0,"total_prompt_tokens":366321,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemma-3-4b-it":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-3-4b-it","variant":"standard","variant_permaslug":"google/gemma-3-4b-it","count":2477338,"total_completion_tokens":252657336,"total_prompt_tokens":2429911554,"total_native_tokens_reasoning":0,"num_media_prompt":330125,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-vl-30b-a3b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-30b-a3b-instruct","variant":"standard","variant_permaslug":"qwen/qwen3-vl-30b-a3b-instruct","count":5864085,"total_completion_tokens":831631909,"total_prompt_tokens":14414093198,"total_native_tokens_reasoning":0,"num_media_prompt":6179492,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":40448,"requests_with_tool_call_errors":1098},"google/gemini-3.1-flash-image-preview-20260226":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-image-preview-20260226","variant":"standard","variant_permaslug":"google/gemini-3.1-flash-image-preview-20260226","count":731110,"total_completion_tokens":1127199323,"total_prompt_tokens":791908181,"total_native_tokens_reasoning":71103092,"num_media_prompt":1081745,"num_media_completion":667935,"image_output_requests":626913,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":47764497,"total_tool_calls":14,"requests_with_tool_call_errors":14},"openai/o4-mini-high-2025-04-16":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o4-mini-high-2025-04-16","variant":"standard","variant_permaslug":"openai/o4-mini-high-2025-04-16","count":15875,"total_completion_tokens":20915154,"total_prompt_tokens":74811952,"total_native_tokens_reasoning":17479303,"num_media_prompt":2456,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":48164608,"total_tool_calls":3526,"requests_with_tool_call_errors":1},"heygen/avatar-iv-20260625":{"date":"2026-08-24 00:00:00","model_permaslug":"heygen/avatar-iv-20260625","variant":"standard","variant_permaslug":"heygen/avatar-iv-20260625","count":44,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":46,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":528.2596100000001,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":1,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/whisper-large-v3-turbo":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/whisper-large-v3-turbo","variant":"standard","variant_permaslug":"openai/whisper-large-v3-turbo","count":3495598,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":3356366119,"num_audio_prompt":3495598,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/voxtral-small-24b-2507":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/voxtral-small-24b-2507","variant":"standard","variant_permaslug":"mistralai/voxtral-small-24b-2507","count":259081,"total_completion_tokens":35149420,"total_prompt_tokens":148579435,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":185443,"total_native_tokens_cached":94817290,"total_tool_calls":3920,"requests_with_tool_call_errors":52},"fish-audio/transcribe-1-20260729":{"date":"2026-08-17 00:00:00","model_permaslug":"fish-audio/transcribe-1-20260729","variant":"standard","variant_permaslug":"fish-audio/transcribe-1-20260729","count":21048,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":2344623,"num_audio_prompt":21048,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"alibaba/wan-3.0-20260824":{"date":"2026-08-24 00:00:00","model_permaslug":"alibaba/wan-3.0-20260824","variant":"standard","variant_permaslug":"alibaba/wan-3.0-20260824","count":1,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":1,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":2,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.1-codex-20251113":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.1-codex-20251113","variant":"standard","variant_permaslug":"openai/gpt-5.1-codex-20251113","count":43023,"total_completion_tokens":30289356,"total_prompt_tokens":1546048357,"total_native_tokens_reasoning":20596607,"num_media_prompt":6225,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1443853824,"total_tool_calls":26141,"requests_with_tool_call_errors":67},"runway/gen-4.5-20260729":{"date":"2026-08-17 00:00:00","model_permaslug":"runway/gen-4.5-20260729","variant":"standard","variant_permaslug":"runway/gen-4.5-20260729","count":584,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":497,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":3061,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/ministral-3b-2512":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/ministral-3b-2512","variant":"standard","variant_permaslug":"mistralai/ministral-3b-2512","count":2380423,"total_completion_tokens":338407981,"total_prompt_tokens":2849064230,"total_native_tokens_reasoning":0,"num_media_prompt":171612,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1477407219,"total_tool_calls":53784,"requests_with_tool_call_errors":3028},"anthropic/claude-4.5-opus-20251124":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.5-opus-20251124","variant":"standard","variant_permaslug":"anthropic/claude-4.5-opus-20251124","count":1202350,"total_completion_tokens":716861421,"total_prompt_tokens":21729037339,"total_native_tokens_reasoning":96809360,"num_media_prompt":123542,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":10567292372,"total_tool_calls":341658,"requests_with_tool_call_errors":1446},"openai/text-embedding-ada-002":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/text-embedding-ada-002","variant":"standard","variant_permaslug":"openai/text-embedding-ada-002","count":4541322,"total_completion_tokens":0,"total_prompt_tokens":1118071080,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3.1-flash-image-20260528":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-image-20260528","variant":"standard","variant_permaslug":"google/gemini-3.1-flash-image-20260528","count":1737082,"total_completion_tokens":2059284616,"total_prompt_tokens":2547226329,"total_native_tokens_reasoning":17569293,"num_media_prompt":1527339,"num_media_completion":1522994,"image_output_requests":1506869,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":16865478,"total_tool_calls":39,"requests_with_tool_call_errors":39},"z-ai/glm-5.2-20260616:free":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5.2-20260616","variant":"free","variant_permaslug":"z-ai/glm-5.2-20260616:free","count":513309,"total_completion_tokens":565849311,"total_prompt_tokens":17033307075,"total_native_tokens_reasoning":220836647,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":134375424,"total_tool_calls":143432,"requests_with_tool_call_errors":3838},"google/gemini-3.1-flash-lite-20260507:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-lite-20260507","variant":"batch","variant_permaslug":"google/gemini-3.1-flash-lite-20260507:batch","count":259750,"total_completion_tokens":87870582,"total_prompt_tokens":549734274,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1110221,"total_tool_calls":0,"requests_with_tool_call_errors":0},"cohere/north-mini-code-20260617":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/north-mini-code-20260617","variant":"standard","variant_permaslug":"cohere/north-mini-code-20260617","count":1137,"total_completion_tokens":283720,"total_prompt_tokens":10286261,"total_native_tokens_reasoning":144485,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":107,"requests_with_tool_call_errors":0},"google/gemini-2.5-flash-lite:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-flash-lite","variant":"batch","variant_permaslug":"google/gemini-2.5-flash-lite:batch","count":195067,"total_completion_tokens":68495282,"total_prompt_tokens":289342902,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":33822092,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/parakeet-tdt-0.6b-v3":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/parakeet-tdt-0.6b-v3","variant":"standard","variant_permaslug":"nvidia/parakeet-tdt-0.6b-v3","count":97159,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":23446802,"num_audio_prompt":97159,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"intfloat/multilingual-e5-large":{"date":"2026-08-21 00:00:00","model_permaslug":"intfloat/multilingual-e5-large","variant":"standard","variant_permaslug":"intfloat/multilingual-e5-large","count":70,"total_completion_tokens":0,"total_prompt_tokens":8203,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"microsoft/phi-4":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/phi-4","variant":"standard","variant_permaslug":"microsoft/phi-4","count":854876,"total_completion_tokens":83809902,"total_prompt_tokens":757215102,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-coder-flash":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-coder-flash","variant":"standard","variant_permaslug":"qwen/qwen3-coder-flash","count":178740,"total_completion_tokens":43108432,"total_prompt_tokens":2520386830,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1503521562,"total_tool_calls":39496,"requests_with_tool_call_errors":1575},"openai/gpt-5.2-20251211":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.2-20251211","variant":"standard","variant_permaslug":"openai/gpt-5.2-20251211","count":3334010,"total_completion_tokens":1513895252,"total_prompt_tokens":25589224116,"total_native_tokens_reasoning":710930524,"num_media_prompt":589771,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":14682134272,"total_tool_calls":470481,"requests_with_tool_call_errors":1931},"thinkingmachines/inkling-small-20260730:free":{"date":"2026-08-21 00:00:00","model_permaslug":"thinkingmachines/inkling-small-20260730","variant":"free","variant_permaslug":"thinkingmachines/inkling-small-20260730:free","count":361021,"total_completion_tokens":190892316,"total_prompt_tokens":12178075906,"total_native_tokens_reasoning":115571203,"num_media_prompt":194108,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":9,"total_native_tokens_cached":7847316736,"total_tool_calls":217159,"requests_with_tool_call_errors":6256},"relace/relace-search-20251208":{"date":"2026-08-17 00:00:00","model_permaslug":"relace/relace-search-20251208","variant":"standard","variant_permaslug":"relace/relace-search-20251208","count":8632,"total_completion_tokens":649058,"total_prompt_tokens":6440938,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":299,"requests_with_tool_call_errors":9},"moonshotai/kimi-k2-0905":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2-0905","variant":"standard","variant_permaslug":"moonshotai/kimi-k2-0905","count":2084868,"total_completion_tokens":278495977,"total_prompt_tokens":7958719907,"total_native_tokens_reasoning":61905383,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4364055913,"total_tool_calls":48826,"requests_with_tool_call_errors":689},"google/gemini-3.7-flash-20260813:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.7-flash-20260813","variant":"batch","variant_permaslug":"google/gemini-3.7-flash-20260813:batch","count":2966018,"total_completion_tokens":2199938732,"total_prompt_tokens":6378949307,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":214481876,"total_tool_calls":9690,"requests_with_tool_call_errors":0},"perplexity/sonar-reasoning-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/sonar-reasoning-pro","variant":"standard","variant_permaslug":"perplexity/sonar-reasoning-pro","count":56874,"total_completion_tokens":62875992,"total_prompt_tokens":115547207,"total_native_tokens_reasoning":0,"num_media_prompt":1853,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"liquid/lfm-2.5-2.6b-20260811:free":{"date":"2026-08-17 00:00:00","model_permaslug":"liquid/lfm-2.5-2.6b-20260811","variant":"free","variant_permaslug":"liquid/lfm-2.5-2.6b-20260811:free","count":872982,"total_completion_tokens":911288945,"total_prompt_tokens":10059788402,"total_native_tokens_reasoning":716326471,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2482841968,"total_tool_calls":209669,"requests_with_tool_call_errors":29335},"qwen/qwen3.8-2.4t-a95b-20260812":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.8-2.4t-a95b-20260812","variant":"standard","variant_permaslug":"qwen/qwen3.8-2.4t-a95b-20260812","count":766207,"total_completion_tokens":2469650166,"total_prompt_tokens":44734207027,"total_native_tokens_reasoning":2006530925,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":39384641373,"total_tool_calls":371888,"requests_with_tool_call_errors":4523},"qwen/qwen3-coder-plus":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-coder-plus","variant":"standard","variant_permaslug":"qwen/qwen3-coder-plus","count":72327,"total_completion_tokens":22932202,"total_prompt_tokens":1966156770,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1493594715,"total_tool_calls":32298,"requests_with_tool_call_errors":1016},"deepseek/deepseek-v4-flash-20260731":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v4-flash-20260731","variant":"standard","variant_permaslug":"deepseek/deepseek-v4-flash-20260731","count":472592925,"total_completion_tokens":357772446410,"total_prompt_tokens":12617720212752,"total_native_tokens_reasoning":222772278685,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9974623294966,"total_tool_calls":134818285,"requests_with_tool_call_errors":3101275},"black-forest-labs/flux.2-flex":{"date":"2026-08-17 00:00:00","model_permaslug":"black-forest-labs/flux.2-flex","variant":"standard","variant_permaslug":"black-forest-labs/flux.2-flex","count":2832,"total_completion_tokens":14245369,"total_prompt_tokens":7502488,"total_native_tokens_reasoning":0,"num_media_prompt":1129,"num_media_completion":2832,"image_output_requests":2832,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-embedding-8b":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-embedding-8b","variant":"standard","variant_permaslug":"qwen/qwen3-embedding-8b","count":90544252,"total_completion_tokens":0,"total_prompt_tokens":109346140797,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-stt-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-stt-20260723","variant":"standard","variant_permaslug":"x-ai/grok-stt-20260723","count":145228,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":67063870,"num_audio_prompt":145228,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"moonshotai/kimi-k2.7-code-20260612":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2.7-code-20260612","variant":"standard","variant_permaslug":"moonshotai/kimi-k2.7-code-20260612","count":1817417,"total_completion_tokens":2512037374,"total_prompt_tokens":68644272323,"total_native_tokens_reasoning":1607259394,"num_media_prompt":523851,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":55258129505,"total_tool_calls":899819,"requests_with_tool_call_errors":14901},"openai/gpt-5.2-codex-20260114":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.2-codex-20260114","variant":"standard","variant_permaslug":"openai/gpt-5.2-codex-20260114","count":86886,"total_completion_tokens":40909769,"total_prompt_tokens":1932071485,"total_native_tokens_reasoning":19106147,"num_media_prompt":17373,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1679200768,"total_tool_calls":28340,"requests_with_tool_call_errors":95},"deepgram/aura-2-20260716":{"date":"2026-08-17 00:00:00","model_permaslug":"deepgram/aura-2-20260716","variant":"standard","variant_permaslug":"deepgram/aura-2-20260716","count":17013,"total_completion_tokens":0,"total_prompt_tokens":510676,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta/muse-spark-1.2-20260805":{"date":"2026-08-17 00:00:00","model_permaslug":"meta/muse-spark-1.2-20260805","variant":"standard","variant_permaslug":"meta/muse-spark-1.2-20260805","count":2173203,"total_completion_tokens":3382631127,"total_prompt_tokens":100424591094,"total_native_tokens_reasoning":2446163144,"num_media_prompt":1327683,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":16064,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":8496,"total_native_tokens_cached":69523020907,"total_tool_calls":1403765,"requests_with_tool_call_errors":5337},"openai/gpt-3.5-turbo-16k":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-3.5-turbo-16k","variant":"standard","variant_permaslug":"openai/gpt-3.5-turbo-16k","count":7677,"total_completion_tokens":208758,"total_prompt_tokens":2077246,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":534272,"total_tool_calls":156,"requests_with_tool_call_errors":0},"fish-audio/s2.1-pro-free-20260729:free":{"date":"2026-08-17 00:00:00","model_permaslug":"fish-audio/s2.1-pro-free-20260729","variant":"free","variant_permaslug":"fish-audio/s2.1-pro-free-20260729:free","count":3262972,"total_completion_tokens":0,"total_prompt_tokens":50171845,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":14137,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-4.20-multi-agent-20260309":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-4.20-multi-agent-20260309","variant":"standard","variant_permaslug":"x-ai/grok-4.20-multi-agent-20260309","count":28022,"total_completion_tokens":163807325,"total_prompt_tokens":3335410917,"total_native_tokens_reasoning":153962161,"num_media_prompt":1356,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2353748740,"total_tool_calls":0,"requests_with_tool_call_errors":0},"cohere/rerank-4-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/rerank-4-pro","variant":"standard","variant_permaslug":"cohere/rerank-4-pro","count":367676,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":22598096,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-8b-04-28":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-8b-04-28","variant":"standard","variant_permaslug":"qwen/qwen3-8b-04-28","count":1578403,"total_completion_tokens":1056725901,"total_prompt_tokens":4012284807,"total_native_tokens_reasoning":786599587,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":116207,"requests_with_tool_call_errors":1918},"bytedance-seed/seedream-5-0-pro-20260812":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seedream-5-0-pro-20260812","variant":"standard","variant_permaslug":"bytedance-seed/seedream-5-0-pro-20260812","count":48216,"total_completion_tokens":522962389,"total_prompt_tokens":21202347,"total_native_tokens_reasoning":0,"num_media_prompt":61594,"num_media_completion":48216,"image_output_requests":48216,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"upstage/solar-pro-3":{"date":"2026-08-17 00:00:00","model_permaslug":"upstage/solar-pro-3","variant":"standard","variant_permaslug":"upstage/solar-pro-3","count":35436,"total_completion_tokens":19031754,"total_prompt_tokens":70793771,"total_native_tokens_reasoning":12868700,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":37128080,"total_tool_calls":1838,"requests_with_tool_call_errors":154},"inclusionai/ling-2.6-flash-20260421":{"date":"2026-08-17 00:00:00","model_permaslug":"inclusionai/ling-2.6-flash-20260421","variant":"standard","variant_permaslug":"inclusionai/ling-2.6-flash-20260421","count":40611820,"total_completion_tokens":12685540481,"total_prompt_tokens":112852372572,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":8063527382,"total_tool_calls":146914,"requests_with_tool_call_errors":8659},"qwen/qwen3.6-max-preview-20260420":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.6-max-preview-20260420","variant":"standard","variant_permaslug":"qwen/qwen3.6-max-preview-20260420","count":48540,"total_completion_tokens":259775356,"total_prompt_tokens":328221268,"total_native_tokens_reasoning":234963971,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3683802,"total_tool_calls":5034,"requests_with_tool_call_errors":292},"bytedance-seed/seed-1.6-flash-20250625":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seed-1.6-flash-20250625","variant":"standard","variant_permaslug":"bytedance-seed/seed-1.6-flash-20250625","count":1452171,"total_completion_tokens":273181930,"total_prompt_tokens":2104538129,"total_native_tokens_reasoning":171152517,"num_media_prompt":903467,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":10454,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":2706,"requests_with_tool_call_errors":918},"mistralai/voxtral-mini-transcribe-2602":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/voxtral-mini-transcribe-2602","variant":"standard","variant_permaslug":"mistralai/voxtral-mini-transcribe-2602","count":375471,"total_completion_tokens":14149026,"total_prompt_tokens":1801625,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":52087703,"num_audio_prompt":375471,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/whisper-large-v3":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/whisper-large-v3","variant":"standard","variant_permaslug":"openai/whisper-large-v3","count":7515935,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":1056600040,"num_audio_prompt":7515935,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/minimax-m2.7-20260318":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m2.7-20260318","variant":"standard","variant_permaslug":"minimax/minimax-m2.7-20260318","count":6958316,"total_completion_tokens":3051710912,"total_prompt_tokens":245807580819,"total_native_tokens_reasoning":1953698510,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":81363618197,"total_tool_calls":1117406,"requests_with_tool_call_errors":35076},"xiaomi/mimo-v2.5-pro-20260422":{"date":"2026-08-17 00:00:00","model_permaslug":"xiaomi/mimo-v2.5-pro-20260422","variant":"standard","variant_permaslug":"xiaomi/mimo-v2.5-pro-20260422","count":11114475,"total_completion_tokens":8188934638,"total_prompt_tokens":596302349665,"total_native_tokens_reasoning":1676008300,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":521745206464,"total_tool_calls":3167917,"requests_with_tool_call_errors":69952},"mistralai/mistral-embed-2312":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-embed-2312","variant":"standard","variant_permaslug":"mistralai/mistral-embed-2312","count":1503251,"total_completion_tokens":0,"total_prompt_tokens":6005084362,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/chirp-3":{"date":"2026-08-17 00:00:00","model_permaslug":"google/chirp-3","variant":"standard","variant_permaslug":"google/chirp-3","count":51235,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":5990229,"num_audio_prompt":51235,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"moonshotai/kimi-k2":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2","variant":"standard","variant_permaslug":"moonshotai/kimi-k2","count":1561440,"total_completion_tokens":361926465,"total_prompt_tokens":3105099232,"total_native_tokens_reasoning":167620337,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1522528541,"total_tool_calls":77917,"requests_with_tool_call_errors":1087},"meta-llama/llama-3.2-1b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-3.2-1b-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-3.2-1b-instruct","count":347958,"total_completion_tokens":558971700,"total_prompt_tokens":171498667,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"baidu/ernie-4.5-vl-424b-a47b":{"date":"2026-08-17 00:00:00","model_permaslug":"baidu/ernie-4.5-vl-424b-a47b","variant":"standard","variant_permaslug":"baidu/ernie-4.5-vl-424b-a47b","count":47433,"total_completion_tokens":17316989,"total_prompt_tokens":44111035,"total_native_tokens_reasoning":790386,"num_media_prompt":7923,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"tencent/hy3-20260706":{"date":"2026-08-17 00:00:00","model_permaslug":"tencent/hy3-20260706","variant":"standard","variant_permaslug":"tencent/hy3-20260706","count":116406230,"total_completion_tokens":137288692629,"total_prompt_tokens":9072012940133,"total_native_tokens_reasoning":84286341107,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":8297566249566,"total_tool_calls":96667070,"requests_with_tool_call_errors":1403314},"openai/text-embedding-3-small":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/text-embedding-3-small","variant":"standard","variant_permaslug":"openai/text-embedding-3-small","count":129630905,"total_completion_tokens":0,"total_prompt_tokens":144757264985,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-5-20260211":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5-20260211","variant":"standard","variant_permaslug":"z-ai/glm-5-20260211","count":3470061,"total_completion_tokens":3549452143,"total_prompt_tokens":45352096382,"total_native_tokens_reasoning":1703924228,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":28345251356,"total_tool_calls":643480,"requests_with_tool_call_errors":3759},"openai/text-embedding-3-large":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/text-embedding-3-large","variant":"standard","variant_permaslug":"openai/text-embedding-3-large","count":20370487,"total_completion_tokens":0,"total_prompt_tokens":79302721025,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"upstage/solar-pro4-20260810":{"date":"2026-08-17 00:00:00","model_permaslug":"upstage/solar-pro4-20260810","variant":"standard","variant_permaslug":"upstage/solar-pro4-20260810","count":19576907,"total_completion_tokens":10121211865,"total_prompt_tokens":627045498100,"total_native_tokens_reasoning":3745926786,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":197734991024,"total_tool_calls":5430554,"requests_with_tool_call_errors":252353},"meta-llama/llama-3.2-3b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-3.2-3b-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-3.2-3b-instruct","count":737700,"total_completion_tokens":53177287,"total_prompt_tokens":480632287,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":121562640,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-3-super-120b-a12b-20230311:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","variant":"free","variant_permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311:free","count":11724963,"total_completion_tokens":12368958710,"total_prompt_tokens":455432936942,"total_native_tokens_reasoning":8954238798,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":310295238400,"total_tool_calls":5724500,"requests_with_tool_call_errors":201785},"qwen/qwen3.7-flash-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.7-flash-20260727","variant":"standard","variant_permaslug":"qwen/qwen3.7-flash-20260727","count":37167298,"total_completion_tokens":26175300055,"total_prompt_tokens":173031835939,"total_native_tokens_reasoning":17500295709,"num_media_prompt":15928222,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":30272,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":49055773142,"total_tool_calls":1815048,"requests_with_tool_call_errors":115493},"openai/gpt-5-nano-2025-08-07:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-nano-2025-08-07","variant":"batch","variant_permaslug":"openai/gpt-5-nano-2025-08-07:batch","count":257996,"total_completion_tokens":193353048,"total_prompt_tokens":492977937,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":60390144,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-vl-235b-a22b-thinking":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-235b-a22b-thinking","variant":"standard","variant_permaslug":"qwen/qwen3-vl-235b-a22b-thinking","count":56330,"total_completion_tokens":55104050,"total_prompt_tokens":160934663,"total_native_tokens_reasoning":46620245,"num_media_prompt":46984,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1704,"requests_with_tool_call_errors":90},"qwen/qwen3-asr-flash-2026-02-10":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-asr-flash-2026-02-10","variant":"standard","variant_permaslug":"qwen/qwen3-asr-flash-2026-02-10","count":263716,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":37763552,"num_audio_prompt":263716,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"voyageai/voyage-4-large-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/voyage-4-large-20260727","variant":"standard","variant_permaslug":"voyageai/voyage-4-large-20260727","count":1996672,"total_completion_tokens":0,"total_prompt_tokens":3637457808,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/ministral-8b-2512":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/ministral-8b-2512","variant":"standard","variant_permaslug":"mistralai/ministral-8b-2512","count":3773370,"total_completion_tokens":628196130,"total_prompt_tokens":4518637427,"total_native_tokens_reasoning":0,"num_media_prompt":546863,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1319155286,"total_tool_calls":83464,"requests_with_tool_call_errors":7544},"google/gemma-4-31b-it-20260402:free":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-4-31b-it-20260402","variant":"free","variant_permaslug":"google/gemma-4-31b-it-20260402:free","count":701071,"total_completion_tokens":196419394,"total_prompt_tokens":1811716844,"total_native_tokens_reasoning":14179761,"num_media_prompt":102465,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":10,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":255974085,"total_tool_calls":19659,"requests_with_tool_call_errors":417},"cohere/rerank-4-fast":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/rerank-4-fast","variant":"standard","variant_permaslug":"cohere/rerank-4-fast","count":321201,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":11459335,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mistral-nemo":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-nemo","variant":"standard","variant_permaslug":"mistralai/mistral-nemo","count":88344963,"total_completion_tokens":11608438737,"total_prompt_tokens":224056691918,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4945075249,"total_tool_calls":21271,"requests_with_tool_call_errors":287},"alibaba/wan-2.6-20260327":{"date":"2026-08-17 00:00:00","model_permaslug":"alibaba/wan-2.6-20260327","variant":"standard","variant_permaslug":"alibaba/wan-2.6-20260327","count":1041,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":583,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":7930,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/voxtral-small-24b-2507-stt-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/voxtral-small-24b-2507-stt-20260813","variant":"standard","variant_permaslug":"mistralai/voxtral-small-24b-2507-stt-20260813","count":5859,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":2042772,"num_audio_prompt":5859,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"recraft/recraft-v4.1-utility-pro-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4.1-utility-pro-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4.1-utility-pro-20260514","count":566,"total_completion_tokens":2371400,"total_prompt_tokens":233776,"total_native_tokens_reasoning":0,"num_media_prompt":63,"num_media_completion":568,"image_output_requests":566,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.8-opus-fast-20260528":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.8-opus-fast-20260528","variant":"standard","variant_permaslug":"anthropic/claude-4.8-opus-fast-20260528","count":301163,"total_completion_tokens":273023775,"total_prompt_tokens":14210447715,"total_native_tokens_reasoning":37169181,"num_media_prompt":193355,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9192777949,"total_tool_calls":54877,"requests_with_tool_call_errors":2107},"poolside/laguna-s-2.1-20260720:free":{"date":"2026-08-17 00:00:00","model_permaslug":"poolside/laguna-s-2.1-20260720","variant":"free","variant_permaslug":"poolside/laguna-s-2.1-20260720:free","count":20132294,"total_completion_tokens":13441141483,"total_prompt_tokens":1766010710308,"total_native_tokens_reasoning":6330993844,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1576201192384,"total_tool_calls":14962722,"requests_with_tool_call_errors":1470529},"google/gemini-3.1-pro-preview-20260219:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-pro-preview-20260219","variant":"batch","variant_permaslug":"google/gemini-3.1-pro-preview-20260219:batch","count":23646,"total_completion_tokens":19189983,"total_prompt_tokens":39391671,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4026759,"total_tool_calls":1517,"requests_with_tool_call_errors":0},"relace/relace-apply-3":{"date":"2026-08-17 00:00:00","model_permaslug":"relace/relace-apply-3","variant":"standard","variant_permaslug":"relace/relace-apply-3","count":32008,"total_completion_tokens":182713070,"total_prompt_tokens":211775040,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"thinkingmachines/inkling-20260715":{"date":"2026-08-17 00:00:00","model_permaslug":"thinkingmachines/inkling-20260715","variant":"standard","variant_permaslug":"thinkingmachines/inkling-20260715","count":704001,"total_completion_tokens":446265124,"total_prompt_tokens":15134256722,"total_native_tokens_reasoning":317610758,"num_media_prompt":22693,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":3783,"total_native_tokens_cached":7624364960,"total_tool_calls":359451,"requests_with_tool_call_errors":47907},"openai/o3-2025-04-16":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o3-2025-04-16","variant":"standard","variant_permaslug":"openai/o3-2025-04-16","count":158716,"total_completion_tokens":137427999,"total_prompt_tokens":745372043,"total_native_tokens_reasoning":97971022,"num_media_prompt":73035,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":431954432,"total_tool_calls":32343,"requests_with_tool_call_errors":85},"mistralai/mistral-large-2512":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-large-2512","variant":"standard","variant_permaslug":"mistralai/mistral-large-2512","count":2502339,"total_completion_tokens":766358859,"total_prompt_tokens":14233398329,"total_native_tokens_reasoning":0,"num_media_prompt":74621,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4850360390,"total_tool_calls":357339,"requests_with_tool_call_errors":3502},"qwen/qwen3-32b-04-28":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-32b-04-28","variant":"standard","variant_permaslug":"qwen/qwen3-32b-04-28","count":14840199,"total_completion_tokens":5516433835,"total_prompt_tokens":34749340999,"total_native_tokens_reasoning":4016499847,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1667749153,"total_tool_calls":576276,"requests_with_tool_call_errors":3884},"mistralai/ministral-8b":{"date":"2026-08-20 00:00:00","model_permaslug":"mistralai/ministral-8b","variant":"standard","variant_permaslug":"mistralai/ministral-8b","count":9,"total_completion_tokens":1106,"total_prompt_tokens":9560,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2176,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-235b-a22b-thinking-2507":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-235b-a22b-thinking-2507","variant":"standard","variant_permaslug":"qwen/qwen3-235b-a22b-thinking-2507","count":438520,"total_completion_tokens":722263219,"total_prompt_tokens":2158451655,"total_native_tokens_reasoning":572858174,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":25812256,"total_tool_calls":24834,"requests_with_tool_call_errors":81},"minimax/minimax-01":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-01","variant":"standard","variant_permaslug":"minimax/minimax-01","count":107467,"total_completion_tokens":16219241,"total_prompt_tokens":267192954,"total_native_tokens_reasoning":0,"num_media_prompt":697,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-imagine-image-quality-20260512":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-imagine-image-quality-20260512","variant":"standard","variant_permaslug":"x-ai/grok-imagine-image-quality-20260512","count":128127,"total_completion_tokens":534930225,"total_prompt_tokens":115064798,"total_native_tokens_reasoning":0,"num_media_prompt":95617,"num_media_completion":128122,"image_output_requests":128122,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"cohere/command-r-08-2024":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/command-r-08-2024","variant":"standard","variant_permaslug":"cohere/command-r-08-2024","count":98899,"total_completion_tokens":16006550,"total_prompt_tokens":103289407,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":6166,"requests_with_tool_call_errors":98},"bytedance-seed/seed-2-1-turbo-20260810":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seed-2-1-turbo-20260810","variant":"standard","variant_permaslug":"bytedance-seed/seed-2-1-turbo-20260810","count":90186,"total_completion_tokens":105612328,"total_prompt_tokens":821220095,"total_native_tokens_reasoning":86379085,"num_media_prompt":50769,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":1667,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":613423976,"total_tool_calls":8398,"requests_with_tool_call_errors":199},"openai/gpt-5-pro-2025-10-06":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-pro-2025-10-06","variant":"standard","variant_permaslug":"openai/gpt-5-pro-2025-10-06","count":2451,"total_completion_tokens":2843794,"total_prompt_tokens":6814340,"total_native_tokens_reasoning":2278119,"num_media_prompt":139,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":148,"requests_with_tool_call_errors":0},"openai/gpt-4o-mini-transcribe":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-mini-transcribe","variant":"standard","variant_permaslug":"openai/gpt-4o-mini-transcribe","count":626062,"total_completion_tokens":39511430,"total_prompt_tokens":153941738,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":145400799,"num_audio_prompt":626062,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-3-nano-30b-a3b:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-nano-30b-a3b","variant":"free","variant_permaslug":"nvidia/nemotron-3-nano-30b-a3b:free","count":2318624,"total_completion_tokens":3273391694,"total_prompt_tokens":44361755922,"total_native_tokens_reasoning":2613479405,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":21945758208,"total_tool_calls":528467,"requests_with_tool_call_errors":32169},"sourceful/riverflow-v2-pro-20260130":{"date":"2026-08-17 00:00:00","model_permaslug":"sourceful/riverflow-v2-pro-20260130","variant":"standard","variant_permaslug":"sourceful/riverflow-v2-pro-20260130","count":561,"total_completion_tokens":2342175,"total_prompt_tokens":588529,"total_native_tokens_reasoning":0,"num_media_prompt":470,"num_media_completion":561,"image_output_requests":561,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-3.5-turbo":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-3.5-turbo","variant":"standard","variant_permaslug":"openai/gpt-3.5-turbo","count":422765,"total_completion_tokens":41916638,"total_prompt_tokens":375039095,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":3275,"requests_with_tool_call_errors":170},"black-forest-labs/flux-3-video-20260804":{"date":"2026-08-17 00:00:00","model_permaslug":"black-forest-labs/flux-3-video-20260804","variant":"standard","variant_permaslug":"black-forest-labs/flux-3-video-20260804","count":2996,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":1839,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":15,"video_output_seconds":27334,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-max-thinking-20260123":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-max-thinking-20260123","variant":"standard","variant_permaslug":"qwen/qwen3-max-thinking-20260123","count":73565,"total_completion_tokens":21648538,"total_prompt_tokens":523623758,"total_native_tokens_reasoning":6637065,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":8814,"requests_with_tool_call_errors":189},"microsoft/mai-transcribe-1.5":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/mai-transcribe-1.5","variant":"standard","variant_permaslug":"microsoft/mai-transcribe-1.5","count":152553,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":35582512,"num_audio_prompt":152553,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"undi95/remm-slerp-l2-13b":{"date":"2026-08-17 00:00:00","model_permaslug":"undi95/remm-slerp-l2-13b","variant":"standard","variant_permaslug":"undi95/remm-slerp-l2-13b","count":67599,"total_completion_tokens":7993319,"total_prompt_tokens":109521819,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"perplexity/pplx-embed-v1-4B":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/pplx-embed-v1-4B","variant":"standard","variant_permaslug":"perplexity/pplx-embed-v1-4B","count":2385424,"total_completion_tokens":0,"total_prompt_tokens":1741456300,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/whisper-1":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/whisper-1","variant":"standard","variant_permaslug":"openai/whisper-1","count":297749,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":116759915,"num_audio_prompt":297749,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta-llama/llama-3.1-70b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-3.1-70b-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-3.1-70b-instruct","count":5823385,"total_completion_tokens":368316103,"total_prompt_tokens":4433173810,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":416264160,"total_tool_calls":12290,"requests_with_tool_call_errors":1430},"openai/gpt-4o-transcribe":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-transcribe","variant":"standard","variant_permaslug":"openai/gpt-4o-transcribe","count":108076,"total_completion_tokens":11967956,"total_prompt_tokens":47699761,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":44470593,"num_audio_prompt":108076,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-4o":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o","variant":"standard","variant_permaslug":"openai/gpt-4o","count":6477672,"total_completion_tokens":864390751,"total_prompt_tokens":14534679398,"total_native_tokens_reasoning":0,"num_media_prompt":2428746,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":5856908288,"total_tool_calls":499618,"requests_with_tool_call_errors":6282},"anthropic/claude-4.6-sonnet-20260217":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.6-sonnet-20260217","variant":"standard","variant_permaslug":"anthropic/claude-4.6-sonnet-20260217","count":33747948,"total_completion_tokens":15758192772,"total_prompt_tokens":754370310008,"total_native_tokens_reasoning":1277425008,"num_media_prompt":6435695,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":562179522156,"total_tool_calls":10747484,"requests_with_tool_call_errors":109208},"canopylabs/orpheus-3b-0.1-ft":{"date":"2026-08-17 00:00:00","model_permaslug":"canopylabs/orpheus-3b-0.1-ft","variant":"standard","variant_permaslug":"canopylabs/orpheus-3b-0.1-ft","count":24367,"total_completion_tokens":0,"total_prompt_tokens":379256,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.6-sonnet-20260217:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.6-sonnet-20260217","variant":"batch","variant_permaslug":"anthropic/claude-4.6-sonnet-20260217:batch","count":36687,"total_completion_tokens":7754543,"total_prompt_tokens":97462607,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":14571745,"total_tool_calls":4650,"requests_with_tool_call_errors":0},"openai/gpt-4o-mini:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-mini","variant":"batch","variant_permaslug":"openai/gpt-4o-mini:batch","count":10614,"total_completion_tokens":2185954,"total_prompt_tokens":12851227,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1082,"requests_with_tool_call_errors":0},"recraft/recraft-v4-vector-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4-vector-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4-vector-20260514","count":445,"total_completion_tokens":1857875,"total_prompt_tokens":109370,"total_native_tokens_reasoning":0,"num_media_prompt":40,"num_media_completion":445,"image_output_requests":445,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-embedding-2":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-embedding-2","variant":"standard","variant_permaslug":"google/gemini-embedding-2","count":20958996,"total_completion_tokens":0,"total_prompt_tokens":35474181071,"total_native_tokens_reasoning":0,"num_media_prompt":3145199,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"morph/morph-v3-large":{"date":"2026-08-17 00:00:00","model_permaslug":"morph/morph-v3-large","variant":"standard","variant_permaslug":"morph/morph-v3-large","count":16595,"total_completion_tokens":64561271,"total_prompt_tokens":71195563,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.8-opus-20260528":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.8-opus-20260528","variant":"standard","variant_permaslug":"anthropic/claude-4.8-opus-20260528","count":8477764,"total_completion_tokens":8970593144,"total_prompt_tokens":452156547248,"total_native_tokens_reasoning":2376053867,"num_media_prompt":3332767,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":334562641798,"total_tool_calls":3228467,"requests_with_tool_call_errors":53150},"z-ai/glm-4.6":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.6","variant":"standard","variant_permaslug":"z-ai/glm-4.6","count":919654,"total_completion_tokens":855376615,"total_prompt_tokens":11577229639,"total_native_tokens_reasoning":502586443,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":7172186958,"total_tool_calls":100051,"requests_with_tool_call_errors":9658},"openai/gpt-4":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4","variant":"standard","variant_permaslug":"openai/gpt-4","count":77889,"total_completion_tokens":16455263,"total_prompt_tokens":50159599,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4782464,"total_tool_calls":2463,"requests_with_tool_call_errors":43},"inclusionai/ling-2.6-1t-20260423":{"date":"2026-08-17 00:00:00","model_permaslug":"inclusionai/ling-2.6-1t-20260423","variant":"standard","variant_permaslug":"inclusionai/ling-2.6-1t-20260423","count":600517,"total_completion_tokens":294299614,"total_prompt_tokens":3492721264,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1665769020,"total_tool_calls":23581,"requests_with_tool_call_errors":1089},"minimax/minimax-m1":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m1","variant":"standard","variant_permaslug":"minimax/minimax-m1","count":23628,"total_completion_tokens":11156656,"total_prompt_tokens":74466601,"total_native_tokens_reasoning":6872528,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":2301,"requests_with_tool_call_errors":12},"amazon/nova-lite-v1":{"date":"2026-08-17 00:00:00","model_permaslug":"amazon/nova-lite-v1","variant":"standard","variant_permaslug":"amazon/nova-lite-v1","count":1079187,"total_completion_tokens":174825082,"total_prompt_tokens":3602387216,"total_native_tokens_reasoning":0,"num_media_prompt":850554,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":438900,"requests_with_tool_call_errors":598},"qwen/qwen3-30b-a3b-04-28":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-30b-a3b-04-28","variant":"standard","variant_permaslug":"qwen/qwen3-30b-a3b-04-28","count":473309,"total_completion_tokens":422350039,"total_prompt_tokens":1358198880,"total_native_tokens_reasoning":286247702,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":8528,"requests_with_tool_call_errors":263},"voyageai/rerank-2.5-lite-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/rerank-2.5-lite-20260727","variant":"standard","variant_permaslug":"voyageai/rerank-2.5-lite-20260727","count":275819,"total_completion_tokens":0,"total_prompt_tokens":4376576349,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":20399188,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"sao10k/l3.3-euryale-70b-v2.3":{"date":"2026-08-17 00:00:00","model_permaslug":"sao10k/l3.3-euryale-70b-v2.3","variant":"standard","variant_permaslug":"sao10k/l3.3-euryale-70b-v2.3","count":136640,"total_completion_tokens":14758406,"total_prompt_tokens":349112679,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"sentence-transformers/all-minilm-l12-v2-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"sentence-transformers/all-minilm-l12-v2-20251117","variant":"standard","variant_permaslug":"sentence-transformers/all-minilm-l12-v2-20251117","count":6394757,"total_completion_tokens":0,"total_prompt_tokens":312373636,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/speech-2.8-turbo-20260716":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/speech-2.8-turbo-20260716","variant":"standard","variant_permaslug":"minimax/speech-2.8-turbo-20260716","count":14133,"total_completion_tokens":0,"total_prompt_tokens":523815,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.5-pro-20260423":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.5-pro-20260423","variant":"standard","variant_permaslug":"openai/gpt-5.5-pro-20260423","count":200494,"total_completion_tokens":33774531,"total_prompt_tokens":341950345,"total_native_tokens_reasoning":23917072,"num_media_prompt":5304,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":4985,"requests_with_tool_call_errors":54},"tencent/hunyuan-a13b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"tencent/hunyuan-a13b-instruct","variant":"standard","variant_permaslug":"tencent/hunyuan-a13b-instruct","count":32881,"total_completion_tokens":17773220,"total_prompt_tokens":29691509,"total_native_tokens_reasoning":9853814,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1350016,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-embedding-001":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-embedding-001","variant":"standard","variant_permaslug":"google/gemini-embedding-001","count":15044595,"total_completion_tokens":0,"total_prompt_tokens":7825670169,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-coder-next-2025-02-03":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-coder-next-2025-02-03","variant":"standard","variant_permaslug":"qwen/qwen3-coder-next-2025-02-03","count":913580,"total_completion_tokens":281127900,"total_prompt_tokens":25311275861,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":18787510560,"total_tool_calls":384977,"requests_with_tool_call_errors":33565},"mistralai/mistral-small-24b-instruct-2501":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-small-24b-instruct-2501","variant":"standard","variant_permaslug":"mistralai/mistral-small-24b-instruct-2501","count":7063201,"total_completion_tokens":1574747898,"total_prompt_tokens":11603684838,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3.5-plus-20260420":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-plus-20260420","variant":"standard","variant_permaslug":"qwen/qwen3.5-plus-20260420","count":93085,"total_completion_tokens":109387987,"total_prompt_tokens":1502500930,"total_native_tokens_reasoning":80231149,"num_media_prompt":29329,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":48,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9999841,"total_tool_calls":22067,"requests_with_tool_call_errors":943},"google/gemini-2.5-flash:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-flash","variant":"batch","variant_permaslug":"google/gemini-2.5-flash:batch","count":123320,"total_completion_tokens":345580024,"total_prompt_tokens":777478314,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":608760749,"total_tool_calls":996,"requests_with_tool_call_errors":0},"qwen/qwen-plus-2025-07-28":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-plus-2025-07-28","variant":"standard","variant_permaslug":"qwen/qwen-plus-2025-07-28","count":153067,"total_completion_tokens":23659090,"total_prompt_tokens":404006431,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":91087,"requests_with_tool_call_errors":1981},"nvidia/llama-nemotron-embed-vl-1b-v2-20260224:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/llama-nemotron-embed-vl-1b-v2-20260224","variant":"free","variant_permaslug":"nvidia/llama-nemotron-embed-vl-1b-v2-20260224:free","count":3911164,"total_completion_tokens":0,"total_prompt_tokens":4945279321,"total_native_tokens_reasoning":0,"num_media_prompt":373201,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.6-luna-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-luna-20260709","variant":"standard","variant_permaslug":"openai/gpt-5.6-luna-20260709","count":310635684,"total_completion_tokens":124304420266,"total_prompt_tokens":5287886048177,"total_native_tokens_reasoning":39454209695,"num_media_prompt":59327208,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4348994382830,"total_tool_calls":70847374,"requests_with_tool_call_errors":5871158},"anthropic/claude-4.7-opus-20260416:batch":{"date":"2026-08-21 00:00:00","model_permaslug":"anthropic/claude-4.7-opus-20260416","variant":"batch","variant_permaslug":"anthropic/claude-4.7-opus-20260416:batch","count":3413,"total_completion_tokens":143637,"total_prompt_tokens":44122246,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":41648310,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nex-agi/nex-n2-mini":{"date":"2026-08-17 00:00:00","model_permaslug":"nex-agi/nex-n2-mini","variant":"standard","variant_permaslug":"nex-agi/nex-n2-mini","count":1811883,"total_completion_tokens":1503186699,"total_prompt_tokens":20051813534,"total_native_tokens_reasoning":1271526292,"num_media_prompt":866526,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":8211739992,"total_tool_calls":126083,"requests_with_tool_call_errors":5959},"anthropic/claude-opus-5-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-opus-5-20260723","variant":"standard","variant_permaslug":"anthropic/claude-opus-5-20260723","count":19808647,"total_completion_tokens":43774972876,"total_prompt_tokens":1653363850788,"total_native_tokens_reasoning":22970000468,"num_media_prompt":9158437,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1406835419851,"total_tool_calls":12571868,"requests_with_tool_call_errors":101218},"cohere/north-mini-code-20260617:free":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/north-mini-code-20260617","variant":"free","variant_permaslug":"cohere/north-mini-code-20260617:free","count":5862323,"total_completion_tokens":27331231137,"total_prompt_tokens":211939695426,"total_native_tokens_reasoning":20198478079,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1015298,"requests_with_tool_call_errors":53563},"google/gemini-2.5-flash-image":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-flash-image","variant":"standard","variant_permaslug":"google/gemini-2.5-flash-image","count":1203900,"total_completion_tokens":1210680013,"total_prompt_tokens":1578171032,"total_native_tokens_reasoning":13762,"num_media_prompt":867977,"num_media_completion":917115,"image_output_requests":910012,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"writer/palmyra-x5-20250428":{"date":"2026-08-17 00:00:00","model_permaslug":"writer/palmyra-x5-20250428","variant":"standard","variant_permaslug":"writer/palmyra-x5-20250428","count":16600,"total_completion_tokens":2057504,"total_prompt_tokens":35703807,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-14b-04-28":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-14b-04-28","variant":"standard","variant_permaslug":"qwen/qwen3-14b-04-28","count":1943793,"total_completion_tokens":777626819,"total_prompt_tokens":2911477696,"total_native_tokens_reasoning":380611830,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":57727,"requests_with_tool_call_errors":1318},"openai/gpt-5.6-luna-20260709:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-luna-20260709","variant":"batch","variant_permaslug":"openai/gpt-5.6-luna-20260709:batch","count":1407699,"total_completion_tokens":5503509787,"total_prompt_tokens":5284185671,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1594102867,"total_tool_calls":3104,"requests_with_tool_call_errors":0},"qwen/qwen3.6-27b-20260422":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.6-27b-20260422","variant":"standard","variant_permaslug":"qwen/qwen3.6-27b-20260422","count":3224175,"total_completion_tokens":2095006574,"total_prompt_tokens":28868411095,"total_native_tokens_reasoning":1188190180,"num_media_prompt":399947,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":255,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9192452820,"total_tool_calls":652430,"requests_with_tool_call_errors":22588},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","variant":"free","variant_permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428:free","count":1703587,"total_completion_tokens":4349903337,"total_prompt_tokens":30134490965,"total_native_tokens_reasoning":3690095563,"num_media_prompt":351411,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":3966,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":1866,"total_native_tokens_cached":17566717440,"total_tool_calls":343726,"requests_with_tool_call_errors":20076},"mistralai/codestral-embed-2505":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/codestral-embed-2505","variant":"standard","variant_permaslug":"mistralai/codestral-embed-2505","count":204901,"total_completion_tokens":0,"total_prompt_tokens":817959472,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-transcribe-20260805":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-transcribe-20260805","variant":"standard","variant_permaslug":"openai/gpt-transcribe-20260805","count":171381,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":36980250,"num_audio_prompt":171381,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"tencent/hy3-preview-20260421":{"date":"2026-08-17 00:00:00","model_permaslug":"tencent/hy3-preview-20260421","variant":"standard","variant_permaslug":"tencent/hy3-preview-20260421","count":2171055,"total_completion_tokens":2999487725,"total_prompt_tokens":15742095072,"total_native_tokens_reasoning":2298124958,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":10118999872,"total_tool_calls":109905,"requests_with_tool_call_errors":2120},"thenlper/gte-base-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"thenlper/gte-base-20251117","variant":"standard","variant_permaslug":"thenlper/gte-base-20251117","count":65914,"total_completion_tokens":0,"total_prompt_tokens":235430879,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.5-sonnet-20250929":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.5-sonnet-20250929","variant":"standard","variant_permaslug":"anthropic/claude-4.5-sonnet-20250929","count":8062736,"total_completion_tokens":3584739549,"total_prompt_tokens":84229741856,"total_native_tokens_reasoning":202621526,"num_media_prompt":638730,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":39495487358,"total_tool_calls":1343674,"requests_with_tool_call_errors":39768},"openai/gpt-5.4-nano-20260317":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-nano-20260317","variant":"standard","variant_permaslug":"openai/gpt-5.4-nano-20260317","count":31093808,"total_completion_tokens":6249354533,"total_prompt_tokens":132804268248,"total_native_tokens_reasoning":1605904165,"num_media_prompt":266461,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":70423120384,"total_tool_calls":3538325,"requests_with_tool_call_errors":16985},"openai/gpt-5.4-20260305:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-20260305","variant":"batch","variant_permaslug":"openai/gpt-5.4-20260305:batch","count":8857,"total_completion_tokens":118364892,"total_prompt_tokens":29644187,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":6912640,"total_tool_calls":0,"requests_with_tool_call_errors":0},"deepseek/deepseek-v4-flash-vision-exp-20260821":{"date":"2026-08-21 00:00:00","model_permaslug":"deepseek/deepseek-v4-flash-vision-exp-20260821","variant":"standard","variant_permaslug":"deepseek/deepseek-v4-flash-vision-exp-20260821","count":807383,"total_completion_tokens":975899503,"total_prompt_tokens":74739634851,"total_native_tokens_reasoning":687177700,"num_media_prompt":1736368,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":67752710144,"total_tool_calls":520325,"requests_with_tool_call_errors":7685},"openai/gpt-5.6-sol-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-sol-20260709","variant":"standard","variant_permaslug":"openai/gpt-5.6-sol-20260709","count":29217123,"total_completion_tokens":18618673537,"total_prompt_tokens":1488730096201,"total_native_tokens_reasoning":8393669379,"num_media_prompt":17733558,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1314052770063,"total_tool_calls":17501772,"requests_with_tool_call_errors":2457077},"recraft/recraft-v4.1-pro-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4.1-pro-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4.1-pro-20260514","count":772,"total_completion_tokens":3294075,"total_prompt_tokens":250783,"total_native_tokens_reasoning":0,"num_media_prompt":159,"num_media_completion":789,"image_output_requests":772,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"thedrummer/skyfall-36b-v2":{"date":"2026-08-17 00:00:00","model_permaslug":"thedrummer/skyfall-36b-v2","variant":"standard","variant_permaslug":"thedrummer/skyfall-36b-v2","count":74367,"total_completion_tokens":15976138,"total_prompt_tokens":209338452,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":131933488,"total_tool_calls":0,"requests_with_tool_call_errors":0},"moonshotai/kimi-k2.5-0127":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2.5-0127","variant":"standard","variant_permaslug":"moonshotai/kimi-k2.5-0127","count":6277080,"total_completion_tokens":5684589437,"total_prompt_tokens":82071785521,"total_native_tokens_reasoning":3272567713,"num_media_prompt":443048,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":62713940157,"total_tool_calls":1177325,"requests_with_tool_call_errors":23911},"google/gemini-3.5-flash-20260519":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.5-flash-20260519","variant":"standard","variant_permaslug":"google/gemini-3.5-flash-20260519","count":16691807,"total_completion_tokens":16283249522,"total_prompt_tokens":131103262343,"total_native_tokens_reasoning":11808457755,"num_media_prompt":5861406,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":520344,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":149839,"total_native_tokens_cached":66254639908,"total_tool_calls":1637818,"requests_with_tool_call_errors":84747},"mistralai/mistral-small-2603":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-small-2603","variant":"standard","variant_permaslug":"mistralai/mistral-small-2603","count":4730155,"total_completion_tokens":1627253027,"total_prompt_tokens":16335100516,"total_native_tokens_reasoning":156736601,"num_media_prompt":100692,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":7320119590,"total_tool_calls":242802,"requests_with_tool_call_errors":10182},"sourceful/riverflow-v2.5-fast-20260605":{"date":"2026-08-17 00:00:00","model_permaslug":"sourceful/riverflow-v2.5-fast-20260605","variant":"standard","variant_permaslug":"sourceful/riverflow-v2.5-fast-20260605","count":5603,"total_completion_tokens":23392525,"total_prompt_tokens":1736534,"total_native_tokens_reasoning":0,"num_media_prompt":1046,"num_media_completion":5603,"image_output_requests":5603,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o3-pro-2025-06-10":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o3-pro-2025-06-10","variant":"standard","variant_permaslug":"openai/o3-pro-2025-06-10","count":2696,"total_completion_tokens":1114227,"total_prompt_tokens":8329249,"total_native_tokens_reasoning":699417,"num_media_prompt":876,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":319,"requests_with_tool_call_errors":0},"mistralai/mistral-medium-3.1":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-medium-3.1","variant":"standard","variant_permaslug":"mistralai/mistral-medium-3.1","count":568011,"total_completion_tokens":221091957,"total_prompt_tokens":2505832171,"total_native_tokens_reasoning":0,"num_media_prompt":23746,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1305893281,"total_tool_calls":25868,"requests_with_tool_call_errors":518},"sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117","variant":"standard","variant_permaslug":"sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117","count":1341,"total_completion_tokens":0,"total_prompt_tokens":586804,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3.6-plus-04-02":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.6-plus-04-02","variant":"standard","variant_permaslug":"qwen/qwen3.6-plus-04-02","count":3681990,"total_completion_tokens":1974544396,"total_prompt_tokens":23113066037,"total_native_tokens_reasoning":1475508121,"num_media_prompt":186539,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":40192,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1834691190,"total_tool_calls":551565,"requests_with_tool_call_errors":23592},"fish-audio/s1-20260729":{"date":"2026-08-17 00:00:00","model_permaslug":"fish-audio/s1-20260729","variant":"standard","variant_permaslug":"fish-audio/s1-20260729","count":1444,"total_completion_tokens":0,"total_prompt_tokens":54430,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4-opus-20250522":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4-opus-20250522","variant":"standard","variant_permaslug":"anthropic/claude-4-opus-20250522","count":85182,"total_completion_tokens":21058607,"total_prompt_tokens":627313656,"total_native_tokens_reasoning":2107197,"num_media_prompt":1344,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":310883086,"total_tool_calls":22319,"requests_with_tool_call_errors":143},"google/veo-3.1-20260320":{"date":"2026-08-17 00:00:00","model_permaslug":"google/veo-3.1-20260320","variant":"standard","variant_permaslug":"google/veo-3.1-20260320","count":4495,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":4340,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":31220,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"kwaipilot/kat-coder-pro-v2.5-20260710":{"date":"2026-08-17 00:00:00","model_permaslug":"kwaipilot/kat-coder-pro-v2.5-20260710","variant":"standard","variant_permaslug":"kwaipilot/kat-coder-pro-v2.5-20260710","count":30412,"total_completion_tokens":21965878,"total_prompt_tokens":902831178,"total_native_tokens_reasoning":11648854,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":589722421,"total_tool_calls":13504,"requests_with_tool_call_errors":116},"sao10k/l3.1-euryale-70b":{"date":"2026-08-17 00:00:00","model_permaslug":"sao10k/l3.1-euryale-70b","variant":"standard","variant_permaslug":"sao10k/l3.1-euryale-70b","count":73612,"total_completion_tokens":16470759,"total_prompt_tokens":217078895,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta-llama/llama-3.1-8b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-3.1-8b-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-3.1-8b-instruct","count":69889470,"total_completion_tokens":5306785849,"total_prompt_tokens":63500790266,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":22869754496,"total_tool_calls":112427,"requests_with_tool_call_errors":34046},"anthropic/claude-4-sonnet-20250522":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4-sonnet-20250522","variant":"standard","variant_permaslug":"anthropic/claude-4-sonnet-20250522","count":2482033,"total_completion_tokens":827171353,"total_prompt_tokens":22234043387,"total_native_tokens_reasoning":9894200,"num_media_prompt":116359,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":10215905926,"total_tool_calls":419818,"requests_with_tool_call_errors":8289},"x-ai/grok-4.5-20260708":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-4.5-20260708","variant":"standard","variant_permaslug":"x-ai/grok-4.5-20260708","count":4453928,"total_completion_tokens":3760685337,"total_prompt_tokens":161243576009,"total_native_tokens_reasoning":1901300602,"num_media_prompt":1377301,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":132435395712,"total_tool_calls":1836451,"requests_with_tool_call_errors":12784},"liquid/lfm-2.5-2.6b-20260811":{"date":"2026-08-17 00:00:00","model_permaslug":"liquid/lfm-2.5-2.6b-20260811","variant":"standard","variant_permaslug":"liquid/lfm-2.5-2.6b-20260811","count":223,"total_completion_tokens":258543,"total_prompt_tokens":2902346,"total_native_tokens_reasoning":159397,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1685584,"total_tool_calls":40,"requests_with_tool_call_errors":0},"minimax/hailuo-2.3-20260420":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/hailuo-2.3-20260420","variant":"standard","variant_permaslug":"minimax/hailuo-2.3-20260420","count":328,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":233,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":2004,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-opus-5-20260723:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-opus-5-20260723","variant":"batch","variant_permaslug":"anthropic/claude-opus-5-20260723:batch","count":155422,"total_completion_tokens":248117691,"total_prompt_tokens":1289020365,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":33276987,"total_tool_calls":3444,"requests_with_tool_call_errors":0},"z-ai/glm-4.7-20251222":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.7-20251222","variant":"standard","variant_permaslug":"z-ai/glm-4.7-20251222","count":4682908,"total_completion_tokens":3537760544,"total_prompt_tokens":50736489877,"total_native_tokens_reasoning":1555013451,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":23901980977,"total_tool_calls":346601,"requests_with_tool_call_errors":9292},"voyageai/voyage-4-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/voyage-4-20260727","variant":"standard","variant_permaslug":"voyageai/voyage-4-20260727","count":315282,"total_completion_tokens":0,"total_prompt_tokens":5791524138,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"amazon/nova-pro-v1":{"date":"2026-08-17 00:00:00","model_permaslug":"amazon/nova-pro-v1","variant":"standard","variant_permaslug":"amazon/nova-pro-v1","count":44077,"total_completion_tokens":9675409,"total_prompt_tokens":115949773,"total_native_tokens_reasoning":0,"num_media_prompt":3717,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1608,"requests_with_tool_call_errors":105},"baai/bge-large-en-v1.5-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"baai/bge-large-en-v1.5-20251117","variant":"standard","variant_permaslug":"baai/bge-large-en-v1.5-20251117","count":88412,"total_completion_tokens":0,"total_prompt_tokens":104688910,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/speech-2.8-hd-20260716":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/speech-2.8-hd-20260716","variant":"standard","variant_permaslug":"minimax/speech-2.8-hd-20260716","count":5073,"total_completion_tokens":0,"total_prompt_tokens":157916,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.6-sol-pro-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-sol-pro-20260709","variant":"standard","variant_permaslug":"openai/gpt-5.6-sol-pro-20260709","count":595576,"total_completion_tokens":2307180286,"total_prompt_tokens":96777427535,"total_native_tokens_reasoning":1319786725,"num_media_prompt":5715749,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":73017345212,"total_tool_calls":212742,"requests_with_tool_call_errors":7184},"nousresearch/hermes-3-llama-3.1-70b":{"date":"2026-08-17 00:00:00","model_permaslug":"nousresearch/hermes-3-llama-3.1-70b","variant":"standard","variant_permaslug":"nousresearch/hermes-3-llama-3.1-70b","count":214298,"total_completion_tokens":50317440,"total_prompt_tokens":476416453,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"sao10k/l3-lunaris-8b":{"date":"2026-08-17 00:00:00","model_permaslug":"sao10k/l3-lunaris-8b","variant":"standard","variant_permaslug":"sao10k/l3-lunaris-8b","count":2369586,"total_completion_tokens":433091139,"total_prompt_tokens":5660873656,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":187955472,"total_tool_calls":0,"requests_with_tool_call_errors":0},"recraft/recraft-v3-20260413":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v3-20260413","variant":"standard","variant_permaslug":"recraft/recraft-v3-20260413","count":987,"total_completion_tokens":4170825,"total_prompt_tokens":117210,"total_native_tokens_reasoning":0,"num_media_prompt":92,"num_media_completion":999,"image_output_requests":987,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3.5-35b-a3b-20260224":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-35b-a3b-20260224","variant":"standard","variant_permaslug":"qwen/qwen3.5-35b-a3b-20260224","count":3160248,"total_completion_tokens":2582972455,"total_prompt_tokens":15671494473,"total_native_tokens_reasoning":1199736805,"num_media_prompt":488616,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":1589,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3064786176,"total_tool_calls":234225,"requests_with_tool_call_errors":6986},"aion-labs/aion-2.0-20260223":{"date":"2026-08-17 00:00:00","model_permaslug":"aion-labs/aion-2.0-20260223","variant":"standard","variant_permaslug":"aion-labs/aion-2.0-20260223","count":213498,"total_completion_tokens":206627853,"total_prompt_tokens":1931080326,"total_native_tokens_reasoning":105759359,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1149905403,"total_tool_calls":8178,"requests_with_tool_call_errors":1021},"nvidia/nemotron-3.5-content-safety-20260604:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3.5-content-safety-20260604","variant":"free","variant_permaslug":"nvidia/nemotron-3.5-content-safety-20260604:free","count":588976,"total_completion_tokens":85324106,"total_prompt_tokens":1275947139,"total_native_tokens_reasoning":90543372,"num_media_prompt":60911,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/minimax-m2":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m2","variant":"standard","variant_permaslug":"minimax/minimax-m2","count":108554,"total_completion_tokens":47469950,"total_prompt_tokens":966449915,"total_native_tokens_reasoning":34348604,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":85536662,"total_tool_calls":34229,"requests_with_tool_call_errors":532},"bytedance/seedance-2.0-mini-20260811":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance/seedance-2.0-mini-20260811","variant":"standard","variant_permaslug":"bytedance/seedance-2.0-mini-20260811","count":29459,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":26003,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":412,"video_output_seconds":255807,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":255,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"aion-labs/aion-3.0-mini-20260707":{"date":"2026-08-17 00:00:00","model_permaslug":"aion-labs/aion-3.0-mini-20260707","variant":"standard","variant_permaslug":"aion-labs/aion-3.0-mini-20260707","count":176604,"total_completion_tokens":225171584,"total_prompt_tokens":2074418893,"total_native_tokens_reasoning":119203227,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1465301701,"total_tool_calls":2592,"requests_with_tool_call_errors":227},"intfloat/e5-large-v2-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"intfloat/e5-large-v2-20251117","variant":"standard","variant_permaslug":"intfloat/e5-large-v2-20251117","count":203110,"total_completion_tokens":0,"total_prompt_tokens":91346067,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"black-forest-labs/flux-video-upscale-20260819":{"date":"2026-08-21 00:00:00","model_permaslug":"black-forest-labs/flux-video-upscale-20260819","variant":"standard","variant_permaslug":"black-forest-labs/flux-video-upscale-20260819","count":77,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":77,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-4.3-20260430":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-4.3-20260430","variant":"standard","variant_permaslug":"x-ai/grok-4.3-20260430","count":12396997,"total_completion_tokens":7077388246,"total_prompt_tokens":59516810886,"total_native_tokens_reasoning":4927364233,"num_media_prompt":2770108,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":30849084137,"total_tool_calls":1236934,"requests_with_tool_call_errors":1327},"openai/o1-2024-12-17":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o1-2024-12-17","variant":"standard","variant_permaslug":"openai/o1-2024-12-17","count":7035,"total_completion_tokens":6535901,"total_prompt_tokens":22814145,"total_native_tokens_reasoning":5901000,"num_media_prompt":250,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":15528576,"total_tool_calls":756,"requests_with_tool_call_errors":3},"nousresearch/hermes-4-70b":{"date":"2026-08-17 00:00:00","model_permaslug":"nousresearch/hermes-4-70b","variant":"standard","variant_permaslug":"nousresearch/hermes-4-70b","count":1144501,"total_completion_tokens":205459897,"total_prompt_tokens":3299817453,"total_native_tokens_reasoning":2907802,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1832418007,"total_tool_calls":0,"requests_with_tool_call_errors":0},"perplexity/pplx-embed-v1-0.6b":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/pplx-embed-v1-0.6b","variant":"standard","variant_permaslug":"perplexity/pplx-embed-v1-0.6b","count":4183,"total_completion_tokens":0,"total_prompt_tokens":138344,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen-plus-2025-07-28:thinking":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-plus-2025-07-28","variant":"thinking","variant_permaslug":"qwen/qwen-plus-2025-07-28:thinking","count":14184,"total_completion_tokens":12467414,"total_prompt_tokens":81349038,"total_native_tokens_reasoning":10719996,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1889,"requests_with_tool_call_errors":71},"arcee-ai/trinity-large-thinking":{"date":"2026-08-17 00:00:00","model_permaslug":"arcee-ai/trinity-large-thinking","variant":"standard","variant_permaslug":"arcee-ai/trinity-large-thinking","count":504426,"total_completion_tokens":169902063,"total_prompt_tokens":615406831,"total_native_tokens_reasoning":138724078,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":495983344,"total_tool_calls":10815,"requests_with_tool_call_errors":477},"google/gemini-2.5-pro:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-pro","variant":"batch","variant_permaslug":"google/gemini-2.5-pro:batch","count":7691,"total_completion_tokens":14906160,"total_prompt_tokens":25291581,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2601241,"total_tool_calls":0,"requests_with_tool_call_errors":0},"amazon/nova-premier-v1":{"date":"2026-08-17 00:00:00","model_permaslug":"amazon/nova-premier-v1","variant":"standard","variant_permaslug":"amazon/nova-premier-v1","count":43032,"total_completion_tokens":10636613,"total_prompt_tokens":189992860,"total_native_tokens_reasoning":0,"num_media_prompt":26255,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":4417,"requests_with_tool_call_errors":5},"meta-llama/llama-4-maverick-17b-128e-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-4-maverick-17b-128e-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-4-maverick-17b-128e-instruct","count":9855536,"total_completion_tokens":1131906410,"total_prompt_tokens":21440867523,"total_native_tokens_reasoning":0,"num_media_prompt":1484305,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1427263808,"total_tool_calls":60023,"requests_with_tool_call_errors":1937},"aion-labs/aion-3.0-20260707":{"date":"2026-08-17 00:00:00","model_permaslug":"aion-labs/aion-3.0-20260707","variant":"standard","variant_permaslug":"aion-labs/aion-3.0-20260707","count":479771,"total_completion_tokens":882016874,"total_prompt_tokens":8826735786,"total_native_tokens_reasoning":255993217,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":5326922350,"total_tool_calls":3053,"requests_with_tool_call_errors":192},"poolside/laguna-s-2.1-20260720":{"date":"2026-08-17 00:00:00","model_permaslug":"poolside/laguna-s-2.1-20260720","variant":"standard","variant_permaslug":"poolside/laguna-s-2.1-20260720","count":811392,"total_completion_tokens":723916949,"total_prompt_tokens":60839456067,"total_native_tokens_reasoning":295254962,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":58344742562,"total_tool_calls":361232,"requests_with_tool_call_errors":38187},"qwen/qwen3-coder-480b-a35b-07-25":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-coder-480b-a35b-07-25","variant":"standard","variant_permaslug":"qwen/qwen3-coder-480b-a35b-07-25","count":835025,"total_completion_tokens":230603658,"total_prompt_tokens":14728498974,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":10130801192,"total_tool_calls":329337,"requests_with_tool_call_errors":6245},"mistralai/devstral-2512":{"date":"2026-08-24 00:00:00","model_permaslug":"mistralai/devstral-2512","variant":"standard","variant_permaslug":"mistralai/devstral-2512","count":1,"total_completion_tokens":5,"total_prompt_tokens":11,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.4-nano-20260317:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-nano-20260317","variant":"batch","variant_permaslug":"openai/gpt-5.4-nano-20260317:batch","count":4114,"total_completion_tokens":4048528,"total_prompt_tokens":6561948,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":277504,"total_tool_calls":0,"requests_with_tool_call_errors":0},"kwaivgi/kling-video-o1-20260420":{"date":"2026-08-17 00:00:00","model_permaslug":"kwaivgi/kling-video-o1-20260420","variant":"standard","variant_permaslug":"kwaivgi/kling-video-o1-20260420","count":1169,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":1187,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":6555,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"bytedance-seed/seed-2.0-lite-20260309":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seed-2.0-lite-20260309","variant":"standard","variant_permaslug":"bytedance-seed/seed-2.0-lite-20260309","count":167805,"total_completion_tokens":92968618,"total_prompt_tokens":1476552684,"total_native_tokens_reasoning":63788664,"num_media_prompt":214407,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":6050,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":543980136,"total_tool_calls":9673,"requests_with_tool_call_errors":5},"thinkingmachines/inkling-small-20260730":{"date":"2026-08-17 00:00:00","model_permaslug":"thinkingmachines/inkling-small-20260730","variant":"standard","variant_permaslug":"thinkingmachines/inkling-small-20260730","count":732209,"total_completion_tokens":533358338,"total_prompt_tokens":12997665475,"total_native_tokens_reasoning":377422437,"num_media_prompt":55990,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":11170,"total_native_tokens_cached":11285064736,"total_tool_calls":159482,"requests_with_tool_call_errors":1168},"openai/gpt-5.5-20260423":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.5-20260423","variant":"standard","variant_permaslug":"openai/gpt-5.5-20260423","count":8959341,"total_completion_tokens":6321757368,"total_prompt_tokens":422222832909,"total_native_tokens_reasoning":2786762794,"num_media_prompt":2631050,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":368469485708,"total_tool_calls":4619119,"requests_with_tool_call_errors":16920},"meta-llama/llama-3.3-70b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-3.3-70b-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-3.3-70b-instruct","count":19967161,"total_completion_tokens":2683813434,"total_prompt_tokens":33099120024,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4320708006,"total_tool_calls":387343,"requests_with_tool_call_errors":52102},"nvidia/nemotron-3.5-lightning-20260807:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3.5-lightning-20260807","variant":"free","variant_permaslug":"nvidia/nemotron-3.5-lightning-20260807:free","count":15285700,"total_completion_tokens":11222835232,"total_prompt_tokens":1106086654426,"total_native_tokens_reasoning":7089394102,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":940978847232,"total_tool_calls":11306997,"requests_with_tool_call_errors":233049},"qwen/qwen3.5-122b-a10b-20260224":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-122b-a10b-20260224","variant":"standard","variant_permaslug":"qwen/qwen3.5-122b-a10b-20260224","count":2715851,"total_completion_tokens":2978557200,"total_prompt_tokens":14015737280,"total_native_tokens_reasoning":725565606,"num_media_prompt":1425055,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":1127,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":145198,"requests_with_tool_call_errors":6516},"anthropic/claude-5-fable-20260609:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-5-fable-20260609","variant":"batch","variant_permaslug":"anthropic/claude-5-fable-20260609:batch","count":291458,"total_completion_tokens":345342849,"total_prompt_tokens":468000250,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2023641,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3.8-27b-20260814":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.8-27b-20260814","variant":"standard","variant_permaslug":"qwen/qwen3.8-27b-20260814","count":6162184,"total_completion_tokens":10464241290,"total_prompt_tokens":140648654824,"total_native_tokens_reasoning":6403098585,"num_media_prompt":3625653,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":24703,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":40021384739,"total_tool_calls":1965956,"requests_with_tool_call_errors":51688},"krea/krea-2-medium-20260720":{"date":"2026-08-17 00:00:00","model_permaslug":"krea/krea-2-medium-20260720","variant":"standard","variant_permaslug":"krea/krea-2-medium-20260720","count":37400,"total_completion_tokens":156145000,"total_prompt_tokens":5514807,"total_native_tokens_reasoning":0,"num_media_prompt":8444,"num_media_completion":37400,"image_output_requests":37400,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-4o-mini":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-mini","variant":"standard","variant_permaslug":"openai/gpt-4o-mini","count":135897354,"total_completion_tokens":15325445332,"total_prompt_tokens":245011321743,"total_native_tokens_reasoning":0,"num_media_prompt":1936560,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":71930454144,"total_tool_calls":4926099,"requests_with_tool_call_errors":141657},"openai/gpt-oss-20b":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-oss-20b","variant":"standard","variant_permaslug":"openai/gpt-oss-20b","count":41270412,"total_completion_tokens":34043821665,"total_prompt_tokens":141346892958,"total_native_tokens_reasoning":27353891521,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":28646314270,"total_tool_calls":4927365,"requests_with_tool_call_errors":429672},"alibaba/happyhorse-1.0-20260624":{"date":"2026-08-17 00:00:00","model_permaslug":"alibaba/happyhorse-1.0-20260624","variant":"standard","variant_permaslug":"alibaba/happyhorse-1.0-20260624","count":342,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":352,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":2348,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-asr-0.6b-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-asr-0.6b-20260813","variant":"standard","variant_permaslug":"qwen/qwen3-asr-0.6b-20260813","count":8802,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":5926964,"num_audio_prompt":8802,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.6-sol-20260709:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-sol-20260709","variant":"batch","variant_permaslug":"openai/gpt-5.6-sol-20260709:batch","count":72204,"total_completion_tokens":51297099,"total_prompt_tokens":151509174,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":43596467,"total_tool_calls":2107,"requests_with_tool_call_errors":0},"perplexity/sonar-deep-research":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/sonar-deep-research","variant":"standard","variant_permaslug":"perplexity/sonar-deep-research","count":10020,"total_completion_tokens":119168780,"total_prompt_tokens":49783598,"total_native_tokens_reasoning":77633,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.6-luna-pro-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-luna-pro-20260709","variant":"standard","variant_permaslug":"openai/gpt-5.6-luna-pro-20260709","count":7882271,"total_completion_tokens":19345645423,"total_prompt_tokens":505238119499,"total_native_tokens_reasoning":11879226024,"num_media_prompt":855426,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":349802621156,"total_tool_calls":1819394,"requests_with_tool_call_errors":43828},"google/gemini-3.1-flash-tts-preview":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-tts-preview","variant":"standard","variant_permaslug":"google/gemini-3.1-flash-tts-preview","count":719358,"total_completion_tokens":215930376,"total_prompt_tokens":48320506,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"bytedance-seed/seedream-4.5-20251203":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seedream-4.5-20251203","variant":"standard","variant_permaslug":"bytedance-seed/seedream-4.5-20251203","count":142048,"total_completion_tokens":2848676014,"total_prompt_tokens":120208779,"total_native_tokens_reasoning":0,"num_media_prompt":99375,"num_media_completion":142040,"image_output_requests":142040,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"amazon/nova-2-lite-v1":{"date":"2026-08-17 00:00:00","model_permaslug":"amazon/nova-2-lite-v1","variant":"standard","variant_permaslug":"amazon/nova-2-lite-v1","count":303668,"total_completion_tokens":42634656,"total_prompt_tokens":624474336,"total_native_tokens_reasoning":8766,"num_media_prompt":96732,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":2753,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":46106,"requests_with_tool_call_errors":357},"inception/mercury-2-20260304":{"date":"2026-08-17 00:00:00","model_permaslug":"inception/mercury-2-20260304","variant":"standard","variant_permaslug":"inception/mercury-2-20260304","count":853127,"total_completion_tokens":487933908,"total_prompt_tokens":3017181978,"total_native_tokens_reasoning":323822653,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":590825410,"total_tool_calls":85415,"requests_with_tool_call_errors":4155},"anthropic/claude-4.7-opus-20260416":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.7-opus-20260416","variant":"standard","variant_permaslug":"anthropic/claude-4.7-opus-20260416","count":8979519,"total_completion_tokens":9369558021,"total_prompt_tokens":438184718741,"total_native_tokens_reasoning":176540398,"num_media_prompt":479478,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":388424779544,"total_tool_calls":790742,"requests_with_tool_call_errors":9323},"alibaba/happyhorse-1.1-20260624":{"date":"2026-08-17 00:00:00","model_permaslug":"alibaba/happyhorse-1.1-20260624","variant":"standard","variant_permaslug":"alibaba/happyhorse-1.1-20260624","count":3835,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":2989,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":33211,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.1-opus-20250805":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.1-opus-20250805","variant":"standard","variant_permaslug":"anthropic/claude-4.1-opus-20250805","count":56432,"total_completion_tokens":22168541,"total_prompt_tokens":638441173,"total_native_tokens_reasoning":1438265,"num_media_prompt":2059,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":226225276,"total_tool_calls":7462,"requests_with_tool_call_errors":1388},"tencent/hy-mt2-30b-a3b-20260521":{"date":"2026-08-20 00:00:00","model_permaslug":"tencent/hy-mt2-30b-a3b-20260521","variant":"standard","variant_permaslug":"tencent/hy-mt2-30b-a3b-20260521","count":45288,"total_completion_tokens":11317635,"total_prompt_tokens":32717934,"total_native_tokens_reasoning":414650,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"voyageai/voyage-multimodal-3.5-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/voyage-multimodal-3.5-20260727","variant":"standard","variant_permaslug":"voyageai/voyage-multimodal-3.5-20260727","count":99412,"total_completion_tokens":0,"total_prompt_tokens":52377521,"total_native_tokens_reasoning":0,"num_media_prompt":18817,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta/muse-spark-1.2-contributor-20260805":{"date":"2026-08-21 00:00:00","model_permaslug":"meta/muse-spark-1.2-contributor-20260805","variant":"standard","variant_permaslug":"meta/muse-spark-1.2-contributor-20260805","count":2283136,"total_completion_tokens":7591686628,"total_prompt_tokens":76444555843,"total_native_tokens_reasoning":5665135713,"num_media_prompt":777945,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":328,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":1129,"total_native_tokens_cached":58953247070,"total_tool_calls":538165,"requests_with_tool_call_errors":39284},"mistralai/mistral-large":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-large","variant":"standard","variant_permaslug":"mistralai/mistral-large","count":122687,"total_completion_tokens":40936372,"total_prompt_tokens":367083784,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":103492719,"total_tool_calls":5986,"requests_with_tool_call_errors":207},"thenlper/gte-large-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"thenlper/gte-large-20251117","variant":"standard","variant_permaslug":"thenlper/gte-large-20251117","count":4231,"total_completion_tokens":0,"total_prompt_tokens":1252727,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-5-turbo-20260315":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5-turbo-20260315","variant":"standard","variant_permaslug":"z-ai/glm-5-turbo-20260315","count":201033,"total_completion_tokens":177226851,"total_prompt_tokens":5552563271,"total_native_tokens_reasoning":147860308,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3490241311,"total_tool_calls":46590,"requests_with_tool_call_errors":98},"openai/gpt-4.1-2025-04-14:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"openai/gpt-4.1-2025-04-14","variant":"batch","variant_permaslug":"openai/gpt-4.1-2025-04-14:batch","count":2894,"total_completion_tokens":562191,"total_prompt_tokens":8240417,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3-pro-image-20260528":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3-pro-image-20260528","variant":"standard","variant_permaslug":"google/gemini-3-pro-image-20260528","count":420188,"total_completion_tokens":530178435,"total_prompt_tokens":595007432,"total_native_tokens_reasoning":113568934,"num_media_prompt":634462,"num_media_completion":620880,"image_output_requests":356626,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":110266409,"total_tool_calls":1699,"requests_with_tool_call_errors":271},"google/lyria-3-pro-preview-20260330":{"date":"2026-08-17 00:00:00","model_permaslug":"google/lyria-3-pro-preview-20260330","variant":"standard","variant_permaslug":"google/lyria-3-pro-preview-20260330","count":17716,"total_completion_tokens":3336550,"total_prompt_tokens":9646408,"total_native_tokens_reasoning":0,"num_media_prompt":955,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"dots-studio/dots-3-note-preview-20260813:free":{"date":"2026-08-17 00:00:00","model_permaslug":"dots-studio/dots-3-note-preview-20260813","variant":"free","variant_permaslug":"dots-studio/dots-3-note-preview-20260813:free","count":3413332,"total_completion_tokens":3892938685,"total_prompt_tokens":118450795783,"total_native_tokens_reasoning":3069665028,"num_media_prompt":588351,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":88672952320,"total_tool_calls":1206813,"requests_with_tool_call_errors":43270},"nvidia/nemotron-3-super-120b-a12b-20230311":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","variant":"standard","variant_permaslug":"nvidia/nemotron-3-super-120b-a12b-20230311","count":1080499,"total_completion_tokens":666332620,"total_prompt_tokens":12813753672,"total_native_tokens_reasoning":406561246,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3356765888,"total_tool_calls":246865,"requests_with_tool_call_errors":13437},"venice/uncensored":{"date":"2026-08-17 00:00:00","model_permaslug":"venice/uncensored","variant":"standard","variant_permaslug":"venice/uncensored","count":319309,"total_completion_tokens":74390022,"total_prompt_tokens":1000539220,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":513938000,"total_tool_calls":0,"requests_with_tool_call_errors":0},"tencent/hy-mt2-1.8b-20260521":{"date":"2026-08-20 00:00:00","model_permaslug":"tencent/hy-mt2-1.8b-20260521","variant":"standard","variant_permaslug":"tencent/hy-mt2-1.8b-20260521","count":56065,"total_completion_tokens":6162316,"total_prompt_tokens":24942896,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.6-terra-20260709:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-terra-20260709","variant":"batch","variant_permaslug":"openai/gpt-5.6-terra-20260709:batch","count":73018,"total_completion_tokens":17004079,"total_prompt_tokens":67008160,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":11113593,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-4.6-20251208":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.6-20251208","variant":"standard","variant_permaslug":"z-ai/glm-4.6-20251208","count":621635,"total_completion_tokens":187047222,"total_prompt_tokens":1842648270,"total_native_tokens_reasoning":137270784,"num_media_prompt":1461799,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":4350,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":337994564,"total_tool_calls":9064,"requests_with_tool_call_errors":1351},"openai/gpt-5.6-terra-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-terra-20260709","variant":"standard","variant_permaslug":"openai/gpt-5.6-terra-20260709","count":23445128,"total_completion_tokens":9890261037,"total_prompt_tokens":796997993716,"total_native_tokens_reasoning":3074219832,"num_media_prompt":23388393,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":682890586796,"total_tool_calls":9143353,"requests_with_tool_call_errors":298919},"sakana/namazu-20260811":{"date":"2026-08-17 00:00:00","model_permaslug":"sakana/namazu-20260811","variant":"standard","variant_permaslug":"sakana/namazu-20260811","count":6984,"total_completion_tokens":8600741,"total_prompt_tokens":35167138,"total_native_tokens_reasoning":6237268,"num_media_prompt":1203,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":8956160,"total_tool_calls":1900,"requests_with_tool_call_errors":254},"google/gemini-3.5-flash-lite-20260721":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.5-flash-lite-20260721","variant":"standard","variant_permaslug":"google/gemini-3.5-flash-lite-20260721","count":42713490,"total_completion_tokens":6215723579,"total_prompt_tokens":157234208239,"total_native_tokens_reasoning":1084354376,"num_media_prompt":8260276,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":260842,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":132816,"total_native_tokens_cached":41331145740,"total_tool_calls":3747852,"requests_with_tool_call_errors":131480},"perplexity/sonar":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/sonar","variant":"standard","variant_permaslug":"perplexity/sonar","count":2297405,"total_completion_tokens":812230294,"total_prompt_tokens":1613038943,"total_native_tokens_reasoning":0,"num_media_prompt":7371,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o4-mini-2025-04-16":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o4-mini-2025-04-16","variant":"standard","variant_permaslug":"openai/o4-mini-2025-04-16","count":287283,"total_completion_tokens":277834181,"total_prompt_tokens":1743721351,"total_native_tokens_reasoning":229466342,"num_media_prompt":28509,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1069335808,"total_tool_calls":35966,"requests_with_tool_call_errors":24},"nvidia/nemotron-3-embed-1b-20260716:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-embed-1b-20260716","variant":"free","variant_permaslug":"nvidia/nemotron-3-embed-1b-20260716:free","count":3403637,"total_completion_tokens":0,"total_prompt_tokens":6370166889,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemma-3n-e4b-it":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-3n-e4b-it","variant":"standard","variant_permaslug":"google/gemma-3n-e4b-it","count":4980006,"total_completion_tokens":291760796,"total_prompt_tokens":2257100162,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"bytedance/seedance-2.0-fast-20260414":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance/seedance-2.0-fast-20260414","variant":"standard","variant_permaslug":"bytedance/seedance-2.0-fast-20260414","count":18774,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":24508,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":498,"video_output_seconds":130625,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":312,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.5-haiku-20251001":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.5-haiku-20251001","variant":"standard","variant_permaslug":"anthropic/claude-4.5-haiku-20251001","count":35876175,"total_completion_tokens":10121003265,"total_prompt_tokens":252734317321,"total_native_tokens_reasoning":610769954,"num_media_prompt":1816422,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":110959678925,"total_tool_calls":6484800,"requests_with_tool_call_errors":111904},"thedrummer/unslopnemo-12b":{"date":"2026-08-17 00:00:00","model_permaslug":"thedrummer/unslopnemo-12b","variant":"standard","variant_permaslug":"thedrummer/unslopnemo-12b","count":132771,"total_completion_tokens":26259342,"total_prompt_tokens":578881094,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":99404704,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-5v-turbo-20260401":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5v-turbo-20260401","variant":"standard","variant_permaslug":"z-ai/glm-5v-turbo-20260401","count":831964,"total_completion_tokens":490986349,"total_prompt_tokens":32079689112,"total_native_tokens_reasoning":178889512,"num_media_prompt":1239670,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":2303,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":27461083752,"total_tool_calls":525763,"requests_with_tool_call_errors":74039},"openai/gpt-5.6-luna-pro-20260709:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-luna-pro-20260709","variant":"batch","variant_permaslug":"openai/gpt-5.6-luna-pro-20260709:batch","count":65325,"total_completion_tokens":154288972,"total_prompt_tokens":1271292180,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":699090597,"total_tool_calls":43,"requests_with_tool_call_errors":0},"bytedance-seed/seed-1.6-20250625":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seed-1.6-20250625","variant":"standard","variant_permaslug":"bytedance-seed/seed-1.6-20250625","count":19638,"total_completion_tokens":19650417,"total_prompt_tokens":77137442,"total_native_tokens_reasoning":12085983,"num_media_prompt":1597,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":20,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1713,"requests_with_tool_call_errors":241},"anthropic/claude-4.6-opus-20260205":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.6-opus-20260205","variant":"standard","variant_permaslug":"anthropic/claude-4.6-opus-20260205","count":5535746,"total_completion_tokens":3561754378,"total_prompt_tokens":188522847765,"total_native_tokens_reasoning":443396183,"num_media_prompt":1655281,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":123682907087,"total_tool_calls":1592772,"requests_with_tool_call_errors":32415},"aion-labs/aion-rp-llama-3.1-8b":{"date":"2026-08-17 00:00:00","model_permaslug":"aion-labs/aion-rp-llama-3.1-8b","variant":"standard","variant_permaslug":"aion-labs/aion-rp-llama-3.1-8b","count":13169,"total_completion_tokens":1823000,"total_prompt_tokens":10260336,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta/muse-spark-1.1-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"meta/muse-spark-1.1-20260709","variant":"standard","variant_permaslug":"meta/muse-spark-1.1-20260709","count":695561,"total_completion_tokens":823674812,"total_prompt_tokens":42836314152,"total_native_tokens_reasoning":600657887,"num_media_prompt":781888,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":889,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":11292,"total_native_tokens_cached":38834723678,"total_tool_calls":429389,"requests_with_tool_call_errors":1249},"qwen/qwen3-235b-a22b-04-28":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-235b-a22b-04-28","variant":"standard","variant_permaslug":"qwen/qwen3-235b-a22b-04-28","count":444205,"total_completion_tokens":387070597,"total_prompt_tokens":2024581794,"total_native_tokens_reasoning":234482519,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":15483,"requests_with_tool_call_errors":628},"gryphe/mythomax-l2-13b":{"date":"2026-08-17 00:00:00","model_permaslug":"gryphe/mythomax-l2-13b","variant":"standard","variant_permaslug":"gryphe/mythomax-l2-13b","count":584490,"total_completion_tokens":94355936,"total_prompt_tokens":653556577,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":38748688,"total_tool_calls":0,"requests_with_tool_call_errors":0},"perplexity/pplx-embed-v1-0.6B":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/pplx-embed-v1-0.6B","variant":"standard","variant_permaslug":"perplexity/pplx-embed-v1-0.6B","count":7369123,"total_completion_tokens":0,"total_prompt_tokens":51769953115,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5-mini-2025-08-07:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-mini-2025-08-07","variant":"batch","variant_permaslug":"openai/gpt-5-mini-2025-08-07:batch","count":640902,"total_completion_tokens":270858460,"total_prompt_tokens":1457858856,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":548814720,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.1-20251113":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.1-20251113","variant":"standard","variant_permaslug":"openai/gpt-5.1-20251113","count":3415593,"total_completion_tokens":1025228748,"total_prompt_tokens":21927070134,"total_native_tokens_reasoning":270606812,"num_media_prompt":236972,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":13763324544,"total_tool_calls":391388,"requests_with_tool_call_errors":5809},"qwen/qwen3.5-9b-20260310":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-9b-20260310","variant":"standard","variant_permaslug":"qwen/qwen3.5-9b-20260310","count":9597975,"total_completion_tokens":6351652617,"total_prompt_tokens":30141827735,"total_native_tokens_reasoning":3890001747,"num_media_prompt":7678922,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":9137,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1179083664,"total_tool_calls":471016,"requests_with_tool_call_errors":16612},"qwen/qwen-2.5-coder-32b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-2.5-coder-32b-instruct","variant":"standard","variant_permaslug":"qwen/qwen-2.5-coder-32b-instruct","count":87201,"total_completion_tokens":4090378,"total_prompt_tokens":52091377,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-4o-2024-08-06":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-2024-08-06","variant":"standard","variant_permaslug":"openai/gpt-4o-2024-08-06","count":875018,"total_completion_tokens":39030590,"total_prompt_tokens":1696202527,"total_native_tokens_reasoning":0,"num_media_prompt":490849,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":452376704,"total_tool_calls":67737,"requests_with_tool_call_errors":66},"openai/gpt-5.4-image-2-20260421":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-image-2-20260421","variant":"standard","variant_permaslug":"openai/gpt-5.4-image-2-20260421","count":294606,"total_completion_tokens":925620810,"total_prompt_tokens":864071327,"total_native_tokens_reasoning":807350,"num_media_prompt":259921,"num_media_completion":222873,"image_output_requests":219689,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":105226368,"total_tool_calls":0,"requests_with_tool_call_errors":0},"intfloat/multilingual-e5-large-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"intfloat/multilingual-e5-large-20251117","variant":"standard","variant_permaslug":"intfloat/multilingual-e5-large-20251117","count":1062333,"total_completion_tokens":0,"total_prompt_tokens":1663153699,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"fish-audio/s2.1-pro-20260729":{"date":"2026-08-17 00:00:00","model_permaslug":"fish-audio/s2.1-pro-20260729","variant":"standard","variant_permaslug":"fish-audio/s2.1-pro-20260729","count":79198,"total_completion_tokens":0,"total_prompt_tokens":2025927,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":41009,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"alibaba/wan-2.7-20260414":{"date":"2026-08-17 00:00:00","model_permaslug":"alibaba/wan-2.7-20260414","variant":"standard","variant_permaslug":"alibaba/wan-2.7-20260414","count":2985,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":3177,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":20835,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-image-1":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-image-1","variant":"standard","variant_permaslug":"openai/gpt-image-1","count":9007,"total_completion_tokens":30778572,"total_prompt_tokens":4456699,"total_native_tokens_reasoning":0,"num_media_prompt":4428,"num_media_completion":9044,"image_output_requests":8998,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"amazon/nova-micro-v1":{"date":"2026-08-17 00:00:00","model_permaslug":"amazon/nova-micro-v1","variant":"standard","variant_permaslug":"amazon/nova-micro-v1","count":24596815,"total_completion_tokens":3621126669,"total_prompt_tokens":67718287542,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":19704,"requests_with_tool_call_errors":846},"cohere/command-r-plus-08-2024":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/command-r-plus-08-2024","variant":"standard","variant_permaslug":"cohere/command-r-plus-08-2024","count":54937,"total_completion_tokens":3106072,"total_prompt_tokens":49288707,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":4492,"requests_with_tool_call_errors":9},"qwen/qwen-plus-2025-01-25":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-plus-2025-01-25","variant":"standard","variant_permaslug":"qwen/qwen-plus-2025-01-25","count":192751,"total_completion_tokens":67083550,"total_prompt_tokens":772060082,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":376992108,"total_tool_calls":6954,"requests_with_tool_call_errors":1096},"bytedance/ui-tars-1.5-7b":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance/ui-tars-1.5-7b","variant":"standard","variant_permaslug":"bytedance/ui-tars-1.5-7b","count":163023,"total_completion_tokens":8415701,"total_prompt_tokens":695811385,"total_native_tokens_reasoning":0,"num_media_prompt":222120,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":74628448,"total_tool_calls":0,"requests_with_tool_call_errors":0},"fish-audio/s2-pro-20260729":{"date":"2026-08-17 00:00:00","model_permaslug":"fish-audio/s2-pro-20260729","variant":"standard","variant_permaslug":"fish-audio/s2-pro-20260729","count":904,"total_completion_tokens":0,"total_prompt_tokens":49181,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3-flash-preview-20251217:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3-flash-preview-20251217","variant":"batch","variant_permaslug":"google/gemini-3-flash-preview-20251217:batch","count":12432,"total_completion_tokens":1521052,"total_prompt_tokens":56305956,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4239415,"total_tool_calls":0,"requests_with_tool_call_errors":0},"microsoft/wizardlm-2-8x22b":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/wizardlm-2-8x22b","variant":"standard","variant_permaslug":"microsoft/wizardlm-2-8x22b","count":145462,"total_completion_tokens":24875951,"total_prompt_tokens":839212677,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":335618914,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-voice-tts-1.0":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-voice-tts-1.0","variant":"standard","variant_permaslug":"x-ai/grok-voice-tts-1.0","count":229271,"total_completion_tokens":0,"total_prompt_tokens":9333877,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-3-ultra-550b-a55b-20260604":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","variant":"standard","variant_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","count":2685137,"total_completion_tokens":3398024461,"total_prompt_tokens":39012627975,"total_native_tokens_reasoning":2399944593,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":23897109920,"total_tool_calls":547448,"requests_with_tool_call_errors":10571},"voyageai/voyage-4-lite-20260727":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/voyage-4-lite-20260727","variant":"standard","variant_permaslug":"voyageai/voyage-4-lite-20260727","count":157936,"total_completion_tokens":0,"total_prompt_tokens":348518727,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-audio-mini":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-audio-mini","variant":"standard","variant_permaslug":"openai/gpt-audio-mini","count":3447648,"total_completion_tokens":574547529,"total_prompt_tokens":554867668,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":171133,"total_native_tokens_cached":0,"total_tool_calls":6682,"requests_with_tool_call_errors":88},"nvidia/nemotron-3-ultra-550b-a55b-20260604:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","variant":"batch","variant_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604:batch","count":7794,"total_completion_tokens":12878807,"total_prompt_tokens":6755515,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"recraft/recraft-v4-pro-20260413":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4-pro-20260413","variant":"standard","variant_permaslug":"recraft/recraft-v4-pro-20260413","count":944,"total_completion_tokens":3941200,"total_prompt_tokens":352250,"total_native_tokens_reasoning":0,"num_media_prompt":151,"num_media_completion":944,"image_output_requests":944,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/minimax-m3-20260531":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m3-20260531","variant":"standard","variant_permaslug":"minimax/minimax-m3-20260531","count":31347562,"total_completion_tokens":29093548325,"total_prompt_tokens":1849488679640,"total_native_tokens_reasoning":17762189568,"num_media_prompt":6966884,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":88726,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1634011896826,"total_tool_calls":14651251,"requests_with_tool_call_errors":528765},"google/gemini-3.1-flash-lite-20260507":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-lite-20260507","variant":"standard","variant_permaslug":"google/gemini-3.1-flash-lite-20260507","count":102971195,"total_completion_tokens":24512689823,"total_prompt_tokens":473573811721,"total_native_tokens_reasoning":4991775070,"num_media_prompt":26730579,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":548367,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":876497,"total_native_tokens_cached":151015661355,"total_tool_calls":6263981,"requests_with_tool_call_errors":450779},"deepseek/deepseek-v4-flash-20260423":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v4-flash-20260423","variant":"standard","variant_permaslug":"deepseek/deepseek-v4-flash-20260423","count":582894411,"total_completion_tokens":322237227195,"total_prompt_tokens":5777772996201,"total_native_tokens_reasoning":146545721485,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3933947749061,"total_tool_calls":54009312,"requests_with_tool_call_errors":2040234},"openai/gpt-5.5-20260423:batch":{"date":"2026-08-19 00:00:00","model_permaslug":"openai/gpt-5.5-20260423","variant":"batch","variant_permaslug":"openai/gpt-5.5-20260423:batch","count":30856,"total_completion_tokens":33811638,"total_prompt_tokens":223474388,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":48566784,"total_tool_calls":1482,"requests_with_tool_call_errors":0},"text-embedding-3-large":{"date":"2026-08-17 00:00:00","model_permaslug":"text-embedding-3-large","variant":"standard","variant_permaslug":"text-embedding-3-large","count":10,"total_completion_tokens":0,"total_prompt_tokens":301,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-3.5-turbo-0613":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-3.5-turbo-0613","variant":"standard","variant_permaslug":"openai/gpt-3.5-turbo-0613","count":21294,"total_completion_tokens":8650123,"total_prompt_tokens":9655057,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2302592,"total_tool_calls":169,"requests_with_tool_call_errors":1},"recraft/recraft-v4-pro-vector-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4-pro-vector-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4-pro-vector-20260514","count":273,"total_completion_tokens":1139775,"total_prompt_tokens":164655,"total_native_tokens_reasoning":0,"num_media_prompt":96,"num_media_completion":273,"image_output_requests":273,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/lyria-3-clip-preview-20260330":{"date":"2026-08-17 00:00:00","model_permaslug":"google/lyria-3-clip-preview-20260330","variant":"standard","variant_permaslug":"google/lyria-3-clip-preview-20260330","count":9959,"total_completion_tokens":466914,"total_prompt_tokens":11224759,"total_native_tokens_reasoning":0,"num_media_prompt":237,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"cohere/command-a-03-2025":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/command-a-03-2025","variant":"standard","variant_permaslug":"cohere/command-a-03-2025","count":57553,"total_completion_tokens":20661104,"total_prompt_tokens":63780661,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3.1-pro-preview-20260219":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-pro-preview-20260219","variant":"standard","variant_permaslug":"google/gemini-3.1-pro-preview-20260219","count":13725547,"total_completion_tokens":24537399284,"total_prompt_tokens":265319181407,"total_native_tokens_reasoning":17304507967,"num_media_prompt":11223835,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":704645,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":518564,"total_native_tokens_cached":125835233132,"total_tool_calls":2140361,"requests_with_tool_call_errors":60057},"stepfun/step-3.7-flash-20260528":{"date":"2026-08-17 00:00:00","model_permaslug":"stepfun/step-3.7-flash-20260528","variant":"standard","variant_permaslug":"stepfun/step-3.7-flash-20260528","count":10852261,"total_completion_tokens":12925036772,"total_prompt_tokens":597516039063,"total_native_tokens_reasoning":167420846,"num_media_prompt":1247914,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":4315,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":539040888030,"total_tool_calls":5706379,"requests_with_tool_call_errors":45440},"stealth/ox-alpha":{"date":"2026-08-20 00:00:00","model_permaslug":"stealth/ox-alpha","variant":"standard","variant_permaslug":"stealth/ox-alpha","count":202024734,"total_completion_tokens":241866339714,"total_prompt_tokens":16132295430032,"total_native_tokens_reasoning":15352965163,"num_media_prompt":57778265,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":33852,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":14269178766208,"total_tool_calls":122575629,"requests_with_tool_call_errors":2701616},"openai/gpt-5.1-codex-mini-20251113":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.1-codex-mini-20251113","variant":"standard","variant_permaslug":"openai/gpt-5.1-codex-mini-20251113","count":96887,"total_completion_tokens":136446037,"total_prompt_tokens":2132241244,"total_native_tokens_reasoning":107312074,"num_media_prompt":13220,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1789629568,"total_tool_calls":34411,"requests_with_tool_call_errors":369},"openai/o3-mini-2025-01-31":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o3-mini-2025-01-31","variant":"standard","variant_permaslug":"openai/o3-mini-2025-01-31","count":72060,"total_completion_tokens":43024015,"total_prompt_tokens":158500273,"total_native_tokens_reasoning":30961620,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":40251904,"total_tool_calls":3626,"requests_with_tool_call_errors":18},"cohere/command-r7b-12-2024":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/command-r7b-12-2024","variant":"standard","variant_permaslug":"cohere/command-r7b-12-2024","count":78878,"total_completion_tokens":8025934,"total_prompt_tokens":138687952,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mistral-saba-2502":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-saba-2502","variant":"standard","variant_permaslug":"mistralai/mistral-saba-2502","count":31564,"total_completion_tokens":14067297,"total_prompt_tokens":65411773,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":31268978,"total_tool_calls":1233,"requests_with_tool_call_errors":72},"mistralai/voxtral-mini-3b-2507-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/voxtral-mini-3b-2507-20260813","variant":"standard","variant_permaslug":"mistralai/voxtral-mini-3b-2507-20260813","count":12837,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":3534238,"num_audio_prompt":12837,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-3.5-lightning-20260807":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3.5-lightning-20260807","variant":"standard","variant_permaslug":"nvidia/nemotron-3.5-lightning-20260807","count":1638457,"total_completion_tokens":2065822345,"total_prompt_tokens":36689094175,"total_native_tokens_reasoning":953264887,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":31151357184,"total_tool_calls":233880,"requests_with_tool_call_errors":8652},"qwen/qwen3.5-397b-a17b-20260216":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-397b-a17b-20260216","variant":"standard","variant_permaslug":"qwen/qwen3.5-397b-a17b-20260216","count":4475848,"total_completion_tokens":3972541503,"total_prompt_tokens":36461801681,"total_native_tokens_reasoning":2080221819,"num_media_prompt":2175751,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":4529,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":7916393950,"total_tool_calls":662760,"requests_with_tool_call_errors":65705},"deepseek/deepseek-v3.2-20251201":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v3.2-20251201","variant":"standard","variant_permaslug":"deepseek/deepseek-v3.2-20251201","count":69066720,"total_completion_tokens":21302809077,"total_prompt_tokens":455264421356,"total_native_tokens_reasoning":1477384012,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":235435395723,"total_tool_calls":1270569,"requests_with_tool_call_errors":17636},"baai/bge-base-en-v1.5-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"baai/bge-base-en-v1.5-20251117","variant":"standard","variant_permaslug":"baai/bge-base-en-v1.5-20251117","count":680604,"total_completion_tokens":0,"total_prompt_tokens":711206143,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3-pro-image-preview-20251120":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3-pro-image-preview-20251120","variant":"standard","variant_permaslug":"google/gemini-3-pro-image-preview-20251120","count":507586,"total_completion_tokens":781615552,"total_prompt_tokens":487132131,"total_native_tokens_reasoning":126908100,"num_media_prompt":741572,"num_media_completion":859781,"image_output_requests":436749,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":26031678,"total_tool_calls":429,"requests_with_tool_call_errors":429},"baai/bge-m3-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"baai/bge-m3-20251117","variant":"standard","variant_permaslug":"baai/bge-m3-20251117","count":19289919,"total_completion_tokens":0,"total_prompt_tokens":26690911676,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-4.5-air":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.5-air","variant":"standard","variant_permaslug":"z-ai/glm-4.5-air","count":623387,"total_completion_tokens":183178192,"total_prompt_tokens":3432060047,"total_native_tokens_reasoning":95723510,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2283747964,"total_tool_calls":83071,"requests_with_tool_call_errors":7638},"z-ai/glm-5.2-20260616":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5.2-20260616","variant":"standard","variant_permaslug":"z-ai/glm-5.2-20260616","count":77936005,"total_completion_tokens":77272959375,"total_prompt_tokens":3694517512411,"total_native_tokens_reasoning":47868942572,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3165112603118,"total_tool_calls":40858895,"requests_with_tool_call_errors":396190},"anthropic/claude-5-fable-20260609":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-5-fable-20260609","variant":"standard","variant_permaslug":"anthropic/claude-5-fable-20260609","count":4210391,"total_completion_tokens":11339114226,"total_prompt_tokens":285938065877,"total_native_tokens_reasoning":6866277774,"num_media_prompt":2986839,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":226039725684,"total_tool_calls":1566668,"requests_with_tool_call_errors":19420},"openai/gpt-4.1-mini-2025-04-14:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4.1-mini-2025-04-14","variant":"batch","variant_permaslug":"openai/gpt-4.1-mini-2025-04-14:batch","count":16513,"total_completion_tokens":1230079,"total_prompt_tokens":19470093,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"recraft/recraft-v4.1-pro-vector-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4.1-pro-vector-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4.1-pro-vector-20260514","count":736,"total_completion_tokens":3231450,"total_prompt_tokens":305869,"total_native_tokens_reasoning":0,"num_media_prompt":225,"num_media_completion":774,"image_output_requests":736,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5-2025-08-07":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-2025-08-07","variant":"standard","variant_permaslug":"openai/gpt-5-2025-08-07","count":2259398,"total_completion_tokens":2096527690,"total_prompt_tokens":10306631528,"total_native_tokens_reasoning":1522541403,"num_media_prompt":602723,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":5150022272,"total_tool_calls":199949,"requests_with_tool_call_errors":1948},"qwen/qwen-2.5-7b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-2.5-7b-instruct","variant":"standard","variant_permaslug":"qwen/qwen-2.5-7b-instruct","count":5870713,"total_completion_tokens":514440595,"total_prompt_tokens":4712614535,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":22271,"requests_with_tool_call_errors":4609},"openai/gpt-5.4-pro-20260305":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-pro-20260305","variant":"standard","variant_permaslug":"openai/gpt-5.4-pro-20260305","count":19567,"total_completion_tokens":6882666,"total_prompt_tokens":51302335,"total_native_tokens_reasoning":4635606,"num_media_prompt":558,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":754,"requests_with_tool_call_errors":1},"z-ai/glm-4.7-flash-20260119":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.7-flash-20260119","variant":"standard","variant_permaslug":"z-ai/glm-4.7-flash-20260119","count":7511255,"total_completion_tokens":1612623485,"total_prompt_tokens":19563395736,"total_native_tokens_reasoning":1016174432,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9847661499,"total_tool_calls":429931,"requests_with_tool_call_errors":20962},"qwen/qwen3.5-flash-20260224":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-flash-20260224","variant":"standard","variant_permaslug":"qwen/qwen3.5-flash-20260224","count":25940017,"total_completion_tokens":5198189720,"total_prompt_tokens":53708347359,"total_native_tokens_reasoning":1678220361,"num_media_prompt":3432871,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":41031,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":269618,"requests_with_tool_call_errors":16974},"google/gemma-3-12b-it":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-3-12b-it","variant":"standard","variant_permaslug":"google/gemma-3-12b-it","count":12657975,"total_completion_tokens":4157078673,"total_prompt_tokens":29522697739,"total_native_tokens_reasoning":0,"num_media_prompt":5612824,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":5259,"requests_with_tool_call_errors":511},"openai/gpt-5.6-sol-pro-20260709:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-sol-pro-20260709","variant":"batch","variant_permaslug":"openai/gpt-5.6-sol-pro-20260709:batch","count":35147,"total_completion_tokens":105868336,"total_prompt_tokens":327595463,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":94872092,"total_tool_calls":177,"requests_with_tool_call_errors":0},"openai/gpt-5-image":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-image","variant":"standard","variant_permaslug":"openai/gpt-5-image","count":13326,"total_completion_tokens":53167040,"total_prompt_tokens":22598882,"total_native_tokens_reasoning":10129299,"num_media_prompt":5467,"num_media_completion":10230,"image_output_requests":10012,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2020906,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-5.1-20260406":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5.1-20260406","variant":"standard","variant_permaslug":"z-ai/glm-5.1-20260406","count":4008892,"total_completion_tokens":3815778373,"total_prompt_tokens":65639237639,"total_native_tokens_reasoning":2307001332,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":42719851986,"total_tool_calls":930517,"requests_with_tool_call_errors":18704},"sentence-transformers/paraphrase-minilm-l6-v2-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"sentence-transformers/paraphrase-minilm-l6-v2-20251117","variant":"standard","variant_permaslug":"sentence-transformers/paraphrase-minilm-l6-v2-20251117","count":4690,"total_completion_tokens":0,"total_prompt_tokens":1637221,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"":{"date":"2026-08-17 00:00:00","model_permaslug":"","variant":"standard","variant_permaslug":"","count":0,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-nano-9b-v2:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-nano-9b-v2","variant":"free","variant_permaslug":"nvidia/nemotron-nano-9b-v2:free","count":1110374,"total_completion_tokens":1047951229,"total_prompt_tokens":13992740118,"total_native_tokens_reasoning":734930537,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":165446,"requests_with_tool_call_errors":14271},"sourceful/riverflow-v2.5-pro-20260605":{"date":"2026-08-17 00:00:00","model_permaslug":"sourceful/riverflow-v2.5-pro-20260605","variant":"standard","variant_permaslug":"sourceful/riverflow-v2.5-pro-20260605","count":3304,"total_completion_tokens":13794200,"total_prompt_tokens":2813739,"total_native_tokens_reasoning":0,"num_media_prompt":3825,"num_media_completion":3304,"image_output_requests":3304,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"inclusionai/ring-2.6-1t-20260508":{"date":"2026-08-17 00:00:00","model_permaslug":"inclusionai/ring-2.6-1t-20260508","variant":"standard","variant_permaslug":"inclusionai/ring-2.6-1t-20260508","count":115513,"total_completion_tokens":191124345,"total_prompt_tokens":3548319761,"total_native_tokens_reasoning":69825126,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2350727541,"total_tool_calls":38734,"requests_with_tool_call_errors":8428},"openai/gpt-audio":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-audio","variant":"standard","variant_permaslug":"openai/gpt-audio","count":43744,"total_completion_tokens":11573968,"total_prompt_tokens":17191731,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":14702,"total_native_tokens_cached":0,"total_tool_calls":120,"requests_with_tool_call_errors":1},"bytedance-seed/seed-2.0-mini-20260224":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance-seed/seed-2.0-mini-20260224","variant":"standard","variant_permaslug":"bytedance-seed/seed-2.0-mini-20260224","count":2596999,"total_completion_tokens":1355390183,"total_prompt_tokens":9948446635,"total_native_tokens_reasoning":953557897,"num_media_prompt":4298147,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":5278,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2617416392,"total_tool_calls":13116,"requests_with_tool_call_errors":281},"google/gemini-2.5-flash":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-flash","variant":"standard","variant_permaslug":"google/gemini-2.5-flash","count":127085167,"total_completion_tokens":32668854432,"total_prompt_tokens":464795044273,"total_native_tokens_reasoning":3270382506,"num_media_prompt":33873066,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":502329,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":1090877,"total_native_tokens_cached":138430445496,"total_tool_calls":10613562,"requests_with_tool_call_errors":1730123},"tencent/hy-mt2-7b-20260521":{"date":"2026-08-22 00:00:00","model_permaslug":"tencent/hy-mt2-7b-20260521","variant":"standard","variant_permaslug":"tencent/hy-mt2-7b-20260521","count":20036,"total_completion_tokens":2119055,"total_prompt_tokens":2448976,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"black-forest-labs/flux.2-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"black-forest-labs/flux.2-pro","variant":"standard","variant_permaslug":"black-forest-labs/flux.2-pro","count":136027,"total_completion_tokens":566265314,"total_prompt_tokens":407000203,"total_native_tokens_reasoning":0,"num_media_prompt":103218,"num_media_completion":136027,"image_output_requests":136027,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/minimax-m3-20260531:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m3-20260531","variant":"batch","variant_permaslug":"minimax/minimax-m3-20260531:batch","count":580842,"total_completion_tokens":141709579,"total_prompt_tokens":393039878,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":78707584,"total_tool_calls":2,"requests_with_tool_call_errors":0},"openai/gpt-4o-2024-11-20":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-2024-11-20","variant":"standard","variant_permaslug":"openai/gpt-4o-2024-11-20","count":456491,"total_completion_tokens":52938089,"total_prompt_tokens":2864786003,"total_native_tokens_reasoning":0,"num_media_prompt":63757,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1935764608,"total_tool_calls":24210,"requests_with_tool_call_errors":225},"mistralai/voxtral-mini-tts-2603":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/voxtral-mini-tts-2603","variant":"standard","variant_permaslug":"mistralai/voxtral-mini-tts-2603","count":5935,"total_completion_tokens":0,"total_prompt_tokens":1119246,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-30b-a3b-thinking-2507":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-30b-a3b-thinking-2507","variant":"standard","variant_permaslug":"qwen/qwen3-30b-a3b-thinking-2507","count":78613,"total_completion_tokens":150903120,"total_prompt_tokens":353360152,"total_native_tokens_reasoning":136284791,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":19712,"requests_with_tool_call_errors":70},"krea/krea-2-medium-turbo-20260720":{"date":"2026-08-17 00:00:00","model_permaslug":"krea/krea-2-medium-turbo-20260720","variant":"standard","variant_permaslug":"krea/krea-2-medium-turbo-20260720","count":21298,"total_completion_tokens":88919150,"total_prompt_tokens":6621828,"total_native_tokens_reasoning":0,"num_media_prompt":1630,"num_media_completion":21298,"image_output_requests":21298,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mistral-medium-3.5-20260430":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-medium-3.5-20260430","variant":"standard","variant_permaslug":"mistralai/mistral-medium-3.5-20260430","count":660403,"total_completion_tokens":239547837,"total_prompt_tokens":4840867392,"total_native_tokens_reasoning":76829009,"num_media_prompt":32401,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2514356994,"total_tool_calls":220739,"requests_with_tool_call_errors":6186},"microsoft/mai-image-2.5":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/mai-image-2.5","variant":"standard","variant_permaslug":"microsoft/mai-image-2.5","count":96592,"total_completion_tokens":98121622,"total_prompt_tokens":185344107,"total_native_tokens_reasoning":0,"num_media_prompt":63529,"num_media_completion":96592,"image_output_requests":96592,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.1-20251113:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.1-20251113","variant":"batch","variant_permaslug":"openai/gpt-5.1-20251113:batch","count":541,"total_completion_tokens":144396,"total_prompt_tokens":1014766,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":108288,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-3-embed-1b:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-embed-1b","variant":"free","variant_permaslug":"nvidia/nemotron-3-embed-1b:free","count":24,"total_completion_tokens":0,"total_prompt_tokens":18060,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-4.5v":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-4.5v","variant":"standard","variant_permaslug":"z-ai/glm-4.5v","count":112172,"total_completion_tokens":42137240,"total_prompt_tokens":142030279,"total_native_tokens_reasoning":27362024,"num_media_prompt":93228,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":36909885,"total_tool_calls":1862,"requests_with_tool_call_errors":16},"openai/sora-2-pro-20260320":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/sora-2-pro-20260320","variant":"standard","variant_permaslug":"openai/sora-2-pro-20260320","count":176,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":35,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":1496,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"poolside/laguna-xs-2.1-20260625":{"date":"2026-08-17 00:00:00","model_permaslug":"poolside/laguna-xs-2.1-20260625","variant":"standard","variant_permaslug":"poolside/laguna-xs-2.1-20260625","count":276413,"total_completion_tokens":124135472,"total_prompt_tokens":4821643436,"total_native_tokens_reasoning":69384219,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3867345504,"total_tool_calls":70953,"requests_with_tool_call_errors":11753},"openai/gpt-5.4-20260305":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-20260305","variant":"standard","variant_permaslug":"openai/gpt-5.4-20260305","count":9173927,"total_completion_tokens":3870637013,"total_prompt_tokens":179877591479,"total_native_tokens_reasoning":1104671308,"num_media_prompt":5458195,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":139068690458,"total_tool_calls":3140244,"requests_with_tool_call_errors":20239},"deepseek/deepseek-r1-0528":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-r1-0528","variant":"standard","variant_permaslug":"deepseek/deepseek-r1-0528","count":1116607,"total_completion_tokens":1405652587,"total_prompt_tokens":9931623811,"total_native_tokens_reasoning":892278145,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4959077961,"total_tool_calls":19986,"requests_with_tool_call_errors":286},"sesame/csm-1b":{"date":"2026-08-17 00:00:00","model_permaslug":"sesame/csm-1b","variant":"standard","variant_permaslug":"sesame/csm-1b","count":579,"total_completion_tokens":0,"total_prompt_tokens":12750,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"stepfun/step-3.5-flash":{"date":"2026-08-17 00:00:00","model_permaslug":"stepfun/step-3.5-flash","variant":"standard","variant_permaslug":"stepfun/step-3.5-flash","count":170593,"total_completion_tokens":182849821,"total_prompt_tokens":2273630620,"total_native_tokens_reasoning":143390620,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":37934,"requests_with_tool_call_errors":937},"qwen/qwen3-reranker-8b":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-reranker-8b","variant":"standard","variant_permaslug":"qwen/qwen3-reranker-8b","count":286571,"total_completion_tokens":0,"total_prompt_tokens":2172650267,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":4878584,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"minimax/minimax-m2.1":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m2.1","variant":"standard","variant_permaslug":"minimax/minimax-m2.1","count":58484,"total_completion_tokens":47916012,"total_prompt_tokens":929707104,"total_native_tokens_reasoning":21521688,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":740341279,"total_tool_calls":24288,"requests_with_tool_call_errors":2268},"openai/gpt-5.6-terra-pro-20260709":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-terra-pro-20260709","variant":"standard","variant_permaslug":"openai/gpt-5.6-terra-pro-20260709","count":270487,"total_completion_tokens":597018708,"total_prompt_tokens":33577298786,"total_native_tokens_reasoning":244223717,"num_media_prompt":183537,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":24615112555,"total_tool_calls":102835,"requests_with_tool_call_errors":1753},"black-forest-labs/flux.2-max":{"date":"2026-08-17 00:00:00","model_permaslug":"black-forest-labs/flux.2-max","variant":"standard","variant_permaslug":"black-forest-labs/flux.2-max","count":28648,"total_completion_tokens":350992040,"total_prompt_tokens":58423603,"total_native_tokens_reasoning":0,"num_media_prompt":7099,"num_media_completion":28648,"image_output_requests":28648,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"kwaivgi/kling-v3.0-pro-20260429":{"date":"2026-08-17 00:00:00","model_permaslug":"kwaivgi/kling-v3.0-pro-20260429","variant":"standard","variant_permaslug":"kwaivgi/kling-v3.0-pro-20260429","count":5912,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":7504,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":41655,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3.5-plus-20260216":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.5-plus-20260216","variant":"standard","variant_permaslug":"qwen/qwen3.5-plus-20260216","count":365314,"total_completion_tokens":1410541141,"total_prompt_tokens":4167032599,"total_native_tokens_reasoning":968043600,"num_media_prompt":1087876,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":5521,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":20213,"requests_with_tool_call_errors":365},"bytedance/seedance-2.5-20260807":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance/seedance-2.5-20260807","variant":"standard","variant_permaslug":"bytedance/seedance-2.5-20260807","count":13048,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":16943,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":571,"video_output_seconds":139763,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":414,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3.6-flash-20260721:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.6-flash-20260721","variant":"batch","variant_permaslug":"google/gemini-3.6-flash-20260721:batch","count":71110,"total_completion_tokens":44979163,"total_prompt_tokens":111566092,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":14621868,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-nano-12b-v2-vl":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-nano-12b-v2-vl","variant":"standard","variant_permaslug":"nvidia/nemotron-nano-12b-v2-vl","count":985,"total_completion_tokens":359263,"total_prompt_tokens":15406257,"total_native_tokens_reasoning":987,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":526,"requests_with_tool_call_errors":0},"deepseek/deepseek-v4-pro-20260423":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v4-pro-20260423","variant":"standard","variant_permaslug":"deepseek/deepseek-v4-pro-20260423","count":81864756,"total_completion_tokens":74803862754,"total_prompt_tokens":2025382155135,"total_native_tokens_reasoning":47632541757,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1663169556642,"total_tool_calls":15269185,"requests_with_tool_call_errors":355146},"qwen/qwen3-vl-8b-thinking":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-8b-thinking","variant":"standard","variant_permaslug":"qwen/qwen3-vl-8b-thinking","count":17303,"total_completion_tokens":33234423,"total_prompt_tokens":36842989,"total_native_tokens_reasoning":31048883,"num_media_prompt":15269,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":979,"requests_with_tool_call_errors":64},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","variant":"standard","variant_permaslug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","count":5462,"total_completion_tokens":2615484,"total_prompt_tokens":66261326,"total_native_tokens_reasoning":2541497,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":53884288,"total_tool_calls":862,"requests_with_tool_call_errors":0},"google/gemini-2.5-flash-lite":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-flash-lite","variant":"standard","variant_permaslug":"google/gemini-2.5-flash-lite","count":289736537,"total_completion_tokens":68198340882,"total_prompt_tokens":742834323658,"total_native_tokens_reasoning":4395900982,"num_media_prompt":233811932,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":663102,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":490361,"total_native_tokens_cached":127267614992,"total_tool_calls":3567154,"requests_with_tool_call_errors":154441},"kwaipilot/kat-coder-air-v2.5-20260710":{"date":"2026-08-17 00:00:00","model_permaslug":"kwaipilot/kat-coder-air-v2.5-20260710","variant":"standard","variant_permaslug":"kwaipilot/kat-coder-air-v2.5-20260710","count":29305,"total_completion_tokens":28846200,"total_prompt_tokens":609329189,"total_native_tokens_reasoning":21841986,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":519321408,"total_tool_calls":10181,"requests_with_tool_call_errors":1191},"qwen/qwen3.6-flash":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.6-flash","variant":"standard","variant_permaslug":"qwen/qwen3.6-flash","count":2660751,"total_completion_tokens":1596842495,"total_prompt_tokens":16644997111,"total_native_tokens_reasoning":1162204934,"num_media_prompt":405508,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":3278,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2692593849,"total_tool_calls":213390,"requests_with_tool_call_errors":18225},"sentence-transformers/all-mpnet-base-v2-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"sentence-transformers/all-mpnet-base-v2-20251117","variant":"standard","variant_permaslug":"sentence-transformers/all-mpnet-base-v2-20251117","count":60341,"total_completion_tokens":0,"total_prompt_tokens":302353766,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta/muse-glimmer-30b-20260810":{"date":"2026-08-17 00:00:00","model_permaslug":"meta/muse-glimmer-30b-20260810","variant":"standard","variant_permaslug":"meta/muse-glimmer-30b-20260810","count":1722914,"total_completion_tokens":1360193331,"total_prompt_tokens":32519894507,"total_native_tokens_reasoning":811809058,"num_media_prompt":235292,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":26515208532,"total_tool_calls":555155,"requests_with_tool_call_errors":4642},"openai/o3-mini-high-2025-01-31":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o3-mini-high-2025-01-31","variant":"standard","variant_permaslug":"openai/o3-mini-high-2025-01-31","count":3485,"total_completion_tokens":3496673,"total_prompt_tokens":3897559,"total_native_tokens_reasoning":3195070,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2347264,"total_tool_calls":216,"requests_with_tool_call_errors":0},"openai/gpt-5.3-codex-20260224":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.3-codex-20260224","variant":"standard","variant_permaslug":"openai/gpt-5.3-codex-20260224","count":777591,"total_completion_tokens":483417437,"total_prompt_tokens":38678012859,"total_native_tokens_reasoning":187384580,"num_media_prompt":102357,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":34325048064,"total_tool_calls":476423,"requests_with_tool_call_errors":3715},"microsoft/mai-voice-2-flash-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/mai-voice-2-flash-20260723","variant":"standard","variant_permaslug":"microsoft/mai-voice-2-flash-20260723","count":27763,"total_completion_tokens":0,"total_prompt_tokens":923017,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"black-forest-labs/flux.2-klein-4b":{"date":"2026-08-17 00:00:00","model_permaslug":"black-forest-labs/flux.2-klein-4b","variant":"standard","variant_permaslug":"black-forest-labs/flux.2-klein-4b","count":73248,"total_completion_tokens":379425516,"total_prompt_tokens":147046340,"total_native_tokens_reasoning":0,"num_media_prompt":24485,"num_media_completion":73248,"image_output_requests":73248,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"dots-studio/dots-3-note-preview-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"dots-studio/dots-3-note-preview-20260813","variant":"standard","variant_permaslug":"dots-studio/dots-3-note-preview-20260813","count":9273,"total_completion_tokens":4913597,"total_prompt_tokens":1047521079,"total_native_tokens_reasoning":4476337,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":988854784,"total_tool_calls":1043,"requests_with_tool_call_errors":0},"nvidia/nemotron-3-nano-30b-a3b":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-nano-30b-a3b","variant":"standard","variant_permaslug":"nvidia/nemotron-3-nano-30b-a3b","count":905520,"total_completion_tokens":816488610,"total_prompt_tokens":3211243172,"total_native_tokens_reasoning":655826657,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":289519872,"total_tool_calls":62721,"requests_with_tool_call_errors":7094},"anthropic/claude-opus-5-fast-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-opus-5-fast-20260723","variant":"standard","variant_permaslug":"anthropic/claude-opus-5-fast-20260723","count":282217,"total_completion_tokens":247277160,"total_prompt_tokens":28045042841,"total_native_tokens_reasoning":87236590,"num_media_prompt":223232,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":22812749948,"total_tool_calls":115086,"requests_with_tool_call_errors":731},"deepseek/deepseek-v3.1-terminus":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v3.1-terminus","variant":"standard","variant_permaslug":"deepseek/deepseek-v3.1-terminus","count":1041172,"total_completion_tokens":266367630,"total_prompt_tokens":8159242600,"total_native_tokens_reasoning":13720785,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3830036370,"total_tool_calls":118427,"requests_with_tool_call_errors":2342},"ibm-granite/granite-4.0-h-micro":{"date":"2026-08-17 00:00:00","model_permaslug":"ibm-granite/granite-4.0-h-micro","variant":"standard","variant_permaslug":"ibm-granite/granite-4.0-h-micro","count":239226,"total_completion_tokens":39593889,"total_prompt_tokens":400142996,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-3.1-flash-lite-preview-20260303":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-flash-lite-preview-20260303","variant":"standard","variant_permaslug":"google/gemini-3.1-flash-lite-preview-20260303","count":26702837,"total_completion_tokens":4757837238,"total_prompt_tokens":97902380797,"total_native_tokens_reasoning":769474710,"num_media_prompt":7872469,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":72323,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":55126,"total_native_tokens_cached":18858152878,"total_tool_calls":574073,"requests_with_tool_call_errors":12185},"meta-llama/llama-4-scout-17b-16e-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-4-scout-17b-16e-instruct","variant":"standard","variant_permaslug":"meta-llama/llama-4-scout-17b-16e-instruct","count":13906572,"total_completion_tokens":2225893318,"total_prompt_tokens":20363815519,"total_native_tokens_reasoning":0,"num_media_prompt":1759933,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":58283,"requests_with_tool_call_errors":661},"openai/gpt-4.1-nano-2025-04-14:batch":{"date":"2026-08-18 00:00:00","model_permaslug":"openai/gpt-4.1-nano-2025-04-14","variant":"batch","variant_permaslug":"openai/gpt-4.1-nano-2025-04-14:batch","count":81,"total_completion_tokens":18995,"total_prompt_tokens":271017,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-nano-12b-v2-vl:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-nano-12b-v2-vl","variant":"free","variant_permaslug":"nvidia/nemotron-nano-12b-v2-vl:free","count":977629,"total_completion_tokens":353328161,"total_prompt_tokens":11471599727,"total_native_tokens_reasoning":6310604,"num_media_prompt":468304,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":6356,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":107407,"requests_with_tool_call_errors":52947},"moonshotai/kimi-k3-20260715":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k3-20260715","variant":"standard","variant_permaslug":"moonshotai/kimi-k3-20260715","count":23264425,"total_completion_tokens":26312081765,"total_prompt_tokens":1481645042948,"total_native_tokens_reasoning":17040978756,"num_media_prompt":16099055,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":3065,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1249300486468,"total_tool_calls":15066449,"requests_with_tool_call_errors":87290},"google/gemini-3.5-flash-lite-20260721:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.5-flash-lite-20260721","variant":"batch","variant_permaslug":"google/gemini-3.5-flash-lite-20260721:batch","count":108382,"total_completion_tokens":35438512,"total_prompt_tokens":332361418,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":21185604,"total_tool_calls":36,"requests_with_tool_call_errors":0},"google/gemini-embedding-2-preview":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-embedding-2-preview","variant":"standard","variant_permaslug":"google/gemini-embedding-2-preview","count":2380916,"total_completion_tokens":0,"total_prompt_tokens":4509302039,"total_native_tokens_reasoning":0,"num_media_prompt":388777,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/veo-3.1-lite-20260331":{"date":"2026-08-17 00:00:00","model_permaslug":"google/veo-3.1-lite-20260331","variant":"standard","variant_permaslug":"google/veo-3.1-lite-20260331","count":26819,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":16630,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":143252,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"moonshotai/kimi-k2.6-20260420":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2.6-20260420","variant":"standard","variant_permaslug":"moonshotai/kimi-k2.6-20260420","count":12073674,"total_completion_tokens":19401544018,"total_prompt_tokens":184958048159,"total_native_tokens_reasoning":16286046552,"num_media_prompt":7802651,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":122006272332,"total_tool_calls":2752592,"requests_with_tool_call_errors":17936},"anthropic/claude-4.5-sonnet-20250929:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.5-sonnet-20250929","variant":"batch","variant_permaslug":"anthropic/claude-4.5-sonnet-20250929:batch","count":2129,"total_completion_tokens":769992,"total_prompt_tokens":9039223,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1211459,"total_tool_calls":0,"requests_with_tool_call_errors":0},"meta-llama/llama-guard-4-12b":{"date":"2026-08-17 00:00:00","model_permaslug":"meta-llama/llama-guard-4-12b","variant":"standard","variant_permaslug":"meta-llama/llama-guard-4-12b","count":3040582,"total_completion_tokens":9660922,"total_prompt_tokens":3285074015,"total_native_tokens_reasoning":0,"num_media_prompt":1375116,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5-2025-08-07:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-2025-08-07","variant":"batch","variant_permaslug":"openai/gpt-5-2025-08-07:batch","count":4740,"total_completion_tokens":8912256,"total_prompt_tokens":3527053,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"cohere/rerank-v3.5":{"date":"2026-08-17 00:00:00","model_permaslug":"cohere/rerank-v3.5","variant":"standard","variant_permaslug":"cohere/rerank-v3.5","count":985627,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":35363328,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"sentence-transformers/all-minilm-l6-v2-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"sentence-transformers/all-minilm-l6-v2-20251117","variant":"standard","variant_permaslug":"sentence-transformers/all-minilm-l6-v2-20251117","count":852680,"total_completion_tokens":0,"total_prompt_tokens":1469272210,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"recraft/recraft-v4.1-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4.1-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4.1-20260514","count":4676,"total_completion_tokens":20645375,"total_prompt_tokens":1666599,"total_native_tokens_reasoning":0,"num_media_prompt":384,"num_media_completion":4945,"image_output_requests":4676,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-build-0.1-20260520":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-build-0.1-20260520","variant":"standard","variant_permaslug":"x-ai/grok-build-0.1-20260520","count":109878,"total_completion_tokens":115423031,"total_prompt_tokens":3965470617,"total_native_tokens_reasoning":94087267,"num_media_prompt":18808,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3661998784,"total_tool_calls":59554,"requests_with_tool_call_errors":115},"qwen/qwen-audio-3.0-tts-flash-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-audio-3.0-tts-flash-20260723","variant":"standard","variant_permaslug":"qwen/qwen-audio-3.0-tts-flash-20260723","count":15004,"total_completion_tokens":0,"total_prompt_tokens":475368,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"recraft/recraft-v4.1-vector-20260514":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4.1-vector-20260514","variant":"standard","variant_permaslug":"recraft/recraft-v4.1-vector-20260514","count":2298,"total_completion_tokens":10642075,"total_prompt_tokens":498001,"total_native_tokens_reasoning":0,"num_media_prompt":205,"num_media_completion":2549,"image_output_requests":2298,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen2.5-vl-72b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen2.5-vl-72b-instruct","variant":"standard","variant_permaslug":"qwen/qwen2.5-vl-72b-instruct","count":1517072,"total_completion_tokens":133912837,"total_prompt_tokens":2999607311,"total_native_tokens_reasoning":0,"num_media_prompt":3053964,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":896638814,"total_tool_calls":13,"requests_with_tool_call_errors":11},"google/gemini-3-flash-preview-20251217":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3-flash-preview-20251217","variant":"standard","variant_permaslug":"google/gemini-3-flash-preview-20251217","count":99520176,"total_completion_tokens":34840543228,"total_prompt_tokens":920340227519,"total_native_tokens_reasoning":5044560187,"num_media_prompt":23805235,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":355922,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":864747,"total_native_tokens_cached":266150915691,"total_tool_calls":9579098,"requests_with_tool_call_errors":372513},"google/gemma-4-26b-a4b-it-20260403:free":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-4-26b-a4b-it-20260403","variant":"free","variant_permaslug":"google/gemma-4-26b-a4b-it-20260403:free","count":1532984,"total_completion_tokens":779875720,"total_prompt_tokens":8171587285,"total_native_tokens_reasoning":42672500,"num_media_prompt":228294,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":150,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":310237662,"total_tool_calls":68002,"requests_with_tool_call_errors":301},"nvidia/nemotron-3-ultra-550b-a55b-20260604:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","variant":"free","variant_permaslug":"nvidia/nemotron-3-ultra-550b-a55b-20260604:free","count":47407287,"total_completion_tokens":26851924467,"total_prompt_tokens":5449950357943,"total_native_tokens_reasoning":9222314473,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4441461125056,"total_tool_calls":32177264,"requests_with_tool_call_errors":736051},"google/gemini-3.1-pro-preview-customtools-20260219":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.1-pro-preview-customtools-20260219","variant":"standard","variant_permaslug":"google/gemini-3.1-pro-preview-customtools-20260219","count":69396,"total_completion_tokens":67747649,"total_prompt_tokens":1847247352,"total_native_tokens_reasoning":43960984,"num_media_prompt":20855,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":117,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":9439,"total_native_tokens_cached":1381606908,"total_tool_calls":25179,"requests_with_tool_call_errors":200},"mistralai/codestral-2508":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/codestral-2508","variant":"standard","variant_permaslug":"mistralai/codestral-2508","count":188399,"total_completion_tokens":36643908,"total_prompt_tokens":805681121,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":520826309,"total_tool_calls":3231,"requests_with_tool_call_errors":88},"openai/gpt-4o-mini-2024-07-18":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-mini-2024-07-18","variant":"standard","variant_permaslug":"openai/gpt-4o-mini-2024-07-18","count":4810859,"total_completion_tokens":441918617,"total_prompt_tokens":5844935915,"total_native_tokens_reasoning":0,"num_media_prompt":12229,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1692068480,"total_tool_calls":106886,"requests_with_tool_call_errors":354},"x-ai/grok-4.6-20260810":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-4.6-20260810","variant":"standard","variant_permaslug":"x-ai/grok-4.6-20260810","count":9615124,"total_completion_tokens":16218495597,"total_prompt_tokens":571976810263,"total_native_tokens_reasoning":10877093999,"num_media_prompt":5665571,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":466919281152,"total_tool_calls":5723887,"requests_with_tool_call_errors":56972},"voyageai/voyage-code-4-20260812":{"date":"2026-08-17 00:00:00","model_permaslug":"voyageai/voyage-code-4-20260812","variant":"standard","variant_permaslug":"voyageai/voyage-code-4-20260812","count":36284,"total_completion_tokens":0,"total_prompt_tokens":159935306,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthracite-org/magnum-v4-72b":{"date":"2026-08-17 00:00:00","model_permaslug":"anthracite-org/magnum-v4-72b","variant":"standard","variant_permaslug":"anthracite-org/magnum-v4-72b","count":40487,"total_completion_tokens":8454598,"total_prompt_tokens":131428573,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-vl-30b-a3b-thinking":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-30b-a3b-thinking","variant":"standard","variant_permaslug":"qwen/qwen3-vl-30b-a3b-thinking","count":90656,"total_completion_tokens":163898196,"total_prompt_tokens":197189298,"total_native_tokens_reasoning":142510672,"num_media_prompt":77624,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1122,"requests_with_tool_call_errors":26},"meituan/longcat-2.0-20260720":{"date":"2026-08-17 00:00:00","model_permaslug":"meituan/longcat-2.0-20260720","variant":"standard","variant_permaslug":"meituan/longcat-2.0-20260720","count":256101,"total_completion_tokens":198081148,"total_prompt_tokens":8346567666,"total_native_tokens_reasoning":141326777,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":7437820544,"total_tool_calls":53648,"requests_with_tool_call_errors":400},"openai/gpt-5.4-mini-20260317":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-mini-20260317","variant":"standard","variant_permaslug":"openai/gpt-5.4-mini-20260317","count":23558048,"total_completion_tokens":5688034567,"total_prompt_tokens":97467264459,"total_native_tokens_reasoning":915230739,"num_media_prompt":1605676,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":52613133696,"total_tool_calls":4010039,"requests_with_tool_call_errors":18215},"x-ai/grok-imagine-video-1.5-20260719":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-imagine-video-1.5-20260719","variant":"standard","variant_permaslug":"x-ai/grok-imagine-video-1.5-20260719","count":6531,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":5186,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":59020,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen-image-3-pro-20260805":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-image-3-pro-20260805","variant":"standard","variant_permaslug":"qwen/qwen-image-3-pro-20260805","count":12313,"total_completion_tokens":51911950,"total_prompt_tokens":4428400,"total_native_tokens_reasoning":0,"num_media_prompt":7476,"num_media_completion":12434,"image_output_requests":12313,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"x-ai/grok-imagine-image-2.0-20260811":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-imagine-image-2.0-20260811","variant":"standard","variant_permaslug":"x-ai/grok-imagine-image-2.0-20260811","count":88467,"total_completion_tokens":203798450,"total_prompt_tokens":103953406,"total_native_tokens_reasoning":0,"num_media_prompt":101136,"num_media_completion":88458,"image_output_requests":88458,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-asr-1.7b-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-asr-1.7b-20260813","variant":"standard","variant_permaslug":"qwen/qwen3-asr-1.7b-20260813","count":54422,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":149081455,"num_audio_prompt":54422,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b-20260813","variant":"standard","variant_permaslug":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b-20260813","count":61877,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":6827003,"num_audio_prompt":61877,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.2-chat-20251211":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.2-chat-20251211","variant":"standard","variant_permaslug":"openai/gpt-5.2-chat-20251211","count":63,"total_completion_tokens":58045,"total_prompt_tokens":411007,"total_native_tokens_reasoning":64,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":41216,"total_tool_calls":0,"requests_with_tool_call_errors":0},"bytedance/seedance-1-5-pro-20260320":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance/seedance-1-5-pro-20260320","variant":"standard","variant_permaslug":"bytedance/seedance-1-5-pro-20260320","count":12336,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":18906,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":97949,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nex-agi/nex-n2-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"nex-agi/nex-n2-pro","variant":"standard","variant_permaslug":"nex-agi/nex-n2-pro","count":67494,"total_completion_tokens":91048293,"total_prompt_tokens":1288178619,"total_native_tokens_reasoning":50015042,"num_media_prompt":3261,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1124204928,"total_tool_calls":30590,"requests_with_tool_call_errors":1024},"openai/gpt-4o:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o","variant":"batch","variant_permaslug":"openai/gpt-4o:batch","count":53113,"total_completion_tokens":2819366,"total_prompt_tokens":466181652,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"sakana/fugu-ultra-20260615":{"date":"2026-08-17 00:00:00","model_permaslug":"sakana/fugu-ultra-20260615","variant":"standard","variant_permaslug":"sakana/fugu-ultra-20260615","count":22279,"total_completion_tokens":36716948,"total_prompt_tokens":1519747154,"total_native_tokens_reasoning":13729968,"num_media_prompt":1296,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1244173463,"total_tool_calls":12118,"requests_with_tool_call_errors":42},"nvidia/nemotron-nano-9b-v2":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-nano-9b-v2","variant":"standard","variant_permaslug":"nvidia/nemotron-nano-9b-v2","count":450,"total_completion_tokens":456447,"total_prompt_tokens":4061159,"total_native_tokens_reasoning":360737,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":45,"requests_with_tool_call_errors":0},"Qwen/Qwen3-Embedding-8B":{"date":"2026-08-17 00:00:00","model_permaslug":"Qwen/Qwen3-Embedding-8B","variant":"standard","variant_permaslug":"Qwen/Qwen3-Embedding-8B","count":9826,"total_completion_tokens":0,"total_prompt_tokens":511039,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mistral-small-3.2-24b-instruct-2506":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-small-3.2-24b-instruct-2506","variant":"standard","variant_permaslug":"mistralai/mistral-small-3.2-24b-instruct-2506","count":8132219,"total_completion_tokens":1319263092,"total_prompt_tokens":17712028093,"total_native_tokens_reasoning":0,"num_media_prompt":363949,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":482315972,"total_tool_calls":433292,"requests_with_tool_call_errors":247961},"google/gemma-3-27b-it":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-3-27b-it","variant":"standard","variant_permaslug":"google/gemma-3-27b-it","count":25643641,"total_completion_tokens":11124805566,"total_prompt_tokens":38174890184,"total_native_tokens_reasoning":0,"num_media_prompt":4948808,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9857730384,"total_tool_calls":7641,"requests_with_tool_call_errors":416},"minimax/minimax-m2-her-20260123":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m2-her-20260123","variant":"standard","variant_permaslug":"minimax/minimax-m2-her-20260123","count":145514,"total_completion_tokens":7895107,"total_prompt_tokens":742163025,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-5.2-20260616:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"z-ai/glm-5.2-20260616","variant":"batch","variant_permaslug":"z-ai/glm-5.2-20260616:batch","count":31404,"total_completion_tokens":10531710,"total_prompt_tokens":31407418,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9135616,"total_tool_calls":2,"requests_with_tool_call_errors":0},"anthropic/claude-4.5-haiku-20251001:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.5-haiku-20251001","variant":"batch","variant_permaslug":"anthropic/claude-4.5-haiku-20251001:batch","count":416457,"total_completion_tokens":93657299,"total_prompt_tokens":395720443,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1196090,"total_tool_calls":1,"requests_with_tool_call_errors":0},"krea/krea-2-large-20260720":{"date":"2026-08-17 00:00:00","model_permaslug":"krea/krea-2-large-20260720","variant":"standard","variant_permaslug":"krea/krea-2-large-20260720","count":1690,"total_completion_tokens":7055750,"total_prompt_tokens":443457,"total_native_tokens_reasoning":0,"num_media_prompt":387,"num_media_completion":1690,"image_output_requests":1690,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-4.1-2025-04-14":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4.1-2025-04-14","variant":"standard","variant_permaslug":"openai/gpt-4.1-2025-04-14","count":11612140,"total_completion_tokens":1966905927,"total_prompt_tokens":56717729317,"total_native_tokens_reasoning":0,"num_media_prompt":1029501,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":32366488407,"total_tool_calls":1371608,"requests_with_tool_call_errors":3499},"kwaipilot/kat-coder-pro-v2-20260327":{"date":"2026-08-17 00:00:00","model_permaslug":"kwaipilot/kat-coder-pro-v2-20260327","variant":"standard","variant_permaslug":"kwaipilot/kat-coder-pro-v2-20260327","count":278238,"total_completion_tokens":27605658,"total_prompt_tokens":795417995,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":544473898,"total_tool_calls":10292,"requests_with_tool_call_errors":204},"qwen/qwen-image-3-20260805":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-image-3-20260805","variant":"standard","variant_permaslug":"qwen/qwen-image-3-20260805","count":42916,"total_completion_tokens":179462375,"total_prompt_tokens":10188429,"total_native_tokens_reasoning":0,"num_media_prompt":11438,"num_media_completion":42985,"image_output_requests":42916,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"intfloat/e5-base-v2-20251117":{"date":"2026-08-17 00:00:00","model_permaslug":"intfloat/e5-base-v2-20251117","variant":"standard","variant_permaslug":"intfloat/e5-base-v2-20251117","count":15080,"total_completion_tokens":0,"total_prompt_tokens":4435077,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"z-ai/glm-5.3-20260816":{"date":"2026-08-18 00:00:00","model_permaslug":"z-ai/glm-5.3-20260816","variant":"standard","variant_permaslug":"z-ai/glm-5.3-20260816","count":7320890,"total_completion_tokens":9641171375,"total_prompt_tokens":582639576352,"total_native_tokens_reasoning":7195701928,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":546340363840,"total_tool_calls":5060799,"requests_with_tool_call_errors":45674},"x-ai/grok-imagine-video-20260512":{"date":"2026-08-17 00:00:00","model_permaslug":"x-ai/grok-imagine-video-20260512","variant":"standard","variant_permaslug":"x-ai/grok-imagine-video-20260512","count":8603,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":6627,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":56948,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5-image-mini":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-image-mini","variant":"standard","variant_permaslug":"openai/gpt-5-image-mini","count":30593,"total_completion_tokens":134370803,"total_prompt_tokens":77671120,"total_native_tokens_reasoning":20589980,"num_media_prompt":9879,"num_media_completion":26986,"image_output_requests":26716,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2721020,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/veo-3.1-fast-20260320":{"date":"2026-08-17 00:00:00","model_permaslug":"google/veo-3.1-fast-20260320","variant":"standard","variant_permaslug":"google/veo-3.1-fast-20260320","count":10727,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":9790,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":68292,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-oss-safeguard-20b":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-oss-safeguard-20b","variant":"standard","variant_permaslug":"openai/gpt-oss-safeguard-20b","count":3248241,"total_completion_tokens":625655949,"total_prompt_tokens":6730092296,"total_native_tokens_reasoning":539530736,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3756688640,"total_tool_calls":1578,"requests_with_tool_call_errors":168},"openai/gpt-oss-120b":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-oss-120b","variant":"standard","variant_permaslug":"openai/gpt-oss-120b","count":148115479,"total_completion_tokens":83032363633,"total_prompt_tokens":479892255500,"total_native_tokens_reasoning":53634906024,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":136321515625,"total_tool_calls":6518659,"requests_with_tool_call_errors":317002},"mistralai/mistral-large-2407":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-large-2407","variant":"standard","variant_permaslug":"mistralai/mistral-large-2407","count":44632,"total_completion_tokens":12427007,"total_prompt_tokens":120442755,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":39411235,"total_tool_calls":1253,"requests_with_tool_call_errors":45},"google/gemini-3.7-flash-20260813":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-3.7-flash-20260813","variant":"standard","variant_permaslug":"google/gemini-3.7-flash-20260813","count":65208307,"total_completion_tokens":52109697842,"total_prompt_tokens":2021684376967,"total_native_tokens_reasoning":24324647225,"num_media_prompt":36620568,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":421995,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":875838,"total_native_tokens_cached":1502944744220,"total_tool_calls":17427983,"requests_with_tool_call_errors":307399},"qwen/qwen3-embedding-4b":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-embedding-4b","variant":"standard","variant_permaslug":"qwen/qwen3-embedding-4b","count":3697789,"total_completion_tokens":0,"total_prompt_tokens":8707177830,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mixtral-8x22b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mixtral-8x22b-instruct","variant":"standard","variant_permaslug":"mistralai/mixtral-8x22b-instruct","count":52333,"total_completion_tokens":21167335,"total_prompt_tokens":109295176,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":35619666,"total_tool_calls":363,"requests_with_tool_call_errors":2},"openai/gpt-5.2-pro-20251211":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.2-pro-20251211","variant":"standard","variant_permaslug":"openai/gpt-5.2-pro-20251211","count":12009,"total_completion_tokens":2525512,"total_prompt_tokens":17048999,"total_native_tokens_reasoning":837744,"num_media_prompt":462,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":202,"requests_with_tool_call_errors":0},"recraft/recraft-v4-20260413":{"date":"2026-08-17 00:00:00","model_permaslug":"recraft/recraft-v4-20260413","variant":"standard","variant_permaslug":"recraft/recraft-v4-20260413","count":2821,"total_completion_tokens":11806900,"total_prompt_tokens":786251,"total_native_tokens_reasoning":0,"num_media_prompt":87,"num_media_completion":2828,"image_output_requests":2821,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"thedrummer/cydonia-24b-v4.1":{"date":"2026-08-17 00:00:00","model_permaslug":"thedrummer/cydonia-24b-v4.1","variant":"standard","variant_permaslug":"thedrummer/cydonia-24b-v4.1","count":411169,"total_completion_tokens":87052044,"total_prompt_tokens":1435722022,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":162999168,"total_tool_calls":0,"requests_with_tool_call_errors":0},"nousresearch/hermes-4-405b":{"date":"2026-08-17 00:00:00","model_permaslug":"nousresearch/hermes-4-405b","variant":"standard","variant_permaslug":"nousresearch/hermes-4-405b","count":173461,"total_completion_tokens":33441208,"total_prompt_tokens":575440830,"total_native_tokens_reasoning":1360592,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":327591112,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-235b-a22b-07-25":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-235b-a22b-07-25","variant":"standard","variant_permaslug":"qwen/qwen3-235b-a22b-07-25","count":18981920,"total_completion_tokens":4364654653,"total_prompt_tokens":69713293716,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":12488898304,"total_tool_calls":898966,"requests_with_tool_call_errors":26505},"moonshotai/kimi-k2.7-code-20260612:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2.7-code-20260612","variant":"batch","variant_permaslug":"moonshotai/kimi-k2.7-code-20260612:batch","count":11520,"total_completion_tokens":320185658,"total_prompt_tokens":3770930,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":2254912,"total_tool_calls":0,"requests_with_tool_call_errors":0},"perplexity/sonar-pro-search":{"date":"2026-08-17 00:00:00","model_permaslug":"perplexity/sonar-pro-search","variant":"standard","variant_permaslug":"perplexity/sonar-pro-search","count":124989,"total_completion_tokens":164195017,"total_prompt_tokens":187104437,"total_native_tokens_reasoning":0,"num_media_prompt":2250,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-coder-30b-a3b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-coder-30b-a3b-instruct","variant":"standard","variant_permaslug":"qwen/qwen3-coder-30b-a3b-instruct","count":643876,"total_completion_tokens":178615762,"total_prompt_tokens":4532535157,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":788773488,"total_tool_calls":145484,"requests_with_tool_call_errors":13835},"minimax/minimax-m2.5-20260211":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/minimax-m2.5-20260211","variant":"standard","variant_permaslug":"minimax/minimax-m2.5-20260211","count":2564320,"total_completion_tokens":1082427819,"total_prompt_tokens":50010818037,"total_native_tokens_reasoning":726754834,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":43499329308,"total_tool_calls":1376627,"requests_with_tool_call_errors":18468},"openai/gpt-image-2":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-image-2","variant":"standard","variant_permaslug":"openai/gpt-image-2","count":521239,"total_completion_tokens":699491230,"total_prompt_tokens":1021458625,"total_native_tokens_reasoning":0,"num_media_prompt":623802,"num_media_completion":528060,"image_output_requests":520875,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-next-80b-a3b-instruct-2509":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-next-80b-a3b-instruct-2509","variant":"standard","variant_permaslug":"qwen/qwen3-next-80b-a3b-instruct-2509","count":3443538,"total_completion_tokens":1075570596,"total_prompt_tokens":15749949537,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":4278389184,"total_tool_calls":200180,"requests_with_tool_call_errors":1071},"anthropic/claude-4.8-opus-20260528:batch":{"date":"2026-08-18 00:00:00","model_permaslug":"anthropic/claude-4.8-opus-20260528","variant":"batch","variant_permaslug":"anthropic/claude-4.8-opus-20260528:batch","count":2863,"total_completion_tokens":859315,"total_prompt_tokens":2147255,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1248,"requests_with_tool_call_errors":0},"qwen/qwen3.7-plus-20260602":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3.7-plus-20260602","variant":"standard","variant_permaslug":"qwen/qwen3.7-plus-20260602","count":20975093,"total_completion_tokens":5064487255,"total_prompt_tokens":97718455158,"total_native_tokens_reasoning":2744331685,"num_media_prompt":3475064,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":58701600312,"total_tool_calls":947797,"requests_with_tool_call_errors":51352},"rekaai/reka-edge-2603":{"date":"2026-08-17 00:00:00","model_permaslug":"rekaai/reka-edge-2603","variant":"standard","variant_permaslug":"rekaai/reka-edge-2603","count":32721,"total_completion_tokens":6115491,"total_prompt_tokens":33509865,"total_native_tokens_reasoning":0,"num_media_prompt":15821,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":347,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":10113264,"total_tool_calls":1059,"requests_with_tool_call_errors":152},"nvidia/llama-nemotron-rerank-vl-1b-v2:free":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/llama-nemotron-rerank-vl-1b-v2","variant":"free","variant_permaslug":"nvidia/llama-nemotron-rerank-vl-1b-v2:free","count":1807478,"total_completion_tokens":0,"total_prompt_tokens":16755817934,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":46228494,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-3.5-turbo-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-3.5-turbo-instruct","variant":"standard","variant_permaslug":"openai/gpt-3.5-turbo-instruct","count":18961,"total_completion_tokens":2650447,"total_prompt_tokens":4102636,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/ministral-14b-2512":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/ministral-14b-2512","variant":"standard","variant_permaslug":"mistralai/ministral-14b-2512","count":1897588,"total_completion_tokens":774131865,"total_prompt_tokens":2969295326,"total_native_tokens_reasoning":0,"num_media_prompt":33640,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1642272323,"total_tool_calls":22324,"requests_with_tool_call_errors":1186},"openai/gpt-5-mini-2025-08-07":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-mini-2025-08-07","variant":"standard","variant_permaslug":"openai/gpt-5-mini-2025-08-07","count":34821111,"total_completion_tokens":22127904305,"total_prompt_tokens":205760876630,"total_native_tokens_reasoning":14758729270,"num_media_prompt":2396390,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":84317766272,"total_tool_calls":11993794,"requests_with_tool_call_errors":11344},"moonshotai/kimi-k2-thinking-20251106":{"date":"2026-08-17 00:00:00","model_permaslug":"moonshotai/kimi-k2-thinking-20251106","variant":"standard","variant_permaslug":"moonshotai/kimi-k2-thinking-20251106","count":243798,"total_completion_tokens":544583416,"total_prompt_tokens":1889297502,"total_native_tokens_reasoning":426978443,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1124424137,"total_tool_calls":31307,"requests_with_tool_call_errors":462},"nvidia/nemotron-3.5-content-safety-20260604":{"date":"2026-08-17 00:00:00","model_permaslug":"nvidia/nemotron-3.5-content-safety-20260604","variant":"standard","variant_permaslug":"nvidia/nemotron-3.5-content-safety-20260604","count":18,"total_completion_tokens":2835,"total_prompt_tokens":32090,"total_native_tokens_reasoning":2933,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"deepseek/deepseek-chat-v3-0324":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-chat-v3-0324","variant":"standard","variant_permaslug":"deepseek/deepseek-chat-v3-0324","count":6753658,"total_completion_tokens":1519702570,"total_prompt_tokens":30294685834,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9565403841,"total_tool_calls":152060,"requests_with_tool_call_errors":1279},"thinkingmachines/inkling-20260715:free":{"date":"2026-08-21 00:00:00","model_permaslug":"thinkingmachines/inkling-20260715","variant":"free","variant_permaslug":"thinkingmachines/inkling-20260715:free","count":610492,"total_completion_tokens":208406584,"total_prompt_tokens":31401913953,"total_native_tokens_reasoning":116413562,"num_media_prompt":410886,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":6,"total_native_tokens_cached":23536767616,"total_tool_calls":464878,"requests_with_tool_call_errors":21172},"anthropic/claude-sonnet-5-20260630":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-sonnet-5-20260630","variant":"standard","variant_permaslug":"anthropic/claude-sonnet-5-20260630","count":22299572,"total_completion_tokens":19818005514,"total_prompt_tokens":1210152770492,"total_native_tokens_reasoning":10033315846,"num_media_prompt":11964333,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":964888799441,"total_tool_calls":9392755,"requests_with_tool_call_errors":237157},"openai/gpt-image-1-mini":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-image-1-mini","variant":"standard","variant_permaslug":"openai/gpt-image-1-mini","count":14679,"total_completion_tokens":25095300,"total_prompt_tokens":7908664,"total_native_tokens_reasoning":0,"num_media_prompt":2801,"num_media_completion":14728,"image_output_requests":14673,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"morph/morph-v3-fast":{"date":"2026-08-17 00:00:00","model_permaslug":"morph/morph-v3-fast","variant":"standard","variant_permaslug":"morph/morph-v3-fast","count":11285,"total_completion_tokens":74039298,"total_prompt_tokens":58087949,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o1-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/o1-pro","variant":"standard","variant_permaslug":"openai/o1-pro","count":1142,"total_completion_tokens":410521,"total_prompt_tokens":386038,"total_native_tokens_reasoning":365888,"num_media_prompt":60,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"mistralai/mistral-small-3.1-24b-instruct-2503":{"date":"2026-08-17 00:00:00","model_permaslug":"mistralai/mistral-small-3.1-24b-instruct-2503","variant":"standard","variant_permaslug":"mistralai/mistral-small-3.1-24b-instruct-2503","count":562758,"total_completion_tokens":44882420,"total_prompt_tokens":546984951,"total_native_tokens_reasoning":0,"num_media_prompt":2761,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemma-4-31b-it-20260402":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemma-4-31b-it-20260402","variant":"standard","variant_permaslug":"google/gemma-4-31b-it-20260402","count":87511704,"total_completion_tokens":25014568278,"total_prompt_tokens":403010788762,"total_native_tokens_reasoning":2739463417,"num_media_prompt":15971680,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":44144,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":111937805881,"total_tool_calls":3698974,"requests_with_tool_call_errors":48307},"qwen/qwen-2.5-72b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen-2.5-72b-instruct","variant":"standard","variant_permaslug":"qwen/qwen-2.5-72b-instruct","count":2691782,"total_completion_tokens":706281034,"total_prompt_tokens":4239450893,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":37328,"requests_with_tool_call_errors":923},"liquid/lfm-2.5-embedding-350m-20260818:free":{"date":"2026-08-18 00:00:00","model_permaslug":"liquid/lfm-2.5-embedding-350m-20260818","variant":"free","variant_permaslug":"liquid/lfm-2.5-embedding-350m-20260818:free","count":348319,"total_completion_tokens":0,"total_prompt_tokens":349781952,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-chat-latest-20260505":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-chat-latest-20260505","variant":"standard","variant_permaslug":"openai/gpt-chat-latest-20260505","count":166935,"total_completion_tokens":37842467,"total_prompt_tokens":1616638019,"total_native_tokens_reasoning":1011968,"num_media_prompt":32596,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":1097246080,"total_tool_calls":12529,"requests_with_tool_call_errors":7},"runway/aleph-2-20260729":{"date":"2026-08-17 00:00:00","model_permaslug":"runway/aleph-2-20260729","variant":"standard","variant_permaslug":"runway/aleph-2-20260729","count":161,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":161,"video_output_seconds":779,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-3.5-turbo:batch":{"date":"2026-08-18 00:00:00","model_permaslug":"openai/gpt-3.5-turbo","variant":"batch","variant_permaslug":"openai/gpt-3.5-turbo:batch","count":563432,"total_completion_tokens":168610637,"total_prompt_tokens":1670748751,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":1694,"requests_with_tool_call_errors":0},"openai/gpt-5.1-codex-max-20251204":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.1-codex-max-20251204","variant":"standard","variant_permaslug":"openai/gpt-5.1-codex-max-20251204","count":15956,"total_completion_tokens":11781839,"total_prompt_tokens":167495074,"total_native_tokens_reasoning":7688159,"num_media_prompt":413,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":132914048,"total_tool_calls":3617,"requests_with_tool_call_errors":134},"poolside/laguna-xs-2.1-20260625:free":{"date":"2026-08-17 00:00:00","model_permaslug":"poolside/laguna-xs-2.1-20260625","variant":"free","variant_permaslug":"poolside/laguna-xs-2.1-20260625:free","count":3115857,"total_completion_tokens":1382570828,"total_prompt_tokens":159877338010,"total_native_tokens_reasoning":447592171,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":81812676752,"total_tool_calls":1792480,"requests_with_tool_call_errors":220168},"openai/gpt-4o-2024-05-13":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-4o-2024-05-13","variant":"standard","variant_permaslug":"openai/gpt-4o-2024-05-13","count":393593,"total_completion_tokens":5670657,"total_prompt_tokens":213295412,"total_native_tokens_reasoning":0,"num_media_prompt":19032,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":9060480,"total_tool_calls":1459,"requests_with_tool_call_errors":15},"mancer/weaver":{"date":"2026-08-17 00:00:00","model_permaslug":"mancer/weaver","variant":"standard","variant_permaslug":"mancer/weaver","count":3241,"total_completion_tokens":331369,"total_prompt_tokens":937809,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"deepgram/nova-3-20260714":{"date":"2026-08-17 00:00:00","model_permaslug":"deepgram/nova-3-20260714","variant":"standard","variant_permaslug":"deepgram/nova-3-20260714","count":224903,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":39282356,"num_audio_prompt":224903,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"qwen/qwen3-vl-32b-instruct":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-vl-32b-instruct","variant":"standard","variant_permaslug":"qwen/qwen3-vl-32b-instruct","count":6328602,"total_completion_tokens":1948641537,"total_prompt_tokens":20399391562,"total_native_tokens_reasoning":0,"num_media_prompt":10116797,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":174292,"requests_with_tool_call_errors":11348},"deepseek/deepseek-v3.2-exp":{"date":"2026-08-17 00:00:00","model_permaslug":"deepseek/deepseek-v3.2-exp","variant":"standard","variant_permaslug":"deepseek/deepseek-v3.2-exp","count":4247803,"total_completion_tokens":1598696232,"total_prompt_tokens":22699760232,"total_native_tokens_reasoning":416337978,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":3242304576,"total_tool_calls":36186,"requests_with_tool_call_errors":442},"minimax/hailuo-03-20260730":{"date":"2026-08-17 00:00:00","model_permaslug":"minimax/hailuo-03-20260730","variant":"standard","variant_permaslug":"minimax/hailuo-03-20260730","count":7476,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":9361,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":562,"video_output_seconds":58976,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":638,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5-nano-2025-08-07":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5-nano-2025-08-07","variant":"standard","variant_permaslug":"openai/gpt-5-nano-2025-08-07","count":18156558,"total_completion_tokens":11995550525,"total_prompt_tokens":36963962856,"total_native_tokens_reasoning":8947035144,"num_media_prompt":1357344,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":13712617216,"total_tool_calls":484701,"requests_with_tool_call_errors":1213},"qwen/qwen3-30b-a3b-instruct-2507":{"date":"2026-08-17 00:00:00","model_permaslug":"qwen/qwen3-30b-a3b-instruct-2507","variant":"standard","variant_permaslug":"qwen/qwen3-30b-a3b-instruct-2507","count":17121301,"total_completion_tokens":2802269191,"total_prompt_tokens":34828616116,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":20017179147,"total_tool_calls":358419,"requests_with_tool_call_errors":11522},"microsoft/mai-image-2.5-pro-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"microsoft/mai-image-2.5-pro-20260723","variant":"standard","variant_permaslug":"microsoft/mai-image-2.5-pro-20260723","count":7225,"total_completion_tokens":7273885,"total_prompt_tokens":7732948,"total_native_tokens_reasoning":0,"num_media_prompt":3044,"num_media_completion":7223,"image_output_requests":7223,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"inclusionai/ling-3.0-flash-20260723":{"date":"2026-08-17 00:00:00","model_permaslug":"inclusionai/ling-3.0-flash-20260723","variant":"standard","variant_permaslug":"inclusionai/ling-3.0-flash-20260723","count":21465114,"total_completion_tokens":5436183604,"total_prompt_tokens":79671090928,"total_native_tokens_reasoning":2477507517,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":47975563359,"total_tool_calls":15086028,"requests_with_tool_call_errors":27276},"perceptron/perceptron-mk1-20260512":{"date":"2026-08-17 00:00:00","model_permaslug":"perceptron/perceptron-mk1-20260512","variant":"standard","variant_permaslug":"perceptron/perceptron-mk1-20260512","count":325828,"total_completion_tokens":21850453,"total_prompt_tokens":437021059,"total_native_tokens_reasoning":113542,"num_media_prompt":216731,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":107926,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"google/gemini-2.5-pro":{"date":"2026-08-17 00:00:00","model_permaslug":"google/gemini-2.5-pro","variant":"standard","variant_permaslug":"google/gemini-2.5-pro","count":4808568,"total_completion_tokens":6571764889,"total_prompt_tokens":49500362988,"total_native_tokens_reasoning":3721163218,"num_media_prompt":1216948,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":7152,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":73112,"total_native_tokens_cached":21629465734,"total_tool_calls":193059,"requests_with_tool_call_errors":12900},"sourceful/riverflow-v2-fast-20260130":{"date":"2026-08-17 00:00:00","model_permaslug":"sourceful/riverflow-v2-fast-20260130","variant":"standard","variant_permaslug":"sourceful/riverflow-v2-fast-20260130","count":10447,"total_completion_tokens":43616225,"total_prompt_tokens":1634329,"total_native_tokens_reasoning":0,"num_media_prompt":562,"num_media_completion":10447,"image_output_requests":10447,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"xiaomi/mimo-v2.5-20260422":{"date":"2026-08-17 00:00:00","model_permaslug":"xiaomi/mimo-v2.5-20260422","variant":"standard","variant_permaslug":"xiaomi/mimo-v2.5-20260422","count":138520406,"total_completion_tokens":77844615259,"total_prompt_tokens":11249121819258,"total_native_tokens_reasoning":13037318068,"num_media_prompt":71267819,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":171190,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":1145633,"total_native_tokens_cached":10675152220410,"total_tool_calls":98503344,"requests_with_tool_call_errors":1144152},"bytedance/seedance-2.0-20260414":{"date":"2026-08-17 00:00:00","model_permaslug":"bytedance/seedance-2.0-20260414","variant":"standard","variant_permaslug":"bytedance/seedance-2.0-20260414","count":14018,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":22966,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":1360,"video_output_seconds":117027,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":227,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.2-20251211:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.2-20251211","variant":"batch","variant_permaslug":"openai/gpt-5.2-20251211:batch","count":1466,"total_completion_tokens":672574,"total_prompt_tokens":1996893,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":292096,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.4-mini-20260317:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.4-mini-20260317","variant":"batch","variant_permaslug":"openai/gpt-5.4-mini-20260317:batch","count":308331,"total_completion_tokens":58009036,"total_prompt_tokens":427357284,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":485632,"total_tool_calls":1,"requests_with_tool_call_errors":0},"openai/gpt-5-pro-2025-10-06:batch":{"date":"2026-08-23 00:00:00","model_permaslug":"openai/gpt-5-pro-2025-10-06","variant":"batch","variant_permaslug":"openai/gpt-5-pro-2025-10-06:batch","count":40,"total_completion_tokens":40960,"total_prompt_tokens":15630,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"BAAI/bge-base-en-v1.5":{"date":"2026-08-17 00:00:00","model_permaslug":"BAAI/bge-base-en-v1.5","variant":"standard","variant_permaslug":"BAAI/bge-base-en-v1.5","count":39,"total_completion_tokens":0,"total_prompt_tokens":451,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-5.6-terra-pro-20260709:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-5.6-terra-pro-20260709","variant":"batch","variant_permaslug":"openai/gpt-5.6-terra-pro-20260709:batch","count":795,"total_completion_tokens":1297136,"total_prompt_tokens":22888803,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":13033375,"total_tool_calls":0,"requests_with_tool_call_errors":0},"baai/bge-m3":{"date":"2026-08-17 00:00:00","model_permaslug":"baai/bge-m3","variant":"standard","variant_permaslug":"baai/bge-m3","count":69,"total_completion_tokens":0,"total_prompt_tokens":19422,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/gpt-oss-20b:free":{"date":"2026-08-17 00:00:00","model_permaslug":"openai/gpt-oss-20b","variant":"free","variant_permaslug":"openai/gpt-oss-20b:free","count":1515778,"total_completion_tokens":1433243207,"total_prompt_tokens":4729441527,"total_native_tokens_reasoning":918096566,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":114309,"requests_with_tool_call_errors":72},"thinkingmachines/inkling-20260715:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"thinkingmachines/inkling-20260715","variant":"batch","variant_permaslug":"thinkingmachines/inkling-20260715:batch","count":341,"total_completion_tokens":1139170,"total_prompt_tokens":385833,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":26240,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.6-opus-20260205:batch":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.6-opus-20260205","variant":"batch","variant_permaslug":"anthropic/claude-4.6-opus-20260205:batch","count":143,"total_completion_tokens":132764,"total_prompt_tokens":1003893,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"deepcogito/cogito-v2.1-671b-20251118":{"date":"2026-08-17 00:00:00","model_permaslug":"deepcogito/cogito-v2.1-671b-20251118","variant":"standard","variant_permaslug":"deepcogito/cogito-v2.1-671b-20251118","count":29850,"total_completion_tokens":2512101,"total_prompt_tokens":58102089,"total_native_tokens_reasoning":186062,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/text-embedding-3-large:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"openai/text-embedding-3-large","variant":"batch","variant_permaslug":"openai/text-embedding-3-large:batch","count":217,"total_completion_tokens":0,"total_prompt_tokens":81085,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o3-mini-2025-01-31:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"openai/o3-mini-2025-01-31","variant":"batch","variant_permaslug":"openai/o3-mini-2025-01-31:batch","count":10,"total_completion_tokens":13715,"total_prompt_tokens":930,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o4-mini-2025-04-16:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"openai/o4-mini-2025-04-16","variant":"batch","variant_permaslug":"openai/o4-mini-2025-04-16:batch","count":10,"total_completion_tokens":12388,"total_prompt_tokens":930,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.5-opus-20251124:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"anthropic/claude-4.5-opus-20251124","variant":"batch","variant_permaslug":"anthropic/claude-4.5-opus-20251124:batch","count":198,"total_completion_tokens":12136,"total_prompt_tokens":216935,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o3-2025-04-16:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"openai/o3-2025-04-16","variant":"batch","variant_permaslug":"openai/o3-2025-04-16:batch","count":10,"total_completion_tokens":14537,"total_prompt_tokens":930,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openai/o1-2024-12-17:batch":{"date":"2026-08-20 00:00:00","model_permaslug":"openai/o1-2024-12-17","variant":"batch","variant_permaslug":"openai/o1-2024-12-17:batch","count":10,"total_completion_tokens":11674,"total_prompt_tokens":930,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"thedrummer/rocinante-12b":{"date":"2026-08-17 00:00:00","model_permaslug":"thedrummer/rocinante-12b","variant":"standard","variant_permaslug":"thedrummer/rocinante-12b","count":44888,"total_completion_tokens":9874980,"total_prompt_tokens":140513748,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":40306848,"total_tool_calls":0,"requests_with_tool_call_errors":0},"arcee-ai/virtuoso-large":{"date":"2026-08-18 00:00:00","model_permaslug":"arcee-ai/virtuoso-large","variant":"standard","variant_permaslug":"arcee-ai/virtuoso-large","count":3,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"ai21/jamba-large-1.7":{"date":"2026-08-18 00:00:00","model_permaslug":"ai21/jamba-large-1.7","variant":"standard","variant_permaslug":"ai21/jamba-large-1.7","count":3,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"anthropic/claude-4.7-opus-fast-20260512":{"date":"2026-08-17 00:00:00","model_permaslug":"anthropic/claude-4.7-opus-fast-20260512","variant":"standard","variant_permaslug":"anthropic/claude-4.7-opus-fast-20260512","count":4,"total_completion_tokens":0,"total_prompt_tokens":0,"total_native_tokens_reasoning":0,"num_media_prompt":0,"num_media_completion":0,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0,"num_audio_prompt":0,"total_native_tokens_cached":0,"total_tool_calls":0,"requests_with_tool_call_errors":0},"openrouter/auto":{"date":"2026-08-17","model_permaslug":"openrouter/auto","variant":"standard","variant_permaslug":"openrouter/auto","count":4109737,"total_completion_tokens":3232703227,"total_prompt_tokens":235518376614,"total_native_tokens_reasoning":1879464612,"num_media_prompt":452258,"num_media_completion":975,"num_audio_prompt":332,"total_native_tokens_cached":175489539627,"total_tool_calls":2236167,"requests_with_tool_call_errors":31664,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0},"openrouter/auto-beta":{"date":"2026-08-17","model_permaslug":"openrouter/auto-beta","variant":"standard","variant_permaslug":"openrouter/auto-beta","count":1835083,"total_completion_tokens":1553448314,"total_prompt_tokens":194175956195,"total_native_tokens_reasoning":698410060,"num_media_prompt":1671030,"num_media_completion":338,"num_audio_prompt":84,"total_native_tokens_cached":173276194758,"total_tool_calls":1198188,"requests_with_tool_call_errors":33971,"image_output_requests":0,"num_video_prompt":0,"video_output_seconds":0,"rerank_documents":0,"stt_transcript_characters":0}},"categories":{"deepseek/deepseek-v4-flash-20260731":[{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"academia","count":11122,"total_prompt_tokens":125797327,"total_completion_tokens":7866688,"volume":9.266183,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"finance","count":15461,"total_prompt_tokens":541518216,"total_completion_tokens":18093062,"volume":20.491202,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"health","count":6173,"total_prompt_tokens":57753798,"total_completion_tokens":6017689,"volume":5.415431,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"legal","count":12274,"total_prompt_tokens":68668829,"total_completion_tokens":7855489,"volume":6.481849,"rank":3},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"marketing","count":8555,"total_prompt_tokens":83156929,"total_completion_tokens":5982946,"volume":7.003327,"rank":2},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"marketing/seo","count":1044,"total_prompt_tokens":20158900,"total_completion_tokens":2093299,"volume":1.450296,"rank":3},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"programming","count":128439,"total_prompt_tokens":7349510711,"total_completion_tokens":104869152,"volume":432.256014,"rank":2},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"roleplay","count":99008,"total_prompt_tokens":664403430,"total_completion_tokens":40808283,"volume":50.042874,"rank":2},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"science","count":61487,"total_prompt_tokens":2615443468,"total_completion_tokens":98923910,"volume":133.947192,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"technology","count":81797,"total_prompt_tokens":3309800896,"total_completion_tokens":66645033,"volume":160.387046,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"translation","count":32141,"total_prompt_tokens":83542699,"total_completion_tokens":11439073,"volume":7.158648,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260731","category":"trivia","count":1448,"total_prompt_tokens":15982660,"total_completion_tokens":896577,"volume":1.076786,"rank":1}],"deepseek/deepseek-v4-flash-20260423":[{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"academia","count":14289,"total_prompt_tokens":93506600,"total_completion_tokens":11170898,"volume":9.575688,"rank":2},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"finance","count":12310,"total_prompt_tokens":114274707,"total_completion_tokens":9978672,"volume":8.080028,"rank":3},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"health","count":7858,"total_prompt_tokens":39669012,"total_completion_tokens":4900135,"volume":4.058373,"rank":3},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"legal","count":6276,"total_prompt_tokens":39207967,"total_completion_tokens":4242879,"volume":3.707541,"rank":4},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"marketing","count":7327,"total_prompt_tokens":91617549,"total_completion_tokens":4003932,"volume":7.843237,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"marketing/seo","count":8572,"total_prompt_tokens":42494039,"total_completion_tokens":24965140,"volume":9.513698,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"programming","count":42654,"total_prompt_tokens":1442387238,"total_completion_tokens":41203649,"volume":59.778934,"rank":6},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"roleplay","count":559117,"total_prompt_tokens":2262600795,"total_completion_tokens":111550930,"volume":101.80011,"rank":1},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"science","count":36003,"total_prompt_tokens":1225341604,"total_completion_tokens":68904230,"volume":56.189194,"rank":3},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"technology","count":89893,"total_prompt_tokens":1732895648,"total_completion_tokens":60195695,"volume":101.053203,"rank":4},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"translation","count":31886,"total_prompt_tokens":62164388,"total_completion_tokens":11453732,"volume":6.572639,"rank":2},{"date":"2026-08-23","model":"deepseek/deepseek-v4-flash-20260423","category":"trivia","count":3014,"total_prompt_tokens":13146184,"total_completion_tokens":930494,"volume":0.82266,"rank":2}],"openai/gpt-5.6-luna-20260709":[{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"academia","count":5695,"total_prompt_tokens":57197100,"total_completion_tokens":4774895,"volume":12.354709,"rank":3},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"finance","count":8169,"total_prompt_tokens":83482853,"total_completion_tokens":2121103,"volume":11.807429,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"health","count":5082,"total_prompt_tokens":35783231,"total_completion_tokens":1911297,"volume":7.348372,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"legal","count":13830,"total_prompt_tokens":78520899,"total_completion_tokens":3112939,"volume":12.343469,"rank":2},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"marketing","count":3112,"total_prompt_tokens":35635763,"total_completion_tokens":1363163,"volume":7.612175,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"marketing/seo","count":654,"total_prompt_tokens":14481268,"total_completion_tokens":537295,"volume":3.725926,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"programming","count":53563,"total_prompt_tokens":3458419390,"total_completion_tokens":17632243,"volume":163.035518,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"roleplay","count":70955,"total_prompt_tokens":77045996,"total_completion_tokens":21485559,"volume":37.406064,"rank":13},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"science","count":24774,"total_prompt_tokens":978399380,"total_completion_tokens":11632710,"volume":65.616715,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"technology","count":54363,"total_prompt_tokens":2019170824,"total_completion_tokens":15946376,"volume":164.517355,"rank":3},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"translation","count":78390,"total_prompt_tokens":48625920,"total_completion_tokens":22447644,"volume":31.572238,"rank":3},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-20260709","category":"trivia","count":1162,"total_prompt_tokens":3715460,"total_completion_tokens":121653,"volume":0.75261,"rank":5}],"openai/gpt-5-mini-2025-08-07":[{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"academia","count":3604,"total_prompt_tokens":47024948,"total_completion_tokens":955809,"volume":8.822437,"rank":4},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"finance","count":3357,"total_prompt_tokens":34784867,"total_completion_tokens":790945,"volume":7.252219,"rank":13},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"health","count":1458,"total_prompt_tokens":14587855,"total_completion_tokens":701304,"volume":4.260631,"rank":10},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"legal","count":9484,"total_prompt_tokens":118486067,"total_completion_tokens":1853620,"volume":21.849907,"rank":1},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"marketing","count":1128,"total_prompt_tokens":4038679,"total_completion_tokens":204375,"volume":1.397074,"rank":30},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"marketing/seo","count":330,"total_prompt_tokens":2790624,"total_completion_tokens":211137,"volume":1.404865,"rank":15},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"science","count":4924,"total_prompt_tokens":27059412,"total_completion_tokens":1250742,"volume":7.984431,"rank":39},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"technology","count":7534,"total_prompt_tokens":76294276,"total_completion_tokens":2559377,"volume":22.083441,"rank":37},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"translation","count":1567,"total_prompt_tokens":1226143,"total_completion_tokens":320429,"volume":1.344797,"rank":44},{"date":"2026-08-23","model":"openai/gpt-5-mini-2025-08-07","category":"trivia","count":303,"total_prompt_tokens":344150,"total_completion_tokens":33500,"volume":0.33212,"rank":41}],"tencent/hy3-20260706":[{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"academia","count":573,"total_prompt_tokens":41380727,"total_completion_tokens":960174,"volume":0.220763,"rank":5},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"finance","count":946,"total_prompt_tokens":47416807,"total_completion_tokens":1212585,"volume":0.449308,"rank":9},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"health","count":276,"total_prompt_tokens":4336700,"total_completion_tokens":234400,"volume":0.040684,"rank":23},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"legal","count":157,"total_prompt_tokens":7466900,"total_completion_tokens":366200,"volume":0.158024,"rank":18},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"marketing","count":531,"total_prompt_tokens":31918907,"total_completion_tokens":840152,"volume":0.167557,"rank":5},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"marketing/seo","count":65,"total_prompt_tokens":4233900,"total_completion_tokens":79900,"volume":0.041,"rank":11},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"programming","count":45843,"total_prompt_tokens":2600479064,"total_completion_tokens":45405863,"volume":22.385228,"rank":5},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"roleplay","count":1070,"total_prompt_tokens":41453995,"total_completion_tokens":1508130,"volume":0.625306,"rank":20},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"science","count":23350,"total_prompt_tokens":1578964999,"total_completion_tokens":24175207,"volume":4.602157,"rank":2},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"technology","count":33759,"total_prompt_tokens":2060530928,"total_completion_tokens":31404268,"volume":9.374208,"rank":2},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"translation","count":526,"total_prompt_tokens":3781250,"total_completion_tokens":712150,"volume":0.21927,"rank":25},{"date":"2026-08-23","model":"tencent/hy3-20260706","category":"trivia","count":62,"total_prompt_tokens":1576180,"total_completion_tokens":59854,"volume":0.023359,"rank":15}],"google/gemini-3.7-flash-20260813":[{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"academia","count":5211,"total_prompt_tokens":29309220,"total_completion_tokens":4883915,"volume":15.932113,"rank":6},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"finance","count":3613,"total_prompt_tokens":34107889,"total_completion_tokens":1336197,"volume":12.560158,"rank":14},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"health","count":1618,"total_prompt_tokens":11143539,"total_completion_tokens":682086,"volume":5.73013,"rank":13},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"legal","count":1341,"total_prompt_tokens":15339974,"total_completion_tokens":1000881,"volume":7.60316,"rank":10},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"marketing","count":3689,"total_prompt_tokens":27285335,"total_completion_tokens":1451296,"volume":17.750834,"rank":6},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"marketing/seo","count":487,"total_prompt_tokens":4016365,"total_completion_tokens":232445,"volume":1.420596,"rank":12},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"programming","count":16805,"total_prompt_tokens":999437107,"total_completion_tokens":8261375,"volume":124.973357,"rank":9},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"roleplay","count":6235,"total_prompt_tokens":144526046,"total_completion_tokens":5048747,"volume":39.186231,"rank":12},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"science","count":9589,"total_prompt_tokens":339954691,"total_completion_tokens":3273685,"volume":52.525742,"rank":9},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"technology","count":19024,"total_prompt_tokens":1067312760,"total_completion_tokens":8418027,"volume":137.902264,"rank":7},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"translation","count":4807,"total_prompt_tokens":11877711,"total_completion_tokens":3859061,"volume":10.727507,"rank":11},{"date":"2026-08-23","model":"google/gemini-3.7-flash-20260813","category":"trivia","count":398,"total_prompt_tokens":1517845,"total_completion_tokens":108058,"volume":0.67946,"rank":16}],"z-ai/glm-5.2-20260616":[{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"academia","count":2397,"total_prompt_tokens":29727169,"total_completion_tokens":2539430,"volume":21.147076,"rank":7},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"finance","count":4889,"total_prompt_tokens":63078294,"total_completion_tokens":3962788,"volume":25.508508,"rank":5},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"health","count":2307,"total_prompt_tokens":53749291,"total_completion_tokens":1835648,"volume":16.346393,"rank":2},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"legal","count":1520,"total_prompt_tokens":17113328,"total_completion_tokens":1112367,"volume":11.475327,"rank":9},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"marketing","count":693,"total_prompt_tokens":14476845,"total_completion_tokens":1087158,"volume":7.031583,"rank":13},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"marketing/seo","count":114,"total_prompt_tokens":4644134,"total_completion_tokens":123953,"volume":1.209383,"rank":10},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"programming","count":55162,"total_prompt_tokens":3869074539,"total_completion_tokens":52870593,"volume":964.996534,"rank":3},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"roleplay","count":10309,"total_prompt_tokens":192582693,"total_completion_tokens":7926991,"volume":94.74762,"rank":11},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"science","count":7555,"total_prompt_tokens":365959292,"total_completion_tokens":7852844,"volume":121.796345,"rank":7},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"technology","count":28173,"total_prompt_tokens":1578570092,"total_completion_tokens":27753144,"volume":406.318641,"rank":6},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"translation","count":790,"total_prompt_tokens":4370321,"total_completion_tokens":479472,"volume":2.990654,"rank":23},{"date":"2026-08-23","model":"z-ai/glm-5.2-20260616","category":"trivia","count":609,"total_prompt_tokens":10723077,"total_completion_tokens":880603,"volume":7.785444,"rank":3}],"xiaomi/mimo-v2.5-20260422":[{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"academia","count":1475,"total_prompt_tokens":30089784,"total_completion_tokens":1444893,"volume":0.711742,"rank":8},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"finance","count":1319,"total_prompt_tokens":59367189,"total_completion_tokens":1251237,"volume":1.845413,"rank":6},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"health","count":776,"total_prompt_tokens":12208199,"total_completion_tokens":708054,"volume":0.451283,"rank":12},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"legal","count":200,"total_prompt_tokens":3049900,"total_completion_tokens":236700,"volume":0.075711,"rank":39},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"marketing","count":756,"total_prompt_tokens":10477710,"total_completion_tokens":368602,"volume":0.474429,"rank":20},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"marketing/seo","count":49,"total_prompt_tokens":1050086,"total_completion_tokens":86456,"volume":0.028414,"rank":28},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"programming","count":197926,"total_prompt_tokens":15710547064,"total_completion_tokens":92757696,"volume":40.909367,"rank":1},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"roleplay","count":15776,"total_prompt_tokens":582858931,"total_completion_tokens":13634916,"volume":14.789868,"rank":3},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"science","count":8772,"total_prompt_tokens":651906412,"total_completion_tokens":5827826,"volume":2.212896,"rank":5},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"technology","count":15654,"total_prompt_tokens":763737212,"total_completion_tokens":8811833,"volume":4.711542,"rank":9},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"translation","count":2373,"total_prompt_tokens":5771641,"total_completion_tokens":1198540,"volume":0.147097,"rank":18},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-20260422","category":"trivia","count":137,"total_prompt_tokens":7017980,"total_completion_tokens":108980,"volume":0.056805,"rank":4}],"moonshotai/kimi-k3-20260715":[{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"academia","count":565,"total_prompt_tokens":26860883,"total_completion_tokens":1310915,"volume":39.905889,"rank":9},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"finance","count":725,"total_prompt_tokens":20602598,"total_completion_tokens":1106060,"volume":35.872503,"rank":20},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"health","count":486,"total_prompt_tokens":4790081,"total_completion_tokens":935347,"volume":17.899794,"rank":17},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"legal","count":202,"total_prompt_tokens":4135897,"total_completion_tokens":340668,"volume":9.816121,"rank":32},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"marketing","count":93,"total_prompt_tokens":2642594,"total_completion_tokens":122227,"volume":4.524816,"rank":36},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"marketing/seo","count":10,"total_prompt_tokens":362612,"total_completion_tokens":23820,"volume":0.888749,"rank":41},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"programming","count":12293,"total_prompt_tokens":971595705,"total_completion_tokens":10938350,"volume":940.647776,"rank":10},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"roleplay","count":586,"total_prompt_tokens":14022382,"total_completion_tokens":796303,"volume":29.643022,"rank":47},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"science","count":3230,"total_prompt_tokens":174288321,"total_completion_tokens":6417931,"volume":218.34485,"rank":13},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"technology","count":6573,"total_prompt_tokens":370145366,"total_completion_tokens":6177500,"volume":411.010721,"rank":14},{"date":"2026-08-23","model":"moonshotai/kimi-k3-20260715","category":"trivia","count":194,"total_prompt_tokens":308070,"total_completion_tokens":185916,"volume":2.619374,"rank":30}],"google/gemini-2.5-flash-lite":[{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"academia","count":6503,"total_prompt_tokens":23059506,"total_completion_tokens":4136677,"volume":2.873131,"rank":10},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"finance","count":17980,"total_prompt_tokens":34750516,"total_completion_tokens":2083150,"volume":4.640306,"rank":11},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"health","count":8401,"total_prompt_tokens":17149956,"total_completion_tokens":3165490,"volume":3.139261,"rank":7},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"legal","count":5822,"total_prompt_tokens":20622649,"total_completion_tokens":1350302,"volume":2.385616,"rank":7},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"marketing","count":8841,"total_prompt_tokens":22373110,"total_completion_tokens":2209900,"volume":2.711468,"rank":7},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"marketing/seo","count":2400,"total_prompt_tokens":4736925,"total_completion_tokens":2448944,"volume":1.239463,"rank":7},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"programming","count":11734,"total_prompt_tokens":37171724,"total_completion_tokens":1841047,"volume":2.935248,"rank":49},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"roleplay","count":77690,"total_prompt_tokens":366261372,"total_completion_tokens":13878636,"volume":27.096995,"rank":5},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"science","count":13079,"total_prompt_tokens":32301756,"total_completion_tokens":2723471,"volume":3.953479,"rank":34},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"technology","count":30479,"total_prompt_tokens":120908005,"total_completion_tokens":16752746,"volume":12.432975,"rank":29},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"translation","count":26683,"total_prompt_tokens":12820207,"total_completion_tokens":4067326,"volume":2.698613,"rank":9},{"date":"2026-08-23","model":"google/gemini-2.5-flash-lite","category":"trivia","count":1284,"total_prompt_tokens":1552054,"total_completion_tokens":105942,"volume":0.190405,"rank":14}],"deepseek/deepseek-v4-pro-20260423":[{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"academia","count":918,"total_prompt_tokens":21332243,"total_completion_tokens":2973282,"volume":13.62348,"rank":11},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"finance","count":3917,"total_prompt_tokens":38874089,"total_completion_tokens":4845722,"volume":22.871459,"rank":10},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"health","count":497,"total_prompt_tokens":4124892,"total_completion_tokens":648832,"volume":3.324148,"rank":21},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"legal","count":498,"total_prompt_tokens":5261368,"total_completion_tokens":820500,"volume":4.458837,"rank":24},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"marketing","count":666,"total_prompt_tokens":10477205,"total_completion_tokens":1057563,"volume":5.682721,"rank":18},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"marketing/seo","count":159,"total_prompt_tokens":3368643,"total_completion_tokens":435173,"volume":1.416668,"rank":13},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"programming","count":20324,"total_prompt_tokens":1096856226,"total_completion_tokens":39704257,"volume":382.469179,"rank":7},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"roleplay","count":34311,"total_prompt_tokens":325255992,"total_completion_tokens":17366094,"volume":106.477444,"rank":6},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"science","count":6145,"total_prompt_tokens":356906950,"total_completion_tokens":6970646,"volume":67.763648,"rank":8},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"technology","count":26918,"total_prompt_tokens":909010982,"total_completion_tokens":68203387,"volume":534.355997,"rank":8},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"translation","count":1333,"total_prompt_tokens":4234881,"total_completion_tokens":1274815,"volume":5.044601,"rank":19},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260423","category":"trivia","count":550,"total_prompt_tokens":2716584,"total_completion_tokens":179618,"volume":0.657648,"rank":6}],"openai/gpt-oss-120b":[{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"academia","count":7132,"total_prompt_tokens":18556815,"total_completion_tokens":3001309,"volume":2.125506,"rank":12},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"finance","count":5651,"total_prompt_tokens":14521271,"total_completion_tokens":3432969,"volume":3.202221,"rank":22},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"health","count":4070,"total_prompt_tokens":20790678,"total_completion_tokens":2284529,"volume":2.824199,"rank":5},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"legal","count":5451,"total_prompt_tokens":25721937,"total_completion_tokens":6321348,"volume":3.156469,"rank":5},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"marketing","count":8916,"total_prompt_tokens":38648582,"total_completion_tokens":4621927,"volume":4.649529,"rank":3},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"marketing/seo","count":18117,"total_prompt_tokens":49340251,"total_completion_tokens":9876833,"volume":4.057377,"rank":2},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"roleplay","count":11872,"total_prompt_tokens":52776899,"total_completion_tokens":9554088,"volume":5.289824,"rank":15},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"science","count":4988,"total_prompt_tokens":19519932,"total_completion_tokens":4374010,"volume":2.21812,"rank":41},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"technology","count":18249,"total_prompt_tokens":82316594,"total_completion_tokens":12124793,"volume":10.743667,"rank":34},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"translation","count":2076,"total_prompt_tokens":3053594,"total_completion_tokens":1650654,"volume":0.831381,"rank":24},{"date":"2026-08-23","model":"openai/gpt-oss-120b","category":"trivia","count":170,"total_prompt_tokens":312400,"total_completion_tokens":32000,"volume":0.037278,"rank":46}],"google/gemma-4-26b-a4b-it-20260403":[{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"academia","count":2268,"total_prompt_tokens":20081342,"total_completion_tokens":676429,"volume":1.339898,"rank":13},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"finance","count":1384,"total_prompt_tokens":3463187,"total_completion_tokens":187894,"volume":0.451481,"rank":49},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"health","count":880,"total_prompt_tokens":7773653,"total_completion_tokens":519974,"volume":0.789499,"rank":15},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"legal","count":2038,"total_prompt_tokens":8220303,"total_completion_tokens":228586,"volume":0.746585,"rank":15},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"marketing","count":2360,"total_prompt_tokens":8823791,"total_completion_tokens":419047,"volume":0.253068,"rank":22},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"programming","count":5650,"total_prompt_tokens":79496927,"total_completion_tokens":2387122,"volume":4.102793,"rank":34},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"roleplay","count":35980,"total_prompt_tokens":219855998,"total_completion_tokens":16396386,"volume":19.813907,"rank":9},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"science","count":10392,"total_prompt_tokens":46118542,"total_completion_tokens":1391602,"volume":3.883483,"rank":28},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"translation","count":11493,"total_prompt_tokens":13669047,"total_completion_tokens":2509376,"volume":1.751883,"rank":10},{"date":"2026-08-23","model":"google/gemma-4-26b-a4b-it-20260403","category":"trivia","count":835,"total_prompt_tokens":1314806,"total_completion_tokens":157141,"volume":0.116358,"rank":17}],"anthropic/claude-opus-5-20260723":[{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"academia","count":564,"total_prompt_tokens":19567065,"total_completion_tokens":590660,"volume":78.12394,"rank":14},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"finance","count":904,"total_prompt_tokens":29727993,"total_completion_tokens":437397,"volume":97.986038,"rank":16},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"health","count":158,"total_prompt_tokens":2447128,"total_completion_tokens":153121,"volume":19.605379,"rank":37},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"legal","count":233,"total_prompt_tokens":2124119,"total_completion_tokens":126188,"volume":14.491847,"rank":47},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"marketing","count":328,"total_prompt_tokens":16324920,"total_completion_tokens":244177,"volume":19.797687,"rank":10},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"marketing/seo","count":28,"total_prompt_tokens":385550,"total_completion_tokens":38832,"volume":3.904216,"rank":37},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"programming","count":7132,"total_prompt_tokens":469048871,"total_completion_tokens":11452495,"volume":1600.305313,"rank":16},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"roleplay","count":573,"total_prompt_tokens":14499856,"total_completion_tokens":497769,"volume":80.748755,"rank":45},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"science","count":1691,"total_prompt_tokens":86658234,"total_completion_tokens":4186275,"volume":408.729971,"rank":17},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"technology","count":4459,"total_prompt_tokens":225360069,"total_completion_tokens":2936154,"volume":622.684412,"rank":23},{"date":"2026-08-23","model":"anthropic/claude-opus-5-20260723","category":"trivia","count":341,"total_prompt_tokens":470140,"total_completion_tokens":40843,"volume":3.302865,"rank":29}],"google/gemini-3.1-flash-lite-20260507":[{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"academia","count":4907,"total_prompt_tokens":17003562,"total_completion_tokens":1901051,"volume":3.893821,"rank":15},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"finance","count":2772,"total_prompt_tokens":18246773,"total_completion_tokens":761165,"volume":4.269411,"rank":21},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"health","count":5656,"total_prompt_tokens":19786745,"total_completion_tokens":1092638,"volume":5.78182,"rank":6},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"legal","count":1528,"total_prompt_tokens":5588587,"total_completion_tokens":461216,"volume":2.137938,"rank":25},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"marketing","count":2811,"total_prompt_tokens":12235977,"total_completion_tokens":902370,"volume":4.475181,"rank":17},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"marketing/seo","count":586,"total_prompt_tokens":1058663,"total_completion_tokens":159999,"volume":0.450318,"rank":26},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"programming","count":7734,"total_prompt_tokens":38875061,"total_completion_tokens":944732,"volume":7.659406,"rank":47},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"roleplay","count":6710,"total_prompt_tokens":27839557,"total_completion_tokens":1382135,"volume":6.047032,"rank":24},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"science","count":9535,"total_prompt_tokens":48268999,"total_completion_tokens":1197626,"volume":9.708694,"rank":27},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"technology","count":18085,"total_prompt_tokens":108637680,"total_completion_tokens":4136559,"volume":21.969928,"rank":31},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"translation","count":9691,"total_prompt_tokens":17377727,"total_completion_tokens":1754740,"volume":6.242086,"rank":7},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-20260507","category":"trivia","count":529,"total_prompt_tokens":1034929,"total_completion_tokens":43628,"volume":0.278135,"rank":20}],"google/gemma-4-31b-it-20260402":[{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"academia","count":1899,"total_prompt_tokens":16978262,"total_completion_tokens":716342,"volume":2.787696,"rank":16},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"finance","count":1410,"total_prompt_tokens":7691284,"total_completion_tokens":383413,"volume":1.972512,"rank":33},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"health","count":1454,"total_prompt_tokens":5050079,"total_completion_tokens":466606,"volume":1.815669,"rank":19},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"legal","count":1990,"total_prompt_tokens":7382443,"total_completion_tokens":1190846,"volume":0.80753,"rank":14},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"marketing","count":2526,"total_prompt_tokens":15042496,"total_completion_tokens":607424,"volume":5.064064,"rank":12},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"roleplay","count":23437,"total_prompt_tokens":228328871,"total_completion_tokens":11612213,"volume":25.135312,"rank":8},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"science","count":4880,"total_prompt_tokens":36863046,"total_completion_tokens":2113556,"volume":6.625732,"rank":31},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"technology","count":8345,"total_prompt_tokens":40040394,"total_completion_tokens":2413899,"volume":8.753112,"rank":49},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"translation","count":12875,"total_prompt_tokens":17698126,"total_completion_tokens":2362491,"volume":4.801706,"rank":6},{"date":"2026-08-23","model":"google/gemma-4-31b-it-20260402","category":"trivia","count":2446,"total_prompt_tokens":2249249,"total_completion_tokens":106958,"volume":0.269154,"rank":11}],"qwen/qwen3.8-max-20260803":[{"date":"2026-08-23","model":"qwen/qwen3.8-max-20260803","category":"academia","count":191,"total_prompt_tokens":15135089,"total_completion_tokens":401496,"volume":3.875852,"rank":17},{"date":"2026-08-23","model":"qwen/qwen3.8-max-20260803","category":"finance","count":293,"total_prompt_tokens":10409200,"total_completion_tokens":545700,"volume":10.522524,"rank":30},{"date":"2026-08-23","model":"qwen/qwen3.8-max-20260803","category":"programming","count":3712,"total_prompt_tokens":220889928,"total_completion_tokens":6628908,"volume":155.086175,"rank":23},{"date":"2026-08-23","model":"qwen/qwen3.8-max-20260803","category":"science","count":866,"total_prompt_tokens":61851166,"total_completion_tokens":1766672,"volume":47.319156,"rank":23},{"date":"2026-08-23","model":"qwen/qwen3.8-max-20260803","category":"technology","count":2310,"total_prompt_tokens":141493609,"total_completion_tokens":3701836,"volume":85.926912,"rank":27},{"date":"2026-08-23","model":"qwen/qwen3.8-max-20260803","category":"trivia","count":112,"total_prompt_tokens":258741,"total_completion_tokens":94787,"volume":0.601949,"rank":45}],"google/gemini-3-flash-preview-20251217":[{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"academia","count":2721,"total_prompt_tokens":13131710,"total_completion_tokens":1120979,"volume":7.674529,"rank":18},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"finance","count":5132,"total_prompt_tokens":150508248,"total_completion_tokens":1568553,"volume":80.944791,"rank":2},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"health","count":3174,"total_prompt_tokens":16469592,"total_completion_tokens":875997,"volume":8.246557,"rank":8},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"legal","count":1866,"total_prompt_tokens":30614906,"total_completion_tokens":643684,"volume":12.918171,"rank":6},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"marketing","count":2928,"total_prompt_tokens":16360551,"total_completion_tokens":1247824,"volume":7.651138,"rank":9},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"marketing/seo","count":996,"total_prompt_tokens":2195799,"total_completion_tokens":268048,"volume":2.109185,"rank":16},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"programming","count":4672,"total_prompt_tokens":95069979,"total_completion_tokens":1598443,"volume":29.873832,"rank":32},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"roleplay","count":25656,"total_prompt_tokens":211836885,"total_completion_tokens":7776528,"volume":69.869338,"rank":10},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"science","count":7546,"total_prompt_tokens":84649599,"total_completion_tokens":3050408,"volume":49.294065,"rank":19},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"technology","count":20732,"total_prompt_tokens":303672208,"total_completion_tokens":6380929,"volume":122.201807,"rank":18},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"translation","count":4705,"total_prompt_tokens":8344103,"total_completion_tokens":1330392,"volume":6.859152,"rank":15},{"date":"2026-08-23","model":"google/gemini-3-flash-preview-20251217","category":"trivia","count":1401,"total_prompt_tokens":2630351,"total_completion_tokens":187487,"volume":2.075857,"rank":7}],"google/gemini-2.5-flash":[{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"academia","count":4167,"total_prompt_tokens":10967071,"total_completion_tokens":1969676,"volume":7.038875,"rank":19},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"finance","count":6314,"total_prompt_tokens":26569796,"total_completion_tokens":2239103,"volume":12.197512,"rank":17},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"health","count":3344,"total_prompt_tokens":9496048,"total_completion_tokens":872472,"volume":5.1032,"rank":14},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"legal","count":2040,"total_prompt_tokens":6660171,"total_completion_tokens":686406,"volume":4.299386,"rank":20},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"marketing","count":4060,"total_prompt_tokens":13713053,"total_completion_tokens":1356082,"volume":5.988409,"rank":14},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"marketing/seo","count":498,"total_prompt_tokens":1728878,"total_completion_tokens":518336,"volume":1.570127,"rank":17},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"roleplay","count":7421,"total_prompt_tokens":45747212,"total_completion_tokens":2092043,"volume":10.243392,"rank":18},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"science","count":7254,"total_prompt_tokens":38047185,"total_completion_tokens":1603854,"volume":10.47154,"rank":30},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"technology","count":42828,"total_prompt_tokens":132800992,"total_completion_tokens":9893702,"volume":53.111429,"rank":28},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"translation","count":5991,"total_prompt_tokens":9442245,"total_completion_tokens":1224763,"volume":5.978718,"rank":14},{"date":"2026-08-23","model":"google/gemini-2.5-flash","category":"trivia","count":914,"total_prompt_tokens":2201962,"total_completion_tokens":214089,"volume":0.80378,"rank":10}],"openai/gpt-5.6-sol-20260709":[{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"academia","count":581,"total_prompt_tokens":12464456,"total_completion_tokens":256745,"volume":22.062794,"rank":20},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"finance","count":462,"total_prompt_tokens":15454648,"total_completion_tokens":307662,"volume":29.167103,"rank":25},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"health","count":560,"total_prompt_tokens":6604355,"total_completion_tokens":131496,"volume":10.130439,"rank":16},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"legal","count":834,"total_prompt_tokens":13017654,"total_completion_tokens":192393,"volume":12.220553,"rank":13},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"marketing","count":118,"total_prompt_tokens":2273241,"total_completion_tokens":64249,"volume":3.418057,"rank":39},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"marketing/seo","count":18,"total_prompt_tokens":242300,"total_completion_tokens":15050,"volume":0.511258,"rank":50},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"programming","count":7644,"total_prompt_tokens":529103979,"total_completion_tokens":3033941,"volume":510.368739,"rank":15},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"roleplay","count":502,"total_prompt_tokens":15593046,"total_completion_tokens":309674,"volume":34.890147,"rank":42},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"science","count":5393,"total_prompt_tokens":159060130,"total_completion_tokens":2796357,"volume":317.218673,"rank":14},{"date":"2026-08-23","model":"openai/gpt-5.6-sol-20260709","category":"technology","count":8669,"total_prompt_tokens":326471166,"total_completion_tokens":4123015,"volume":414.290201,"rank":16}],"anthropic/claude-4.6-sonnet-20260217":[{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"academia","count":928,"total_prompt_tokens":11261986,"total_completion_tokens":475687,"volume":23.24468,"rank":21},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"finance","count":1433,"total_prompt_tokens":33297974,"total_completion_tokens":522175,"volume":45.824778,"rank":15},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"health","count":2517,"total_prompt_tokens":14008907,"total_completion_tokens":3203337,"volume":76.058444,"rank":9},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"legal","count":436,"total_prompt_tokens":4417372,"total_completion_tokens":177035,"volume":11.697906,"rank":31},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"marketing","count":1248,"total_prompt_tokens":15453638,"total_completion_tokens":474021,"volume":24.988797,"rank":11},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"marketing/seo","count":350,"total_prompt_tokens":1628654,"total_completion_tokens":206614,"volume":7.913576,"rank":20},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"programming","count":3124,"total_prompt_tokens":101002204,"total_completion_tokens":1027118,"volume":92.57938,"rank":31},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"roleplay","count":2113,"total_prompt_tokens":21139235,"total_completion_tokens":796883,"volume":51.191151,"rank":33},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"science","count":6133,"total_prompt_tokens":50172756,"total_completion_tokens":1650473,"volume":84.117671,"rank":26},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"technology","count":10298,"total_prompt_tokens":301794284,"total_completion_tokens":3290149,"volume":226.06118,"rank":19},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"translation","count":1212,"total_prompt_tokens":3341787,"total_completion_tokens":216806,"volume":11.569722,"rank":30},{"date":"2026-08-23","model":"anthropic/claude-4.6-sonnet-20260217","category":"trivia","count":1103,"total_prompt_tokens":2200200,"total_completion_tokens":222239,"volume":9.552989,"rank":9}],"qwen/qwen3.7-plus-20260602":[{"date":"2026-08-23","model":"qwen/qwen3.7-plus-20260602","category":"academia","count":1082,"total_prompt_tokens":9184941,"total_completion_tokens":1428221,"volume":3.559792,"rank":22},{"date":"2026-08-23","model":"qwen/qwen3.7-plus-20260602","category":"finance","count":225,"total_prompt_tokens":3951038,"total_completion_tokens":333237,"volume":1.715544,"rank":46},{"date":"2026-08-23","model":"qwen/qwen3.7-plus-20260602","category":"health","count":472,"total_prompt_tokens":2368362,"total_completion_tokens":412845,"volume":1.116728,"rank":32},{"date":"2026-08-23","model":"qwen/qwen3.7-plus-20260602","category":"marketing","count":165,"total_prompt_tokens":1373650,"total_completion_tokens":72228,"volume":0.294217,"rank":47},{"date":"2026-08-23","model":"qwen/qwen3.7-plus-20260602","category":"science","count":915,"total_prompt_tokens":20678917,"total_completion_tokens":973691,"volume":3.746994,"rank":46},{"date":"2026-08-23","model":"qwen/qwen3.7-plus-20260602","category":"trivia","count":4467,"total_prompt_tokens":2399351,"total_completion_tokens":90000,"volume":0.892869,"rank":8}],"anthropic/claude-sonnet-5-20260630":[{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"academia","count":942,"total_prompt_tokens":8661344,"total_completion_tokens":432153,"volume":22.833429,"rank":23},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"finance","count":1630,"total_prompt_tokens":57468685,"total_completion_tokens":589707,"volume":54.252359,"rank":7},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"health","count":653,"total_prompt_tokens":4504902,"total_completion_tokens":222551,"volume":12.389594,"rank":22},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"legal","count":443,"total_prompt_tokens":5791112,"total_completion_tokens":295638,"volume":13.45839,"rank":23},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"marketing","count":542,"total_prompt_tokens":11146516,"total_completion_tokens":208331,"volume":20.276804,"rank":19},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"marketing/seo","count":219,"total_prompt_tokens":2003944,"total_completion_tokens":228951,"volume":4.160838,"rank":18},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"programming","count":5543,"total_prompt_tokens":334190921,"total_completion_tokens":2034894,"volume":268.354629,"rank":20},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"roleplay","count":1075,"total_prompt_tokens":15779860,"total_completion_tokens":490377,"volume":32.655231,"rank":40},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"science","count":2575,"total_prompt_tokens":108111281,"total_completion_tokens":1339389,"volume":127.333994,"rank":16},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"technology","count":6647,"total_prompt_tokens":409932895,"total_completion_tokens":2352939,"volume":236.561754,"rank":13},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"translation","count":794,"total_prompt_tokens":3857922,"total_completion_tokens":343080,"volume":16.123826,"rank":27},{"date":"2026-08-23","model":"anthropic/claude-sonnet-5-20260630","category":"trivia","count":210,"total_prompt_tokens":689475,"total_completion_tokens":18322,"volume":1.561588,"rank":24}],"qwen/qwen3.7-flash-20260727":[{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"academia","count":1589,"total_prompt_tokens":5902275,"total_completion_tokens":2603973,"volume":0.625085,"rank":24},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"finance","count":1105,"total_prompt_tokens":6927358,"total_completion_tokens":963152,"volume":0.551768,"rank":34},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"legal","count":1183,"total_prompt_tokens":5872851,"total_completion_tokens":874865,"volume":0.388673,"rank":22},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"marketing","count":676,"total_prompt_tokens":5962580,"total_completion_tokens":705542,"volume":0.407398,"rank":25},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"marketing/seo","count":909,"total_prompt_tokens":2752918,"total_completion_tokens":2085883,"volume":0.327346,"rank":8},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"programming","count":1739,"total_prompt_tokens":38601122,"total_completion_tokens":1538743,"volume":2.430516,"rank":46},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"roleplay","count":3539,"total_prompt_tokens":15283747,"total_completion_tokens":3118211,"volume":0.812281,"rank":35},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"science","count":2898,"total_prompt_tokens":29621049,"total_completion_tokens":2473093,"volume":2.05595,"rank":35},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"translation","count":9595,"total_prompt_tokens":26490389,"total_completion_tokens":1117517,"volume":0.561747,"rank":5},{"date":"2026-08-23","model":"qwen/qwen3.7-flash-20260727","category":"trivia","count":101,"total_prompt_tokens":833658,"total_completion_tokens":61397,"volume":0.122619,"rank":21}],"openai/gpt-5.6-terra-20260709":[{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"academia","count":630,"total_prompt_tokens":7644914,"total_completion_tokens":215919,"volume":8.631934,"rank":25},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"finance","count":900,"total_prompt_tokens":6012685,"total_completion_tokens":225803,"volume":8.271247,"rank":39},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"health","count":311,"total_prompt_tokens":2893105,"total_completion_tokens":104035,"volume":4.095978,"rank":27},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"legal","count":420,"total_prompt_tokens":3492638,"total_completion_tokens":140733,"volume":5.211328,"rank":38},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"marketing","count":428,"total_prompt_tokens":13049537,"total_completion_tokens":108969,"volume":6.289096,"rank":16},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"marketing/seo","count":264,"total_prompt_tokens":14492629,"total_completion_tokens":130274,"volume":4.664815,"rank":5},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"programming","count":4374,"total_prompt_tokens":233608614,"total_completion_tokens":1728194,"volume":143.857777,"rank":22},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"science","count":2043,"total_prompt_tokens":54234736,"total_completion_tokens":698406,"volume":47.852498,"rank":25},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"technology","count":4554,"total_prompt_tokens":190329416,"total_completion_tokens":1605617,"volume":107.722244,"rank":24},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"translation","count":3301,"total_prompt_tokens":3780449,"total_completion_tokens":1239636,"volume":16.964963,"rank":22},{"date":"2026-08-23","model":"openai/gpt-5.6-terra-20260709","category":"trivia","count":94,"total_prompt_tokens":343972,"total_completion_tokens":10303,"volume":0.410295,"rank":44}],"upstage/solar-pro4-20260810":[{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"academia","count":204,"total_prompt_tokens":7434571,"total_completion_tokens":277573,"volume":0.053019,"rank":26},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"finance","count":438,"total_prompt_tokens":6888800,"total_completion_tokens":227850,"volume":0.114452,"rank":36},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"marketing","count":32,"total_prompt_tokens":1720650,"total_completion_tokens":13550,"volume":0.002815,"rank":42},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"marketing/seo","count":25,"total_prompt_tokens":369700,"total_completion_tokens":4000,"volume":0.000796,"rank":43},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"programming","count":1448,"total_prompt_tokens":40350818,"total_completion_tokens":325872,"volume":0.423042,"rank":45},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"science","count":5876,"total_prompt_tokens":454721700,"total_completion_tokens":5167295,"volume":0.479568,"rank":6},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"technology","count":6654,"total_prompt_tokens":469687691,"total_completion_tokens":5448920,"volume":0.50647,"rank":12},{"date":"2026-08-23","model":"upstage/solar-pro4-20260810","category":"trivia","count":43,"total_prompt_tokens":663900,"total_completion_tokens":25150,"volume":0.003195,"rank":25}],"x-ai/grok-4.6-20260810":[{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"academia","count":244,"total_prompt_tokens":7504600,"total_completion_tokens":152941,"volume":9.382375,"rank":27},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"finance","count":374,"total_prompt_tokens":11072483,"total_completion_tokens":122339,"volume":19.206786,"rank":29},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"health","count":204,"total_prompt_tokens":1853654,"total_completion_tokens":126933,"volume":3.874004,"rank":42},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"legal","count":483,"total_prompt_tokens":20525850,"total_completion_tokens":198053,"volume":13.52824,"rank":8},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"marketing","count":198,"total_prompt_tokens":7240892,"total_completion_tokens":106972,"volume":4.257187,"rank":24},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"marketing/seo","count":16,"total_prompt_tokens":667000,"total_completion_tokens":12900,"volume":0.406401,"rank":35},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"programming","count":4662,"total_prompt_tokens":368287408,"total_completion_tokens":3546139,"volume":384.447426,"rank":19},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"science","count":1162,"total_prompt_tokens":56505869,"total_completion_tokens":755681,"volume":64.465234,"rank":24},{"date":"2026-08-23","model":"x-ai/grok-4.6-20260810","category":"technology","count":3494,"total_prompt_tokens":173760297,"total_completion_tokens":2082226,"volume":232.642828,"rank":25}],"minimax/minimax-m3-20260531":[{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"academia","count":474,"total_prompt_tokens":6584480,"total_completion_tokens":949545,"volume":0.772536,"rank":28},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"finance","count":1939,"total_prompt_tokens":47306728,"total_completion_tokens":2144790,"volume":2.300448,"rank":8},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"health","count":155,"total_prompt_tokens":2043539,"total_completion_tokens":206232,"volume":0.254465,"rank":38},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"legal","count":737,"total_prompt_tokens":6232850,"total_completion_tokens":2059650,"volume":0.584757,"rank":16},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"marketing","count":628,"total_prompt_tokens":8243864,"total_completion_tokens":463829,"volume":3.030924,"rank":23},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"marketing/seo","count":206,"total_prompt_tokens":4691305,"total_completion_tokens":103154,"volume":0.765592,"rank":9},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"programming","count":12581,"total_prompt_tokens":1065286664,"total_completion_tokens":13821345,"volume":44.91303,"rank":8},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"roleplay","count":1205,"total_prompt_tokens":20759670,"total_completion_tokens":1107631,"volume":1.750274,"rank":34},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"science","count":3583,"total_prompt_tokens":231462749,"total_completion_tokens":2769425,"volume":12.793285,"rank":12},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"technology","count":10772,"total_prompt_tokens":656021915,"total_completion_tokens":6851017,"volume":37.676777,"rank":10},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"translation","count":720,"total_prompt_tokens":2066338,"total_completion_tokens":896404,"volume":0.262821,"rank":31},{"date":"2026-08-23","model":"minimax/minimax-m3-20260531","category":"trivia","count":122,"total_prompt_tokens":427873,"total_completion_tokens":54616,"volume":0.12601,"rank":33}],"deepseek/deepseek-v4-pro-20260813":[{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"academia","count":169,"total_prompt_tokens":6577074,"total_completion_tokens":591236,"volume":4.698587,"rank":29},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"finance","count":452,"total_prompt_tokens":16333497,"total_completion_tokens":1259142,"volume":11.668437,"rank":23},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"health","count":199,"total_prompt_tokens":1872521,"total_completion_tokens":351416,"volume":1.48624,"rank":39},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"legal","count":124,"total_prompt_tokens":2414012,"total_completion_tokens":265605,"volume":1.726563,"rank":43},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"marketing","count":135,"total_prompt_tokens":5421800,"total_completion_tokens":250700,"volume":2.180457,"rank":27},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"marketing/seo","count":24,"total_prompt_tokens":889400,"total_completion_tokens":77750,"volume":0.406238,"rank":30},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"programming","count":6466,"total_prompt_tokens":542954238,"total_completion_tokens":12733679,"volume":173.642415,"rank":14},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"roleplay","count":4188,"total_prompt_tokens":90472354,"total_completion_tokens":3497094,"volume":22.940324,"rank":14},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"science","count":2014,"total_prompt_tokens":142886262,"total_completion_tokens":3271208,"volume":43.964233,"rank":15},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"technology","count":6930,"total_prompt_tokens":303583368,"total_completion_tokens":14686679,"volume":109.532741,"rank":17},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"translation","count":205,"total_prompt_tokens":1034037,"total_completion_tokens":897911,"volume":3.190097,"rank":39},{"date":"2026-08-23","model":"deepseek/deepseek-v4-pro-20260813","category":"trivia","count":278,"total_prompt_tokens":819012,"total_completion_tokens":333309,"volume":1.138142,"rank":19}],"openai/gpt-5.4-nano-20260317":[{"date":"2026-08-23","model":"openai/gpt-5.4-nano-20260317","category":"academia","count":1906,"total_prompt_tokens":5765289,"total_completion_tokens":1233843,"volume":2.159083,"rank":30},{"date":"2026-08-23","model":"openai/gpt-5.4-nano-20260317","category":"marketing/seo","count":363,"total_prompt_tokens":1900990,"total_completion_tokens":75336,"volume":0.224484,"rank":19},{"date":"2026-08-23","model":"openai/gpt-5.4-nano-20260317","category":"technology","count":15799,"total_prompt_tokens":61087345,"total_completion_tokens":1132024,"volume":7.825555,"rank":40},{"date":"2026-08-23","model":"openai/gpt-5.4-nano-20260317","category":"translation","count":5307,"total_prompt_tokens":18193652,"total_completion_tokens":247169,"volume":2.008061,"rank":8}],"stepfun/step-3.7-flash-20260528":[{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"academia","count":113,"total_prompt_tokens":6606400,"total_completion_tokens":105300,"volume":0.051234,"rank":31},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"finance","count":522,"total_prompt_tokens":10956256,"total_completion_tokens":1081656,"volume":0.091623,"rank":28},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"marketing","count":56,"total_prompt_tokens":2750300,"total_completion_tokens":49400,"volume":0.007447,"rank":35},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"marketing/seo","count":17,"total_prompt_tokens":1459250,"total_completion_tokens":6550,"volume":0.00085,"rank":23},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"programming","count":2403,"total_prompt_tokens":78733152,"total_completion_tokens":1737395,"volume":0.879098,"rank":36},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"science","count":4999,"total_prompt_tokens":294338750,"total_completion_tokens":2666350,"volume":0.576596,"rank":10},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"technology","count":6492,"total_prompt_tokens":331918651,"total_completion_tokens":3699399,"volume":2.260211,"rank":15},{"date":"2026-08-23","model":"stepfun/step-3.7-flash-20260528","category":"trivia","count":98,"total_prompt_tokens":2162850,"total_completion_tokens":139750,"volume":0.024923,"rank":12}],"google/gemini-3.5-flash-20260519":[{"date":"2026-08-23","model":"google/gemini-3.5-flash-20260519","category":"academia","count":1223,"total_prompt_tokens":5755469,"total_completion_tokens":603537,"volume":15.454564,"rank":32},{"date":"2026-08-23","model":"google/gemini-3.5-flash-20260519","category":"health","count":468,"total_prompt_tokens":1604382,"total_completion_tokens":215394,"volume":8.545605,"rank":46},{"date":"2026-08-23","model":"google/gemini-3.5-flash-20260519","category":"legal","count":622,"total_prompt_tokens":3991189,"total_completion_tokens":237117,"volume":7.672953,"rank":34},{"date":"2026-08-23","model":"google/gemini-3.5-flash-20260519","category":"marketing","count":3353,"total_prompt_tokens":8420835,"total_completion_tokens":1276219,"volume":36.327453,"rank":21},{"date":"2026-08-21","model":"google/gemini-3.5-flash-20260519","category":"marketing/seo","count":37,"total_prompt_tokens":732350,"total_completion_tokens":50700,"volume":1.765436,"rank":33},{"date":"2026-08-23","model":"google/gemini-3.5-flash-20260519","category":"science","count":2891,"total_prompt_tokens":26979297,"total_completion_tokens":690017,"volume":18.504504,"rank":40},{"date":"2026-08-23","model":"google/gemini-3.5-flash-20260519","category":"translation","count":1841,"total_prompt_tokens":13075018,"total_completion_tokens":457344,"volume":12.410653,"rank":12}],"openai/gpt-4o-mini":[{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"academia","count":5615,"total_prompt_tokens":4827610,"total_completion_tokens":997017,"volume":1.25264,"rank":33},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"finance","count":5738,"total_prompt_tokens":9378448,"total_completion_tokens":767456,"volume":2.461396,"rank":31},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"health","count":2873,"total_prompt_tokens":14278055,"total_completion_tokens":416669,"volume":1.011752,"rank":11},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"legal","count":2676,"total_prompt_tokens":4344004,"total_completion_tokens":292947,"volume":0.884244,"rank":30},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"marketing","count":5923,"total_prompt_tokens":14480027,"total_completion_tokens":515775,"volume":1.951041,"rank":15},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"marketing/seo","count":2406,"total_prompt_tokens":2980925,"total_completion_tokens":565891,"volume":0.726204,"rank":14},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"roleplay","count":29470,"total_prompt_tokens":37085709,"total_completion_tokens":2409748,"volume":6.550263,"rank":21},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"science","count":15082,"total_prompt_tokens":34810680,"total_completion_tokens":2103281,"volume":5.202366,"rank":32},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"technology","count":21769,"total_prompt_tokens":46506573,"total_completion_tokens":2473599,"volume":7.724473,"rank":44},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"translation","count":13834,"total_prompt_tokens":7664884,"total_completion_tokens":1770322,"volume":1.864398,"rank":17},{"date":"2026-08-23","model":"openai/gpt-4o-mini","category":"trivia","count":1316,"total_prompt_tokens":863975,"total_completion_tokens":30632,"volume":0.294674,"rank":22}],"google/gemma-3-27b-it":[{"date":"2026-08-23","model":"google/gemma-3-27b-it","category":"academia","count":2866,"total_prompt_tokens":3937500,"total_completion_tokens":1649650,"volume":0.74668,"rank":34},{"date":"2026-08-23","model":"google/gemma-3-27b-it","category":"marketing","count":1913,"total_prompt_tokens":3773011,"total_completion_tokens":44864,"volume":0.238298,"rank":31},{"date":"2026-08-23","model":"google/gemma-3-27b-it","category":"marketing/seo","count":5644,"total_prompt_tokens":9253800,"total_completion_tokens":999300,"volume":0.773242,"rank":6},{"date":"2026-08-23","model":"google/gemma-3-27b-it","category":"roleplay","count":3497,"total_prompt_tokens":15131784,"total_completion_tokens":1156560,"volume":1.466647,"rank":39}],"stealth/ox-alpha":[{"date":"2026-08-23","model":"stealth/ox-alpha","category":"academia","count":271,"total_prompt_tokens":4760992,"total_completion_tokens":693054,"volume":0,"rank":35},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"finance","count":573,"total_prompt_tokens":22398390,"total_completion_tokens":670743,"volume":0.028,"rank":19},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"health","count":140,"total_prompt_tokens":2600842,"total_completion_tokens":394248,"volume":0.063,"rank":28},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"legal","count":1349,"total_prompt_tokens":8033817,"total_completion_tokens":6680236,"volume":0.007,"rank":11},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"marketing","count":57,"total_prompt_tokens":1347300,"total_completion_tokens":111150,"volume":0.021,"rank":45},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"marketing/seo","count":8,"total_prompt_tokens":328750,"total_completion_tokens":11500,"volume":0,"rank":44},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"programming","count":9502,"total_prompt_tokens":931435756,"total_completion_tokens":7857733,"volume":0.116,"rank":12},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"science","count":3107,"total_prompt_tokens":283837064,"total_completion_tokens":2962862,"volume":0.007,"rank":11},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"technology","count":2985,"total_prompt_tokens":245859532,"total_completion_tokens":2271901,"volume":0.126,"rank":21},{"date":"2026-08-23","model":"stealth/ox-alpha","category":"translation","count":249,"total_prompt_tokens":2312528,"total_completion_tokens":631314,"volume":0,"rank":33}],"google/gemini-3.6-flash-20260721":[{"date":"2026-08-23","model":"google/gemini-3.6-flash-20260721","category":"academia","count":1079,"total_prompt_tokens":4090312,"total_completion_tokens":367814,"volume":3.668887,"rank":36},{"date":"2026-08-23","model":"google/gemini-3.6-flash-20260721","category":"marketing","count":200,"total_prompt_tokens":1168866,"total_completion_tokens":206474,"volume":2.357082,"rank":48},{"date":"2026-08-21","model":"google/gemini-3.6-flash-20260721","category":"marketing/seo","count":48,"total_prompt_tokens":381050,"total_completion_tokens":17500,"volume":0.298936,"rank":38},{"date":"2026-08-23","model":"google/gemini-3.6-flash-20260721","category":"programming","count":7813,"total_prompt_tokens":948049873,"total_completion_tokens":3900679,"volume":195.398533,"rank":11},{"date":"2026-08-23","model":"google/gemini-3.6-flash-20260721","category":"technology","count":16488,"total_prompt_tokens":1745134855,"total_completion_tokens":7690670,"volume":359.278897,"rank":5},{"date":"2026-08-23","model":"google/gemini-3.6-flash-20260721","category":"translation","count":1367,"total_prompt_tokens":1129506,"total_completion_tokens":188572,"volume":1.572232,"rank":45}],"openai/gpt-5.4-mini-20260317":[{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"academia","count":1171,"total_prompt_tokens":3316211,"total_completion_tokens":1128406,"volume":6.958038,"rank":37},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"finance","count":1526,"total_prompt_tokens":5710711,"total_completion_tokens":376837,"volume":4.326595,"rank":40},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"health","count":809,"total_prompt_tokens":3934370,"total_completion_tokens":172286,"volume":1.898723,"rank":25},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"legal","count":978,"total_prompt_tokens":7104734,"total_completion_tokens":192926,"volume":3.071804,"rank":21},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"marketing","count":541,"total_prompt_tokens":1657110,"total_completion_tokens":141690,"volume":2.099136,"rank":40},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"marketing/seo","count":164,"total_prompt_tokens":1600290,"total_completion_tokens":71199,"volume":0.987034,"rank":21},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"science","count":2848,"total_prompt_tokens":18931659,"total_completion_tokens":488083,"volume":7.31657,"rank":48},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"translation","count":2073,"total_prompt_tokens":3058041,"total_completion_tokens":2046002,"volume":10.53082,"rank":21},{"date":"2026-08-23","model":"openai/gpt-5.4-mini-20260317","category":"trivia","count":916,"total_prompt_tokens":337500,"total_completion_tokens":35700,"volume":0.283877,"rank":42}],"openai/gpt-4.1-mini-2025-04-14":[{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"academia","count":1641,"total_prompt_tokens":4068651,"total_completion_tokens":267516,"volume":1.503016,"rank":38},{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"health","count":554,"total_prompt_tokens":2619053,"total_completion_tokens":84146,"volume":0.364718,"rank":35},{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"legal","count":1515,"total_prompt_tokens":3457364,"total_completion_tokens":190162,"volume":1.22045,"rank":37},{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"marketing","count":779,"total_prompt_tokens":2465837,"total_completion_tokens":173049,"volume":0.771624,"rank":37},{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"marketing/seo","count":142,"total_prompt_tokens":347088,"total_completion_tokens":43126,"volume":0.154331,"rank":39},{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"translation","count":5705,"total_prompt_tokens":9205548,"total_completion_tokens":464076,"volume":2.841768,"rank":16},{"date":"2026-08-23","model":"openai/gpt-4.1-mini-2025-04-14","category":"trivia","count":315,"total_prompt_tokens":312841,"total_completion_tokens":11602,"volume":0.108854,"rank":48}],"google/gemini-3.1-pro-preview-20260219":[{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"academia","count":520,"total_prompt_tokens":3574587,"total_completion_tokens":530414,"volume":16.316896,"rank":39},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"health","count":438,"total_prompt_tokens":3936532,"total_completion_tokens":256498,"volume":14.673695,"rank":24},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"legal","count":1366,"total_prompt_tokens":12906035,"total_completion_tokens":518672,"volume":38.902447,"rank":12},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"marketing","count":204,"total_prompt_tokens":2250176,"total_completion_tokens":241199,"volume":8.44862,"rank":38},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"programming","count":2104,"total_prompt_tokens":101620177,"total_completion_tokens":1742560,"volume":196.574642,"rank":30},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"roleplay","count":1568,"total_prompt_tokens":27933332,"total_completion_tokens":1707237,"volume":56.721742,"rank":23},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"science","count":1597,"total_prompt_tokens":20712813,"total_completion_tokens":1698380,"volume":70.325159,"rank":45},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"technology","count":3001,"total_prompt_tokens":101797706,"total_completion_tokens":2438140,"volume":253.53327,"rank":33},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"translation","count":753,"total_prompt_tokens":1384865,"total_completion_tokens":372536,"volume":9.211975,"rank":40},{"date":"2026-08-23","model":"google/gemini-3.1-pro-preview-20260219","category":"trivia","count":151,"total_prompt_tokens":350620,"total_completion_tokens":47667,"volume":1.920956,"rank":39}],"moonshotai/kimi-k2.6-20260420":[{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"academia","count":261,"total_prompt_tokens":2836661,"total_completion_tokens":1103495,"volume":5.512203,"rank":40},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"finance","count":2976,"total_prompt_tokens":27096988,"total_completion_tokens":9125588,"volume":35.308376,"rank":12},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"health","count":233,"total_prompt_tokens":1331500,"total_completion_tokens":494100,"volume":1.838983,"rank":45},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"marketing/seo","count":138,"total_prompt_tokens":206205,"total_completion_tokens":83573,"volume":0.299808,"rank":48},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"programming","count":2774,"total_prompt_tokens":127403144,"total_completion_tokens":3228333,"volume":42.464623,"rank":27},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"roleplay","count":4235,"total_prompt_tokens":10446370,"total_completion_tokens":3718150,"volume":6.942185,"rank":50},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"science","count":1472,"total_prompt_tokens":16664814,"total_completion_tokens":6166960,"volume":26.720773,"rank":44},{"date":"2026-08-23","model":"moonshotai/kimi-k2.6-20260420","category":"trivia","count":245,"total_prompt_tokens":470900,"total_completion_tokens":389159,"volume":1.233392,"rank":23}],"google/gemini-3.5-flash-lite-20260721":[{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"academia","count":1412,"total_prompt_tokens":3340154,"total_completion_tokens":352742,"volume":1.290078,"rank":41},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"finance","count":3453,"total_prompt_tokens":6268369,"total_completion_tokens":147633,"volume":1.962144,"rank":37},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"health","count":1078,"total_prompt_tokens":3373784,"total_completion_tokens":226108,"volume":1.785859,"rank":26},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"marketing","count":351,"total_prompt_tokens":1406913,"total_completion_tokens":97181,"volume":0.709404,"rank":44},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"marketing/seo","count":70,"total_prompt_tokens":278737,"total_completion_tokens":22262,"volume":0.470084,"rank":46},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"science","count":7731,"total_prompt_tokens":29570093,"total_completion_tokens":319852,"volume":8.006996,"rank":37},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"translation","count":7177,"total_prompt_tokens":2589220,"total_completion_tokens":373042,"volume":1.40781,"rank":32},{"date":"2026-08-23","model":"google/gemini-3.5-flash-lite-20260721","category":"trivia","count":549,"total_prompt_tokens":1140357,"total_completion_tokens":29089,"volume":0.363331,"rank":18}],"openai/gpt-5.5-20260423":[{"date":"2026-08-23","model":"openai/gpt-5.5-20260423","category":"academia","count":138,"total_prompt_tokens":3361014,"total_completion_tokens":163097,"volume":12.530496,"rank":42},{"date":"2026-08-23","model":"openai/gpt-5.5-20260423","category":"programming","count":1965,"total_prompt_tokens":196411526,"total_completion_tokens":729511,"volume":399.354549,"rank":24},{"date":"2026-08-23","model":"openai/gpt-5.5-20260423","category":"science","count":909,"total_prompt_tokens":19853864,"total_completion_tokens":692752,"volume":90.028426,"rank":47},{"date":"2026-08-23","model":"openai/gpt-5.5-20260423","category":"technology","count":3849,"total_prompt_tokens":273875446,"total_completion_tokens":1580228,"volume":490.22474,"rank":20}],"qwen/qwen3.6-flash":[{"date":"2026-08-23","model":"qwen/qwen3.6-flash","category":"academia","count":36,"total_prompt_tokens":3440750,"total_completion_tokens":63850,"volume":0.178764,"rank":43}],"z-ai/glm-5.3-20260816":[{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"academia","count":166,"total_prompt_tokens":3142202,"total_completion_tokens":235503,"volume":2.199897,"rank":44},{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"finance","count":178,"total_prompt_tokens":8316650,"total_completion_tokens":351350,"volume":5.353917,"rank":32},{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"legal","count":164,"total_prompt_tokens":4968650,"total_completion_tokens":756600,"volume":5.547013,"rank":28},{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"marketing/seo","count":22,"total_prompt_tokens":1152733,"total_completion_tokens":228832,"volume":0.878704,"rank":24},{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"programming","count":4674,"total_prompt_tokens":465765961,"total_completion_tokens":5212398,"volume":189.813945,"rank":17},{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"science","count":849,"total_prompt_tokens":71581945,"total_completion_tokens":1129872,"volume":29.774199,"rank":21},{"date":"2026-08-23","model":"z-ai/glm-5.3-20260816","category":"technology","count":1991,"total_prompt_tokens":121145691,"total_completion_tokens":2758707,"volume":59.229645,"rank":30}],"anthropic/claude-4.5-haiku-20251001":[{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"academia","count":1039,"total_prompt_tokens":2943102,"total_completion_tokens":384967,"volume":4.773458,"rank":45},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"finance","count":3006,"total_prompt_tokens":14158802,"total_completion_tokens":554254,"volume":13.36527,"rank":27},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"health","count":1302,"total_prompt_tokens":5462459,"total_completion_tokens":238917,"volume":5.094399,"rank":18},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"legal","count":719,"total_prompt_tokens":2062382,"total_completion_tokens":234094,"volume":3.402267,"rank":46},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"marketing","count":1061,"total_prompt_tokens":5340342,"total_completion_tokens":328265,"volume":6.392824,"rank":28},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"marketing/seo","count":238,"total_prompt_tokens":741938,"total_completion_tokens":221195,"volume":1.246962,"rank":31},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"programming","count":4215,"total_prompt_tokens":58019609,"total_completion_tokens":1113615,"volume":20.897353,"rank":39},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"roleplay","count":2297,"total_prompt_tokens":15439056,"total_completion_tokens":601230,"volume":11.122934,"rank":41},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"science","count":3702,"total_prompt_tokens":34141900,"total_completion_tokens":1417529,"volume":30.392371,"rank":33},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"technology","count":10802,"total_prompt_tokens":87263437,"total_completion_tokens":2183064,"volume":56.470046,"rank":35},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"translation","count":1544,"total_prompt_tokens":4921362,"total_completion_tokens":304950,"volume":3.810869,"rank":20},{"date":"2026-08-23","model":"anthropic/claude-4.5-haiku-20251001","category":"trivia","count":302,"total_prompt_tokens":365080,"total_completion_tokens":60586,"volume":0.635553,"rank":36}],"qwen/qwen3-235b-a22b-07-25":[{"date":"2026-08-23","model":"qwen/qwen3-235b-a22b-07-25","category":"academia","count":1130,"total_prompt_tokens":2715530,"total_completion_tokens":341551,"volume":0.528075,"rank":46},{"date":"2026-08-23","model":"qwen/qwen3-235b-a22b-07-25","category":"roleplay","count":3666,"total_prompt_tokens":21460587,"total_completion_tokens":1067530,"volume":2.864673,"rank":31},{"date":"2026-08-23","model":"qwen/qwen3-235b-a22b-07-25","category":"translation","count":932,"total_prompt_tokens":1199739,"total_completion_tokens":510104,"volume":0.453534,"rank":41}],"openai/gpt-5.6-luna-pro-20260709":[{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"academia","count":2477,"total_prompt_tokens":2322877,"total_completion_tokens":533212,"volume":8.186745,"rank":47},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"health","count":425,"total_prompt_tokens":1547127,"total_completion_tokens":166018,"volume":1.411176,"rank":48},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"legal","count":267,"total_prompt_tokens":2101535,"total_completion_tokens":66318,"volume":1.478307,"rank":49},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"marketing/seo","count":11,"total_prompt_tokens":277662,"total_completion_tokens":18004,"volume":0.189787,"rank":47},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"programming","count":1011,"total_prompt_tokens":53240037,"total_completion_tokens":557824,"volume":20.840588,"rank":40},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"science","count":4327,"total_prompt_tokens":31061117,"total_completion_tokens":990535,"volume":23.457345,"rank":36},{"date":"2026-08-23","model":"openai/gpt-5.6-luna-pro-20260709","category":"technology","count":1325,"total_prompt_tokens":49507298,"total_completion_tokens":573235,"volume":18.898616,"rank":43}],"anthropic/claude-4.8-opus-20260528":[{"date":"2026-08-23","model":"anthropic/claude-4.8-opus-20260528","category":"academia","count":275,"total_prompt_tokens":2412931,"total_completion_tokens":165285,"volume":12.514047,"rank":48},{"date":"2026-08-23","model":"anthropic/claude-4.8-opus-20260528","category":"finance","count":570,"total_prompt_tokens":22999552,"total_completion_tokens":269435,"volume":62.038572,"rank":18},{"date":"2026-08-22","model":"anthropic/claude-4.8-opus-20260528","category":"marketing/seo","count":33,"total_prompt_tokens":307050,"total_completion_tokens":32450,"volume":2.34813,"rank":45},{"date":"2026-08-23","model":"anthropic/claude-4.8-opus-20260528","category":"programming","count":3863,"total_prompt_tokens":178862216,"total_completion_tokens":1813363,"volume":484.097693,"rank":25},{"date":"2026-08-23","model":"anthropic/claude-4.8-opus-20260528","category":"science","count":899,"total_prompt_tokens":28865235,"total_completion_tokens":659240,"volume":103.886334,"rank":38},{"date":"2026-08-23","model":"anthropic/claude-4.8-opus-20260528","category":"technology","count":4985,"total_prompt_tokens":148161940,"total_completion_tokens":1751080,"volume":379.998844,"rank":26}],"openai/gpt-oss-20b":[{"date":"2026-08-23","model":"openai/gpt-oss-20b","category":"academia","count":828,"total_prompt_tokens":2138254,"total_completion_tokens":426910,"volume":0.19089,"rank":49},{"date":"2026-08-23","model":"openai/gpt-oss-20b","category":"finance","count":2399,"total_prompt_tokens":5066614,"total_completion_tokens":797879,"volume":0.349426,"rank":42},{"date":"2026-08-23","model":"openai/gpt-oss-20b","category":"health","count":1572,"total_prompt_tokens":4690431,"total_completion_tokens":694016,"volume":0.366798,"rank":20},{"date":"2026-08-23","model":"openai/gpt-oss-20b","category":"legal","count":1121,"total_prompt_tokens":2570471,"total_completion_tokens":1259758,"volume":0.210032,"rank":36},{"date":"2026-08-23","model":"openai/gpt-oss-20b","category":"translation","count":912,"total_prompt_tokens":2196133,"total_completion_tokens":1390038,"volume":0.277614,"rank":29}],"openai/gpt-5.4-20260305":[{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"academia","count":235,"total_prompt_tokens":2099639,"total_completion_tokens":148971,"volume":6.067265,"rank":50},{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"health","count":493,"total_prompt_tokens":2510495,"total_completion_tokens":248277,"volume":5.519303,"rank":33},{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"marketing","count":503,"total_prompt_tokens":3037304,"total_completion_tokens":68342,"volume":2.339659,"rank":33},{"date":"2026-08-21","model":"openai/gpt-5.4-20260305","category":"marketing/seo","count":28,"total_prompt_tokens":1203704,"total_completion_tokens":35841,"volume":0.557055,"rank":25},{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"science","count":2598,"total_prompt_tokens":86692692,"total_completion_tokens":1696438,"volume":88.002185,"rank":18},{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"technology","count":3612,"total_prompt_tokens":109183209,"total_completion_tokens":1553638,"volume":89.374803,"rank":32},{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"translation","count":210,"total_prompt_tokens":1163633,"total_completion_tokens":48104,"volume":1.370355,"rank":48},{"date":"2026-08-23","model":"openai/gpt-5.4-20260305","category":"trivia","count":224,"total_prompt_tokens":473470,"total_completion_tokens":6315,"volume":1.043298,"rank":34}],"openai/text-embedding-3-large":[{"date":"2026-08-23","model":"openai/text-embedding-3-large","category":"finance","count":556,"total_prompt_tokens":16952572,"total_completion_tokens":0,"volume":1.878839,"rank":24}],"anthropic/claude-4.6-opus-20260205":[{"date":"2026-08-23","model":"anthropic/claude-4.6-opus-20260205","category":"finance","count":338,"total_prompt_tokens":15115074,"total_completion_tokens":108978,"volume":15.585141,"rank":26},{"date":"2026-08-23","model":"anthropic/claude-4.6-opus-20260205","category":"programming","count":817,"total_prompt_tokens":43420733,"total_completion_tokens":473629,"volume":61.953231,"rank":43},{"date":"2026-08-23","model":"anthropic/claude-4.6-opus-20260205","category":"roleplay","count":985,"total_prompt_tokens":23071831,"total_completion_tokens":921117,"volume":110.915612,"rank":28},{"date":"2026-08-23","model":"anthropic/claude-4.6-opus-20260205","category":"technology","count":1473,"total_prompt_tokens":70924848,"total_completion_tokens":473617,"volume":148.798063,"rank":39},{"date":"2026-08-23","model":"anthropic/claude-4.6-opus-20260205","category":"translation","count":1274,"total_prompt_tokens":2546300,"total_completion_tokens":229450,"volume":17.766965,"rank":35}],"xiaomi/mimo-v2.5-pro-20260422":[{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"finance","count":191,"total_prompt_tokens":7732268,"total_completion_tokens":145063,"volume":1.551786,"rank":35},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"marketing","count":89,"total_prompt_tokens":2986600,"total_completion_tokens":24500,"volume":0.124671,"rank":34},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"programming","count":3752,"total_prompt_tokens":403126022,"total_completion_tokens":2429761,"volume":8.771273,"rank":18},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"roleplay","count":8490,"total_prompt_tokens":323955217,"total_completion_tokens":8166464,"volume":39.155745,"rank":7},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"science","count":863,"total_prompt_tokens":69404883,"total_completion_tokens":1041009,"volume":3.435341,"rank":22},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"technology","count":1282,"total_prompt_tokens":78467237,"total_completion_tokens":858475,"volume":3.73399,"rank":36},{"date":"2026-08-23","model":"xiaomi/mimo-v2.5-pro-20260422","category":"trivia","count":28,"total_prompt_tokens":586217,"total_completion_tokens":3480,"volume":0.012165,"rank":27}],"anthropic/claude-5-fable-20260609":[{"date":"2026-08-23","model":"anthropic/claude-5-fable-20260609","category":"finance","count":116,"total_prompt_tokens":6338689,"total_completion_tokens":66704,"volume":27.785135,"rank":38},{"date":"2026-08-23","model":"anthropic/claude-5-fable-20260609","category":"marketing/seo","count":9,"total_prompt_tokens":698050,"total_completion_tokens":9500,"volume":3.200214,"rank":34},{"date":"2026-08-23","model":"anthropic/claude-5-fable-20260609","category":"programming","count":1525,"total_prompt_tokens":126741179,"total_completion_tokens":884281,"volume":567.102843,"rank":28},{"date":"2026-08-23","model":"anthropic/claude-5-fable-20260609","category":"science","count":666,"total_prompt_tokens":22159333,"total_completion_tokens":772842,"volume":252.626602,"rank":43},{"date":"2026-08-23","model":"anthropic/claude-5-fable-20260609","category":"technology","count":1021,"total_prompt_tokens":48074632,"total_completion_tokens":515357,"volume":222.802484,"rank":45}],"qwen/qwen3.8-27b-20260814":[{"date":"2026-08-23","model":"qwen/qwen3.8-27b-20260814","category":"finance","count":201,"total_prompt_tokens":5759961,"total_completion_tokens":244049,"volume":3.390549,"rank":41},{"date":"2026-08-23","model":"qwen/qwen3.8-27b-20260814","category":"health","count":622,"total_prompt_tokens":2298004,"total_completion_tokens":679142,"volume":2.409656,"rank":29},{"date":"2026-08-23","model":"qwen/qwen3.8-27b-20260814","category":"programming","count":1926,"total_prompt_tokens":72813432,"total_completion_tokens":3629227,"volume":49.637726,"rank":37},{"date":"2026-08-23","model":"qwen/qwen3.8-27b-20260814","category":"trivia","count":111,"total_prompt_tokens":273849,"total_completion_tokens":64592,"volume":0.259571,"rank":47}],"anthropic/claude-4.7-opus-20260416":[{"date":"2026-08-23","model":"anthropic/claude-4.7-opus-20260416","category":"finance","count":259,"total_prompt_tokens":5453100,"total_completion_tokens":208650,"volume":13.456606,"rank":43},{"date":"2026-08-23","model":"anthropic/claude-4.7-opus-20260416","category":"programming","count":5481,"total_prompt_tokens":260153308,"total_completion_tokens":3668280,"volume":106.664098,"rank":21},{"date":"2026-08-23","model":"anthropic/claude-4.7-opus-20260416","category":"technology","count":10055,"total_prompt_tokens":470588603,"total_completion_tokens":6878930,"volume":42.125969,"rank":11}],"x-ai/grok-4.5-20260708":[{"date":"2026-08-23","model":"x-ai/grok-4.5-20260708","category":"finance","count":203,"total_prompt_tokens":4692809,"total_completion_tokens":94562,"volume":9.271972,"rank":44},{"date":"2026-08-23","model":"x-ai/grok-4.5-20260708","category":"health","count":80,"total_prompt_tokens":1735190,"total_completion_tokens":26724,"volume":1.342059,"rank":47},{"date":"2026-08-23","model":"x-ai/grok-4.5-20260708","category":"legal","count":122,"total_prompt_tokens":2961638,"total_completion_tokens":41557,"volume":2.268637,"rank":41},{"date":"2026-08-23","model":"x-ai/grok-4.5-20260708","category":"marketing/seo","count":9,"total_prompt_tokens":382300,"total_completion_tokens":2550,"volume":0.618571,"rank":42},{"date":"2026-08-23","model":"x-ai/grok-4.5-20260708","category":"programming","count":1431,"total_prompt_tokens":89210678,"total_completion_tokens":812194,"volume":70.015283,"rank":33},{"date":"2026-08-23","model":"x-ai/grok-4.5-20260708","category":"technology","count":1195,"total_prompt_tokens":41396658,"total_completion_tokens":614405,"volume":37.933912,"rank":50}],"x-ai/grok-4.3-20260430":[{"date":"2026-08-23","model":"x-ai/grok-4.3-20260430","category":"finance","count":786,"total_prompt_tokens":4318119,"total_completion_tokens":231447,"volume":4.833556,"rank":45},{"date":"2026-08-23","model":"x-ai/grok-4.3-20260430","category":"roleplay","count":3183,"total_prompt_tokens":13486641,"total_completion_tokens":903718,"volume":14.713514,"rank":49},{"date":"2026-08-23","model":"x-ai/grok-4.3-20260430","category":"trivia","count":324,"total_prompt_tokens":259500,"total_completion_tokens":50600,"volume":0.77639,"rank":49}],"deepseek/deepseek-v3.2-20251201":[{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"finance","count":1033,"total_prompt_tokens":3790945,"total_completion_tokens":290435,"volume":1.148005,"rank":47},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"health","count":467,"total_prompt_tokens":1530706,"total_completion_tokens":163793,"volume":0.823328,"rank":49},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"legal","count":712,"total_prompt_tokens":7815790,"total_completion_tokens":275780,"volume":0.863001,"rank":17},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"marketing","count":445,"total_prompt_tokens":5871459,"total_completion_tokens":166361,"volume":0.999711,"rank":26},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"marketing/seo","count":861,"total_prompt_tokens":1344089,"total_completion_tokens":227302,"volume":0.247311,"rank":22},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"roleplay","count":62642,"total_prompt_tokens":505207478,"total_completion_tokens":21879552,"volume":79.464271,"rank":4},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"science","count":2217,"total_prompt_tokens":16409587,"total_completion_tokens":1340488,"volume":3.086932,"rank":49},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"technology","count":7207,"total_prompt_tokens":56393687,"total_completion_tokens":1235332,"volume":11.657022,"rank":41},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"translation","count":6267,"total_prompt_tokens":10320410,"total_completion_tokens":1159353,"volume":1.895219,"rank":13},{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-20251201","category":"trivia","count":315,"total_prompt_tokens":445084,"total_completion_tokens":159749,"volume":0.133512,"rank":26}],"anthropic/claude-4.5-sonnet-20250929":[{"date":"2026-08-23","model":"anthropic/claude-4.5-sonnet-20250929","category":"finance","count":379,"total_prompt_tokens":3588469,"total_completion_tokens":122225,"volume":5.978957,"rank":48},{"date":"2026-08-23","model":"anthropic/claude-4.5-sonnet-20250929","category":"health","count":253,"total_prompt_tokens":1767672,"total_completion_tokens":104452,"volume":5.205262,"rank":44},{"date":"2026-08-23","model":"anthropic/claude-4.5-sonnet-20250929","category":"marketing","count":234,"total_prompt_tokens":1232206,"total_completion_tokens":107506,"volume":5.89559,"rank":50},{"date":"2026-08-23","model":"anthropic/claude-4.5-sonnet-20250929","category":"marketing/seo","count":154,"total_prompt_tokens":1045471,"total_completion_tokens":107549,"volume":2.210743,"rank":27},{"date":"2026-08-23","model":"anthropic/claude-4.5-sonnet-20250929","category":"roleplay","count":3131,"total_prompt_tokens":23427351,"total_completion_tokens":1193074,"volume":72.735849,"rank":26},{"date":"2026-08-23","model":"anthropic/claude-4.5-sonnet-20250929","category":"translation","count":368,"total_prompt_tokens":925206,"total_completion_tokens":172635,"volume":5.016857,"rank":50}],"openai/gpt-5.1-20251113":[{"date":"2026-08-23","model":"openai/gpt-5.1-20251113","category":"finance","count":154,"total_prompt_tokens":3393192,"total_completion_tokens":95208,"volume":2.69466,"rank":50},{"date":"2026-08-23","model":"openai/gpt-5.1-20251113","category":"health","count":228,"total_prompt_tokens":1941456,"total_completion_tokens":44526,"volume":1.193897,"rank":41},{"date":"2026-08-23","model":"openai/gpt-5.1-20251113","category":"legal","count":194,"total_prompt_tokens":5608500,"total_completion_tokens":220500,"volume":5.812494,"rank":27}],"meta-llama/llama-3.3-70b-instruct":[{"date":"2026-08-23","model":"meta-llama/llama-3.3-70b-instruct","category":"health","count":1125,"total_prompt_tokens":2528642,"total_completion_tokens":325902,"volume":1.14356,"rank":30},{"date":"2026-08-23","model":"meta-llama/llama-3.3-70b-instruct","category":"marketing","count":2343,"total_prompt_tokens":3153274,"total_completion_tokens":77915,"volume":1.681072,"rank":32},{"date":"2026-08-23","model":"meta-llama/llama-3.3-70b-instruct","category":"trivia","count":828,"total_prompt_tokens":466050,"total_completion_tokens":25250,"volume":0.080048,"rank":31}],"openai/gpt-4.1-nano-2025-04-14":[{"date":"2026-08-23","model":"openai/gpt-4.1-nano-2025-04-14","category":"health","count":314,"total_prompt_tokens":2781091,"total_completion_tokens":44413,"volume":0.33407,"rank":31},{"date":"2026-08-23","model":"openai/gpt-4.1-nano-2025-04-14","category":"roleplay","count":1044,"total_prompt_tokens":14741756,"total_completion_tokens":116253,"volume":0.769906,"rank":46},{"date":"2026-08-23","model":"openai/gpt-4.1-nano-2025-04-14","category":"translation","count":1493,"total_prompt_tokens":1897255,"total_completion_tokens":252094,"volume":0.116525,"rank":38}],"qwen/qwen3-vl-32b-instruct":[{"date":"2026-08-23","model":"qwen/qwen3-vl-32b-instruct","category":"health","count":183,"total_prompt_tokens":2679550,"total_completion_tokens":62350,"volume":0.127666,"rank":34},{"date":"2026-08-23","model":"qwen/qwen3-vl-32b-instruct","category":"legal","count":862,"total_prompt_tokens":2092200,"total_completion_tokens":133100,"volume":0.167915,"rank":48}],"qwen/qwen3.5-397b-a17b-20260216":[{"date":"2026-08-23","model":"qwen/qwen3.5-397b-a17b-20260216","category":"health","count":525,"total_prompt_tokens":2538250,"total_completion_tokens":162300,"volume":1.299044,"rank":36},{"date":"2026-08-23","model":"qwen/qwen3.5-397b-a17b-20260216","category":"trivia","count":187,"total_prompt_tokens":193050,"total_completion_tokens":218450,"volume":0.894341,"rank":37}],"qwen/qwen3-embedding-8b":[{"date":"2026-08-23","model":"qwen/qwen3-embedding-8b","category":"health","count":613,"total_prompt_tokens":2118658,"total_completion_tokens":0,"volume":0.026616,"rank":40},{"date":"2026-08-23","model":"qwen/qwen3-embedding-8b","category":"legal","count":1008,"total_prompt_tokens":2894402,"total_completion_tokens":0,"volume":0.046421,"rank":42}],"qwen/qwen3.5-35b-a3b-20260224":[{"date":"2026-08-23","model":"qwen/qwen3.5-35b-a3b-20260224","category":"health","count":369,"total_prompt_tokens":1731550,"total_completion_tokens":239050,"volume":0.582851,"rank":43}],"openai/gpt-4.1-2025-04-14":[{"date":"2026-08-23","model":"openai/gpt-4.1-2025-04-14","category":"health","count":400,"total_prompt_tokens":1620076,"total_completion_tokens":40467,"volume":2.900328,"rank":50},{"date":"2026-08-23","model":"openai/gpt-4.1-2025-04-14","category":"marketing","count":294,"total_prompt_tokens":1247623,"total_completion_tokens":108294,"volume":2.197691,"rank":49},{"date":"2026-08-23","model":"openai/gpt-4.1-2025-04-14","category":"trivia","count":336,"total_prompt_tokens":534550,"total_completion_tokens":30100,"volume":0.825617,"rank":28}],"google/gemini-3.1-flash-lite-preview-20260303":[{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-preview-20260303","category":"legal","count":261,"total_prompt_tokens":7278512,"total_completion_tokens":225882,"volume":1.486557,"rank":19},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-preview-20260303","category":"marketing","count":643,"total_prompt_tokens":1677207,"total_completion_tokens":111404,"volume":0.393737,"rank":41},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-preview-20260303","category":"roleplay","count":4286,"total_prompt_tokens":14344505,"total_completion_tokens":301295,"volume":2.995583,"rank":48},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-preview-20260303","category":"science","count":4466,"total_prompt_tokens":16686170,"total_completion_tokens":666228,"volume":2.614876,"rank":50},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-preview-20260303","category":"translation","count":967,"total_prompt_tokens":1998325,"total_completion_tokens":240498,"volume":0.570826,"rank":37},{"date":"2026-08-23","model":"google/gemini-3.1-flash-lite-preview-20260303","category":"trivia","count":329,"total_prompt_tokens":1715327,"total_completion_tokens":18512,"volume":0.325935,"rank":13}],"bytedance-seed/seed-2.0-mini-20260224":[{"date":"2026-08-23","model":"bytedance-seed/seed-2.0-mini-20260224","category":"legal","count":443,"total_prompt_tokens":5435550,"total_completion_tokens":588600,"volume":0.775258,"rank":26}],"qwen/qwen3.7-max-20260520":[{"date":"2026-08-23","model":"qwen/qwen3.7-max-20260520","category":"legal","count":178,"total_prompt_tokens":4978200,"total_completion_tokens":483750,"volume":5.576634,"rank":29},{"date":"2026-08-23","model":"qwen/qwen3.7-max-20260520","category":"programming","count":504,"total_prompt_tokens":38623639,"total_completion_tokens":547131,"volume":16.005097,"rank":48},{"date":"2026-08-23","model":"qwen/qwen3.7-max-20260520","category":"trivia","count":78,"total_prompt_tokens":242950,"total_completion_tokens":126050,"volume":0.766682,"rank":43}],"openai/gpt-5-nano-2025-08-07":[{"date":"2026-08-23","model":"openai/gpt-5-nano-2025-08-07","category":"legal","count":1153,"total_prompt_tokens":3817684,"total_completion_tokens":560782,"volume":0.552808,"rank":33},{"date":"2026-08-23","model":"openai/gpt-5-nano-2025-08-07","category":"marketing/seo","count":2016,"total_prompt_tokens":673642,"total_completion_tokens":378839,"volume":0.194314,"rank":29}],"openai/text-embedding-3-small":[{"date":"2026-08-23","model":"openai/text-embedding-3-small","category":"legal","count":740,"total_prompt_tokens":4013407,"total_completion_tokens":0,"volume":0.077529,"rank":35}],"inclusionai/ling-3.0-flash-20260723":[{"date":"2026-08-23","model":"inclusionai/ling-3.0-flash-20260723","category":"legal","count":1509,"total_prompt_tokens":2485207,"total_completion_tokens":688186,"volume":0.086733,"rank":40},{"date":"2026-08-23","model":"inclusionai/ling-3.0-flash-20260723","category":"translation","count":277,"total_prompt_tokens":484147,"total_completion_tokens":738287,"volume":0.079321,"rank":47}],"baai/bge-m3-20251117":[{"date":"2026-08-23","model":"baai/bge-m3-20251117","category":"legal","count":264,"total_prompt_tokens":2584287,"total_completion_tokens":0,"volume":0.014629,"rank":44}],"perplexity/pplx-embed-v1-0.6B":[{"date":"2026-08-23","model":"perplexity/pplx-embed-v1-0.6B","category":"legal","count":87,"total_prompt_tokens":2314884,"total_completion_tokens":0,"volume":0.011073,"rank":45}],"meta/muse-spark-1.2-20260805":[{"date":"2026-08-23","model":"meta/muse-spark-1.2-20260805","category":"legal","count":68,"total_prompt_tokens":2036919,"total_completion_tokens":73488,"volume":2.224515,"rank":50},{"date":"2026-08-23","model":"meta/muse-spark-1.2-20260805","category":"technology","count":929,"total_prompt_tokens":42380470,"total_completion_tokens":361941,"volume":33.134209,"rank":48}],"amazon/nova-micro-v1":[{"date":"2026-08-23","model":"amazon/nova-micro-v1","category":"marketing","count":9342,"total_prompt_tokens":20547054,"total_completion_tokens":1152324,"volume":0.891324,"rank":8},{"date":"2026-08-23","model":"amazon/nova-micro-v1","category":"marketing/seo","count":308,"total_prompt_tokens":779801,"total_completion_tokens":63504,"volume":0.036049,"rank":32}],"mistralai/mistral-nemo":[{"date":"2026-08-23","model":"mistralai/mistral-nemo","category":"marketing","count":1830,"total_prompt_tokens":3923598,"total_completion_tokens":457291,"volume":0.097451,"rank":29},{"date":"2026-08-23","model":"mistralai/mistral-nemo","category":"roleplay","count":15305,"total_prompt_tokens":48541577,"total_completion_tokens":1988448,"volume":0.724839,"rank":17},{"date":"2026-08-23","model":"mistralai/mistral-nemo","category":"translation","count":1551,"total_prompt_tokens":1253218,"total_completion_tokens":298537,"volume":0.045153,"rank":43},{"date":"2026-08-23","model":"mistralai/mistral-nemo","category":"trivia","count":140,"total_prompt_tokens":369100,"total_completion_tokens":12100,"volume":0.002007,"rank":40}],"qwen/qwen3-30b-a3b-instruct-2507":[{"date":"2026-08-23","model":"qwen/qwen3-30b-a3b-instruct-2507","category":"marketing","count":829,"total_prompt_tokens":1500623,"total_completion_tokens":90589,"volume":0.13296,"rank":43}],"minimax/minimax-m2.7-20260318":[{"date":"2026-08-23","model":"minimax/minimax-m2.7-20260318","category":"marketing","count":42,"total_prompt_tokens":1326800,"total_completion_tokens":126550,"volume":0.313109,"rank":46},{"date":"2026-08-23","model":"minimax/minimax-m2.7-20260318","category":"technology","count":4291,"total_prompt_tokens":234342746,"total_completion_tokens":964271,"volume":49.583861,"rank":22}],"inclusionai/ling-2.6-flash-20260421":[{"date":"2026-08-22","model":"inclusionai/ling-2.6-flash-20260421","category":"marketing/seo","count":416,"total_prompt_tokens":215950,"total_completion_tokens":435350,"volume":0.013935,"rank":36},{"date":"2026-08-23","model":"inclusionai/ling-2.6-flash-20260421","category":"roleplay","count":4676,"total_prompt_tokens":16727343,"total_completion_tokens":1487574,"volume":0.204542,"rank":36},{"date":"2026-08-23","model":"inclusionai/ling-2.6-flash-20260421","category":"translation","count":416,"total_prompt_tokens":684618,"total_completion_tokens":470899,"volume":0.021328,"rank":49}],"poolside/laguna-s-2.1-20260720:free":[{"date":"2026-08-23","model":"poolside/laguna-s-2.1-20260720","category":"programming","count":527,"total_prompt_tokens":50471748,"total_completion_tokens":641074,"volume":0.804867,"rank":41}],"google/gemma-3-12b-it":[{"date":"2026-08-23","model":"google/gemma-3-12b-it","category":"marketing/seo","count":62,"total_prompt_tokens":255250,"total_completion_tokens":33100,"volume":0.017198,"rank":49},{"date":"2026-08-23","model":"google/gemma-3-12b-it","category":"roleplay","count":2444,"total_prompt_tokens":14724822,"total_completion_tokens":3020753,"volume":1.014605,"rank":37}],"nvidia/nemotron-3-ultra-550b-a55b-20260604:free":[{"date":"2026-08-23","model":"nvidia/nemotron-3-ultra-550b-a55b-20260604","category":"trivia","count":34,"total_prompt_tokens":443087,"total_completion_tokens":35254,"volume":0.257854,"rank":35}],"nvidia/nemotron-3.5-lightning-20260807:free":[{"date":"2026-08-23","model":"nvidia/nemotron-3.5-lightning-20260807","category":"technology","count":1165,"total_prompt_tokens":46278865,"total_completion_tokens":1101631,"volume":3.115007,"rank":46}],"z-ai/glm-5v-turbo-20260401":[{"date":"2026-08-23","model":"z-ai/glm-5v-turbo-20260401","category":"programming","count":1733,"total_prompt_tokens":79789332,"total_completion_tokens":861720,"volume":33.839468,"rank":35},{"date":"2026-08-23","model":"z-ai/glm-5v-turbo-20260401","category":"technology","count":1089,"total_prompt_tokens":51015800,"total_completion_tokens":612000,"volume":22.166374,"rank":42}],"moonshotai/kimi-k2.7-code-20260612":[{"date":"2026-08-23","model":"moonshotai/kimi-k2.7-code-20260612","category":"programming","count":1209,"total_prompt_tokens":59172051,"total_completion_tokens":1702991,"volume":25.705096,"rank":38}],"openai/gpt-5.3-codex-20260224":[{"date":"2026-08-23","model":"openai/gpt-5.3-codex-20260224","category":"programming","count":917,"total_prompt_tokens":49780554,"total_completion_tokens":271037,"volume":22.734618,"rank":42}],"qwen/qwen3.6-35b-a3b-20260415":[{"date":"2026-08-23","model":"qwen/qwen3.6-35b-a3b-20260415","category":"programming","count":3272,"total_prompt_tokens":39750234,"total_completion_tokens":2419399,"volume":7.187084,"rank":44}],"meta/muse-spark-1.1-20260709":[{"date":"2026-08-23","model":"meta/muse-spark-1.1-20260709","category":"programming","count":461,"total_prompt_tokens":37104410,"total_completion_tokens":182192,"volume":14.652966,"rank":50}],"z-ai/glm-4.7-20251222":[{"date":"2026-08-23","model":"z-ai/glm-4.7-20251222","category":"roleplay","count":3139,"total_prompt_tokens":52017679,"total_completion_tokens":3438326,"volume":17.003752,"rank":16}],"google/gemini-2.5-pro":[{"date":"2026-08-23","model":"google/gemini-2.5-pro","category":"roleplay","count":2474,"total_prompt_tokens":43549731,"total_completion_tokens":3286312,"volume":49.275852,"rank":19},{"date":"2026-08-23","model":"google/gemini-2.5-pro","category":"translation","count":283,"total_prompt_tokens":848324,"total_completion_tokens":381434,"volume":4.215274,"rank":46}],"z-ai/glm-5-20260211":[{"date":"2026-08-23","model":"z-ai/glm-5-20260211","category":"roleplay","count":2024,"total_prompt_tokens":35424807,"total_completion_tokens":1883924,"volume":14.824047,"rank":22}],"z-ai/glm-5.1-20260406":[{"date":"2026-08-23","model":"z-ai/glm-5.1-20260406","category":"roleplay","count":1725,"total_prompt_tokens":23673010,"total_completion_tokens":1207515,"volume":17.690595,"rank":25}],"deepseek/deepseek-chat-v3.1":[{"date":"2026-08-23","model":"deepseek/deepseek-chat-v3.1","category":"roleplay","count":4474,"total_prompt_tokens":23771334,"total_completion_tokens":836141,"volume":7.44522,"rank":27}],"moonshotai/kimi-k2.5-0127":[{"date":"2026-08-23","model":"moonshotai/kimi-k2.5-0127","category":"roleplay","count":1221,"total_prompt_tokens":22360899,"total_completion_tokens":1631993,"volume":8.229178,"rank":29}],"deepseek/deepseek-chat-v3-0324":[{"date":"2026-08-23","model":"deepseek/deepseek-chat-v3-0324","category":"roleplay","count":2690,"total_prompt_tokens":22298284,"total_completion_tokens":820738,"volume":6.707064,"rank":30}],"x-ai/grok-4.20-20260309":[{"date":"2026-08-23","model":"x-ai/grok-4.20-20260309","category":"roleplay","count":2166,"total_prompt_tokens":21246647,"total_completion_tokens":1101945,"volume":21.827991,"rank":32},{"date":"2026-08-23","model":"x-ai/grok-4.20-20260309","category":"trivia","count":191,"total_prompt_tokens":260350,"total_completion_tokens":41450,"volume":0.518967,"rank":50}],"meta-llama/llama-4-maverick-17b-128e-instruct":[{"date":"2026-08-23","model":"meta-llama/llama-4-maverick-17b-128e-instruct","category":"roleplay","count":5640,"total_prompt_tokens":17208216,"total_completion_tokens":267735,"volume":3.574176,"rank":38}],"deepseek/deepseek-r1-0528":[{"date":"2026-08-23","model":"deepseek/deepseek-r1-0528","category":"roleplay","count":1001,"total_prompt_tokens":14244325,"total_completion_tokens":1127261,"volume":7.477014,"rank":43}],"deepseek/deepseek-v3.2-exp":[{"date":"2026-08-23","model":"deepseek/deepseek-v3.2-exp","category":"roleplay","count":1028,"total_prompt_tokens":13985175,"total_completion_tokens":1230017,"volume":3.700962,"rank":44}],"qwen/qwen3-32b-04-28":[{"date":"2026-08-23","model":"qwen/qwen3-32b-04-28","category":"science","count":3562,"total_prompt_tokens":21426466,"total_completion_tokens":1629212,"volume":2.437827,"rank":42}],"meta-llama/llama-3.1-8b-instruct":[{"date":"2026-08-23","model":"meta-llama/llama-3.1-8b-instruct","category":"translation","count":38769,"total_prompt_tokens":44910916,"total_completion_tokens":1678873,"volume":1.723094,"rank":4},{"date":"2026-08-23","model":"meta-llama/llama-3.1-8b-instruct","category":"trivia","count":475,"total_prompt_tokens":407050,"total_completion_tokens":3650,"volume":0.012411,"rank":38}],"qwen/qwen3.5-flash-20260224":[{"date":"2026-08-23","model":"qwen/qwen3.5-flash-20260224","category":"translation","count":1669,"total_prompt_tokens":3833175,"total_completion_tokens":400772,"volume":0.310441,"rank":26}],"meta/muse-glimmer-30b-20260810":[{"date":"2026-08-22","model":"meta/muse-glimmer-30b-20260810","category":"translation","count":89,"total_prompt_tokens":3542450,"total_completion_tokens":48400,"volume":0.354218,"rank":28}],"qwen/qwen3.5-9b-20260310":[{"date":"2026-08-23","model":"qwen/qwen3.5-9b-20260310","category":"translation","count":397,"total_prompt_tokens":513409,"total_completion_tokens":2277484,"volume":0.477228,"rank":34}],"openai/gpt-4o":[{"date":"2026-08-23","model":"openai/gpt-4o","category":"translation","count":737,"total_prompt_tokens":2296731,"total_completion_tokens":108791,"volume":4.087082,"rank":36}],"mistralai/ministral-14b-2512":[{"date":"2026-08-23","model":"mistralai/ministral-14b-2512","category":"translation","count":232,"total_prompt_tokens":870083,"total_completion_tokens":820234,"volume":0.269842,"rank":42}],"openai/gpt-4o-mini-2024-07-18":[{"date":"2026-08-23","model":"openai/gpt-4o-mini-2024-07-18","category":"trivia","count":936,"total_prompt_tokens":481450,"total_completion_tokens":5700,"volume":0.069696,"rank":32}]},"modality_counts":{"video":25,"text":417,"embeddings":35,"transcription":19,"image":43,"rerank":7,"speech":18,"audio":4},"benchmarks":{"z-ai/glm-5.3-20260816":{"aa":{"intelligence_index":59.5,"coding_index":74.8,"agentic_index":59.1}},"qwen/qwen3.8-27b-20260814":{"aa":{"intelligence_index":52,"coding_index":68.1,"agentic_index":50.9}},"google/gemini-3.7-flash-20260813":{"aa":{"intelligence_index":56,"coding_index":76.1,"agentic_index":45.1},"da":{"default_elo":1331,"elo_by_category":{"models-3d":1360,"models-codecategories":1331,"models-dataviz":1348,"models-gamedev":1348,"models-uicomponent":1315,"models-website":1323}}},"qwen/qwen3.8-2.4t-a95b-20260812":{"aa":{"intelligence_index":57.7,"coding_index":71.9,"agentic_index":57.1}},"deepseek/deepseek-v4-pro-20260813":{"aa":{"intelligence_index":53.2,"coding_index":68.8,"agentic_index":49.6}},"x-ai/grok-4.6-20260810":{"aa":{"intelligence_index":60.9,"coding_index":76.8,"agentic_index":58.7},"da":{"default_elo":1326,"elo_by_category":{"models-3d":1327,"models-asciiart":1304,"models-codecategories":1326,"models-dataviz":1313,"models-gamedev":1340,"models-svg":1278,"models-uicomponent":1341,"models-website":1322}}},"nvidia/nemotron-3.5-lightning-20260807":{"aa":{"intelligence_index":23.6,"coding_index":26.8,"agentic_index":13.8}},"upstage/solar-pro4-20260810":{"aa":{"intelligence_index":41.6,"coding_index":52.7,"agentic_index":33.6},"da":{"default_elo":1179,"elo_by_category":{"models-3d":1179,"models-codecategories":1179,"models-dataviz":1100,"models-gamedev":1150,"models-uicomponent":1175,"models-website":1187}}},"meta/muse-spark-1.2-20260805":{"aa":{"intelligence_index":56.8,"coding_index":72.2,"agentic_index":49.3},"da":{"default_elo":1344,"elo_by_category":{"models-3d":1346,"models-codecategories":1344,"models-dataviz":1367,"models-gamedev":1352,"models-uicomponent":1351,"models-website":1335}}},"qwen/qwen3.8-max-20260803":{"aa":{"intelligence_index":58.1,"coding_index":71.8,"agentic_index":58.4},"da":{"default_elo":1321,"elo_by_category":{"models-3d":1377,"models-codecategories":1321,"models-dataviz":1271,"models-gamedev":1340,"models-uicomponent":1360,"models-website":1302}}},"deepseek/deepseek-v4-flash-20260731":{"aa":{"intelligence_index":51.8,"coding_index":69.1,"agentic_index":48.4},"da":{"default_elo":1258,"elo_by_category":{"models-3d":1255,"models-codecategories":1258,"models-dataviz":1194,"models-gamedev":1249,"models-uicomponent":1268,"models-website":1262}}},"thinkingmachines/inkling-small-20260730":{"aa":{"intelligence_index":41.2,"coding_index":52.9,"agentic_index":31.9}},"anthropic/claude-opus-5-20260723":{"aa":{"intelligence_index":63.1,"coding_index":78,"agentic_index":59.2},"da":{"default_elo":1349,"elo_by_category":{"models-3d":1380,"models-codecategories":1349,"models-dataviz":1358,"models-gamedev":1382,"models-svg":1364,"models-uicomponent":1372,"models-website":1332}}},"inclusionai/ling-3.0-flash-20260723":{"aa":{"intelligence_index":37.8,"coding_index":50.6,"agentic_index":29.3}},"google/gemini-3.6-flash-20260721":{"aa":{"intelligence_index":51.6,"coding_index":69.2,"agentic_index":40.5},"da":{"default_elo":1319,"elo_by_category":{"models-3d":1323,"models-asciiart":1288,"models-codecategories":1319,"models-dataviz":1322,"models-gamedev":1297,"models-uicomponent":1331,"models-website":1323}}},"google/gemini-3.5-flash-lite-20260721":{"aa":{"intelligence_index":37.4,"coding_index":49.3,"agentic_index":27.2}},"meituan/longcat-2.0-20260720":{"aa":{"intelligence_index":34,"coding_index":45.3,"agentic_index":22}},"thinkingmachines/inkling-20260715":{"aa":{"intelligence_index":42.3,"coding_index":52.1,"agentic_index":34.1},"da":{"default_elo":1218,"elo_by_category":{"models-3d":1205,"models-asciiart":1130,"models-codecategories":1218,"models-dataviz":1200,"models-gamedev":1193,"models-uicomponent":1206,"models-website":1226}}},"moonshotai/kimi-k3-20260715":{"aa":{"intelligence_index":59.7,"coding_index":76.2,"agentic_index":54.3},"da":{"default_elo":1407,"elo_by_category":{"models-3d":1445,"models-codecategories":1407,"models-dataviz":1375,"models-gamedev":1431,"models-svg":1356,"models-uicomponent":1377,"models-website":1372}}},"meta/muse-spark-1.1-20260709":{"aa":{"intelligence_index":53.2,"coding_index":71.3,"agentic_index":39.7},"da":{"default_elo":1303,"elo_by_category":{"models-3d":1301,"models-asciiart":1321,"models-codecategories":1303,"models-dataviz":1303,"models-gamedev":1317,"models-svg":1271,"models-uicomponent":1321,"models-website":1290}}},"openai/gpt-5.6-luna-20260709":{"aa":{"intelligence_index":52.3,"coding_index":71.4,"agentic_index":46.9}},"openai/gpt-5.6-terra-20260709":{"aa":{"intelligence_index":56.6,"coding_index":76.7,"agentic_index":50.2}},"openai/gpt-5.6-sol-20260709":{"aa":{"intelligence_index":60.9,"coding_index":77.4,"agentic_index":57.8}},"x-ai/grok-4.5-20260708":{"aa":{"intelligence_index":55.8,"coding_index":72.4,"agentic_index":48.9},"da":{"default_elo":1306,"elo_by_category":{"models-3d":1308,"models-asciiart":1293,"models-codecategories":1306,"models-dataviz":1297,"models-gamedev":1305,"models-svg":1266,"models-uicomponent":1309,"models-website":1307}}},"tencent/hy3-20260706":{"da":{"default_elo":1202,"elo_by_category":{"models-3d":1222,"models-codecategories":1202,"models-dataviz":1148,"models-gamedev":1173,"models-uicomponent":1190,"models-website":1203}}},"anthropic/claude-sonnet-5-20260630":{"aa":{"intelligence_index":55.3,"coding_index":71.5,"agentic_index":49.7},"da":{"default_elo":1301,"elo_by_category":{"models-3d":1304,"models-asciiart":1232,"models-codecategories":1301,"models-dataviz":1263,"models-gamedev":1329,"models-svg":1229,"models-uicomponent":1305,"models-website":1297}}},"cohere/north-mini-code-20260617":{"aa":{"intelligence_index":20.2,"coding_index":36.5,"agentic_index":3.1}},"z-ai/glm-5.2-20260616":{"aa":{"intelligence_index":52.6,"coding_index":68.8,"agentic_index":45.7},"da":{"default_elo":1331,"elo_by_category":{"models-3d":1347,"models-asciiart":1246,"models-codecategories":1331,"models-dataviz":1324,"models-gamedev":1322,"models-svg":1256,"models-uicomponent":1327,"models-website":1326}}},"moonshotai/kimi-k2.7-code-20260612":{"aa":{"intelligence_index":43,"coding_index":60.8,"agentic_index":30.3},"da":{"default_elo":1283,"elo_by_category":{"models-3d":1288,"models-asciiart":1239,"models-codecategories":1283,"models-dataviz":1242,"models-gamedev":1252,"models-svg":1217,"models-uicomponent":1292,"models-website":1292}}},"anthropic/claude-5-fable-20260609":{"aa":{"intelligence_index":62.1,"coding_index":76.5,"agentic_index":56.6},"da":{"default_elo":1339,"elo_by_category":{"models-3d":1365,"models-asciiart":1367,"models-codecategories":1339,"models-dataviz":1333,"models-gamedev":1383,"models-svg":1344,"models-uicomponent":1345,"models-website":1320}}},"nex-agi/nex-n2-pro":{"aa":{"intelligence_index":41.7,"coding_index":59.1,"agentic_index":31.2},"da":{"default_elo":1258,"elo_by_category":{"models-3d":1297,"models-asciiart":1127,"models-codecategories":1258,"models-dataviz":1251,"models-gamedev":1258,"models-svg":1241,"models-uicomponent":1245,"models-website":1242}}},"nvidia/nemotron-3-ultra-550b-a55b-20260604":{"aa":{"intelligence_index":38.3,"coding_index":49.3,"agentic_index":27.5},"da":{"default_elo":1159,"elo_by_category":{"models-3d":1179,"models-asciiart":1097,"models-codecategories":1159,"models-dataviz":1156,"models-gamedev":1160,"models-svg":1121,"models-uicomponent":1163,"models-website":1146}}},"qwen/qwen3.7-plus-20260602":{"aa":{"intelligence_index":39.4,"coding_index":55.9,"agentic_index":20.7},"da":{"default_elo":1289,"elo_by_category":{"models-3d":1287,"models-asciiart":1182,"models-codecategories":1289,"models-dataviz":1287,"models-gamedev":1293,"models-svg":1260,"models-uicomponent":1275,"models-website":1290}}},"minimax/minimax-m3-20260531":{"aa":{"intelligence_index":45.4,"coding_index":58.6,"agentic_index":36.1},"da":{"default_elo":1275,"elo_by_category":{"models-3d":1257,"models-asciiart":1185,"models-codecategories":1275,"models-dataviz":1255,"models-gamedev":1247,"models-svg":1211,"models-uicomponent":1273,"models-website":1280}}},"stepfun/step-3.7-flash-20260528":{"aa":{"intelligence_index":30.9,"coding_index":39.6,"agentic_index":21.7},"da":{"default_elo":1203,"elo_by_category":{"models-3d":1170,"models-asciiart":1181,"models-codecategories":1203,"models-dataviz":1193,"models-gamedev":1190,"models-svg":1113,"models-uicomponent":1200,"models-website":1212}}},"anthropic/claude-4.8-opus-20260528":{"aa":{"intelligence_index":57.3,"coding_index":74.3,"agentic_index":49.4},"da":{"default_elo":1273,"elo_by_category":{"models-3d":1268,"models-asciiart":1295,"models-codecategories":1273,"models-dataviz":1261,"models-gamedev":1290,"models-svg":1222,"models-uicomponent":1280,"models-website":1271}}},"qwen/qwen3.7-max-20260520":{"aa":{"intelligence_index":46.7,"coding_index":66,"agentic_index":30.9},"da":{"default_elo":1302,"elo_by_category":{"models-3d":1316,"models-asciiart":1241,"models-codecategories":1302,"models-dataviz":1298,"models-gamedev":1308,"models-svg":1261,"models-uicomponent":1298,"models-website":1294}}},"x-ai/grok-build-0.1-20260520":{"aa":{"intelligence_index":40.7,"coding_index":51.5,"agentic_index":28.9}},"google/gemini-3.5-flash-20260519":{"aa":{"intelligence_index":52,"coding_index":70.1,"agentic_index":39.7},"da":{"default_elo":1288,"elo_by_category":{"models-3d":1289,"models-asciiart":1284,"models-codecategories":1288,"models-dataviz":1258,"models-gamedev":1302,"models-svg":1292,"models-uicomponent":1301,"models-website":1282}}},"x-ai/grok-4.3-20260430":{"aa":{"intelligence_index":37.9,"coding_index":42.2,"agentic_index":24.2},"da":{"default_elo":1211,"elo_by_category":{"models-3d":1169,"models-asciiart":1161,"models-codecategories":1211,"models-dataviz":1203,"models-gamedev":1209,"models-svg":1125,"models-uicomponent":1219,"models-website":1213}}},"ibm-granite/granite-4.1-8b-20260429":{"aa":{"intelligence_index":null,"coding_index":9.5,"agentic_index":null}},"mistralai/mistral-medium-3.5-20260430":{"aa":{"intelligence_index":30.4,"coding_index":46.9,"agentic_index":19.2}},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428":{"aa":{"intelligence_index":null,"coding_index":13.8,"agentic_index":null}},"qwen/qwen3.6-35b-a3b-20260415":{"aa":{"intelligence_index":32.1,"coding_index":41.9,"agentic_index":21.6}},"qwen/qwen3.6-27b-20260422":{"aa":{"intelligence_index":37.7,"coding_index":53.7,"agentic_index":27.5}},"openai/gpt-5.5-20260423":{"aa":{"intelligence_index":56.3,"coding_index":74.9,"agentic_index":47.4},"da":{"default_elo":1284,"elo_by_category":{"models-3d":1243,"models-asciiart":1283,"models-codecategories":1284,"models-dataviz":1281,"models-gamedev":1337,"models-svg":1274,"models-uicomponent":1282,"models-website":1277}}},"deepseek/deepseek-v4-pro-20260423":{"aa":{"intelligence_index":45.3,"coding_index":59.4,"agentic_index":37.8},"da":{"default_elo":1267,"elo_by_category":{"models-3d":1302,"models-asciiart":1177,"models-codecategories":1267,"models-dataviz":1221,"models-gamedev":1269,"models-svg":1178,"models-uicomponent":1250,"models-website":1255}}},"deepseek/deepseek-v4-flash-20260423":{"aa":{"intelligence_index":42.1,"coding_index":56.2,"agentic_index":33.7},"da":{"default_elo":1230,"elo_by_category":{"models-3d":1234,"models-asciiart":1136,"models-codecategories":1230,"models-dataviz":1148,"models-gamedev":1233,"models-svg":1195,"models-uicomponent":1191,"models-website":1228}}},"tencent/hy3-preview-20260421":{"aa":{"intelligence_index":42.2,"coding_index":58.8,"agentic_index":31.4}},"xiaomi/mimo-v2.5-pro-20260422":{"aa":{"intelligence_index":42.9,"coding_index":60.2,"agentic_index":29.5},"da":{"default_elo":1298,"elo_by_category":{"models-3d":1294,"models-asciiart":1176,"models-codecategories":1298,"models-dataviz":1286,"models-gamedev":1301,"models-svg":1224,"models-uicomponent":1288,"models-website":1296}}},"xiaomi/mimo-v2.5-20260422":{"aa":{"intelligence_index":38,"coding_index":56.8,"agentic_index":24.4},"da":{"default_elo":1285,"elo_by_category":{"models-3d":1259,"models-asciiart":1159,"models-codecategories":1285,"models-dataviz":1273,"models-gamedev":1278,"models-svg":1215,"models-uicomponent":1285,"models-website":1288}}},"moonshotai/kimi-k2.6-20260420":{"aa":{"intelligence_index":45.1,"coding_index":61.8,"agentic_index":31.2},"da":{"default_elo":1299,"elo_by_category":{"models-3d":1315,"models-asciiart":1186,"models-codecategories":1299,"models-dataviz":1274,"models-gamedev":1288,"models-svg":1223,"models-uicomponent":1295,"models-website":1292}}},"anthropic/claude-4.7-opus-20260416":{"aa":{"intelligence_index":55,"coding_index":73.6,"agentic_index":46.3},"da":{"default_elo":1316,"elo_by_category":{"models-3d":1296,"models-asciiart":1309,"models-codecategories":1316,"models-dataviz":1310,"models-gamedev":1327,"models-svg":1265,"models-uicomponent":1332,"models-website":1315}}},"z-ai/glm-5.1-20260406":{"aa":{"intelligence_index":41,"coding_index":55.8,"agentic_index":30.6},"da":{"default_elo":1294,"elo_by_category":{"models-3d":1336,"models-asciiart":1159,"models-codecategories":1294,"models-dataviz":1366,"models-gamedev":1298,"models-svg":1259,"models-uicomponent":1294,"models-website":1290}}},"google/gemma-4-26b-a4b-it-20260403":{"aa":{"intelligence_index":26.1,"coding_index":39.3,"agentic_index":11}},"google/gemma-4-31b-it-20260402":{"aa":{"intelligence_index":29.7,"coding_index":43.4,"agentic_index":14.4}},"qwen/qwen3.6-plus-04-02":{"aa":{"intelligence_index":40.5,"coding_index":54.5,"agentic_index":29},"da":{"default_elo":1260,"elo_by_category":{"models-3d":1246,"models-asciiart":1130,"models-codecategories":1260,"models-dataviz":1250,"models-gamedev":1244,"models-svg":1203,"models-uicomponent":1264,"models-website":1261}}},"z-ai/glm-5v-turbo-20260401":{"da":{"default_elo":1254,"elo_by_category":{"models-3d":1255,"models-asciiart":1134,"models-codecategories":1254,"models-dataviz":1219,"models-gamedev":1253,"models-svg":1192,"models-uicomponent":1241,"models-website":1251}}},"arcee-ai/trinity-large-thinking":{"aa":{"intelligence_index":18.7,"coding_index":25.8,"agentic_index":3.7},"da":{"default_elo":1142,"elo_by_category":{"models-3d":1127,"models-asciiart":1066,"models-codecategories":1142,"models-dataviz":1120,"models-gamedev":1115,"models-svg":1057,"models-uicomponent":1072,"models-website":1157}}},"x-ai/grok-4.20-20260309":{"da":{"default_elo":1245,"elo_by_category":{"models-3d":1238,"models-asciiart":1204,"models-codecategories":1245,"models-dataviz":1240,"models-gamedev":1232,"models-svg":1203,"models-uicomponent":1229,"models-website":1249}}},"kwaipilot/kat-coder-pro-v2-20260327":{"aa":{"intelligence_index":33.7,"coding_index":59.5,"agentic_index":15.1}},"minimax/minimax-m2.7-20260318":{"aa":{"intelligence_index":38.9,"coding_index":52.6,"agentic_index":25.9},"da":{"default_elo":1259,"elo_by_category":{"models-3d":1240,"models-asciiart":1166,"models-codecategories":1259,"models-dataviz":1251,"models-gamedev":1244,"models-svg":1178,"models-uicomponent":1237,"models-website":1266}}},"openai/gpt-5.4-nano-20260317":{"aa":{"intelligence_index":39.7,"coding_index":56.1,"agentic_index":29.7}},"openai/gpt-5.4-mini-20260317":{"aa":{"intelligence_index":40.9,"coding_index":56.1,"agentic_index":31.5}},"mistralai/mistral-small-2603":{"aa":{"intelligence_index":19.7,"coding_index":26.6,"agentic_index":4.6}},"z-ai/glm-5-turbo-20260315":{"da":{"default_elo":1292,"elo_by_category":{"models-3d":1297,"models-asciiart":1175,"models-codecategories":1292,"models-dataviz":1287,"models-gamedev":1291,"models-svg":1247,"models-uicomponent":1293,"models-website":1288}}},"nvidia/nemotron-3-super-120b-a12b-20230311":{"aa":{"intelligence_index":25.7,"coding_index":37.7,"agentic_index":8.8}},"qwen/qwen3.5-9b-20260310":{"aa":{"intelligence_index":21.8,"coding_index":28.7,"agentic_index":7}},"openai/gpt-5.4-20260305":{"aa":{"intelligence_index":53.1,"coding_index":71.1,"agentic_index":44.2},"da":{"default_elo":1237,"elo_by_category":{"models-3d":1147,"models-asciiart":1225,"models-codecategories":1237,"models-dataviz":1256,"models-gamedev":1275,"models-svg":1236,"models-uicomponent":1267,"models-website":1240}}},"inception/mercury-2-20260304":{"aa":{"intelligence_index":21.9,"coding_index":31.1,"agentic_index":9.5},"da":{"default_elo":1029,"elo_by_category":{"models-3d":1020,"models-asciiart":1034,"models-codecategories":1029,"models-dataviz":1019,"models-gamedev":1007,"models-svg":1022,"models-uicomponent":1001,"models-website":1035}}},"google/gemini-3.1-flash-lite-preview-20260303":{"aa":{"intelligence_index":25.6,"coding_index":34.7,"agentic_index":6.5},"da":{"default_elo":1097,"elo_by_category":{"models-3d":1093,"models-asciiart":1193,"models-codecategories":1097,"models-dataviz":1067,"models-gamedev":1065,"models-svg":1093,"models-uicomponent":1099,"models-website":1103}}},"google/gemini-3.1-flash-image-preview-20260226":{"da":{"default_elo":null,"elo_by_category":{"models-graphicdesign":1286,"models-image":1296,"models-logo":1275}}},"qwen/qwen3.5-35b-a3b-20260224":{"aa":{"intelligence_index":24.3,"coding_index":37,"agentic_index":11.8}},"qwen/qwen3.5-122b-a10b-20260224":{"aa":{"intelligence_index":32.8,"coding_index":45.7,"agentic_index":21.3}},"openai/gpt-5.3-codex-20260224":{"da":{"default_elo":1170,"elo_by_category":{"models-3d":1054,"models-asciiart":1177,"models-codecategories":1170,"models-dataviz":1186,"models-gamedev":1198,"models-svg":1170,"models-uicomponent":1165,"models-website":1183}}},"google/gemini-3.1-pro-preview-20260219":{"aa":{"intelligence_index":47.7,"coding_index":68.8,"agentic_index":23},"da":{"default_elo":1269,"elo_by_category":{"models-3d":1280,"models-asciiart":1297,"models-codecategories":1269,"models-dataviz":1260,"models-gamedev":1238,"models-svg":1329,"models-uicomponent":1307,"models-website":1273}}},"anthropic/claude-4.6-sonnet-20260217":{"aa":{"intelligence_index":48.4,"coding_index":63,"agentic_index":42.1},"da":{"default_elo":1301,"elo_by_category":{"models-3d":1280,"models-asciiart":1259,"models-codecategories":1301,"models-dataviz":1301,"models-gamedev":1296,"models-svg":1238,"models-uicomponent":1299,"models-website":1305}}},"qwen/qwen3.5-plus-20260216":{"da":{"default_elo":1192,"elo_by_category":{"models-3d":1165,"models-asciiart":1119,"models-codecategories":1192,"models-dataviz":1158,"models-gamedev":1142,"models-svg":1149,"models-uicomponent":1205,"models-website":1208}}},"qwen/qwen3.5-397b-a17b-20260216":{"aa":{"intelligence_index":34.3,"coding_index":48.2,"agentic_index":19.8},"da":{"default_elo":1205,"elo_by_category":{"models-3d":1207,"models-codecategories":1205,"models-dataviz":1197,"models-gamedev":1176,"models-svg":1181,"models-uicomponent":1191,"models-website":1211}}},"minimax/minimax-m2.5-20260211":{"da":{"default_elo":1232,"elo_by_category":{"models-3d":1216,"models-codecategories":1232,"models-dataviz":1194,"models-gamedev":1213,"models-svg":1191,"models-uicomponent":1200,"models-website":1242}}},"z-ai/glm-5-20260211":{"da":{"default_elo":1272,"elo_by_category":{"models-3d":1274,"models-asciiart":1173,"models-codecategories":1272,"models-dataviz":1250,"models-gamedev":1270,"models-svg":1209,"models-uicomponent":1258,"models-website":1268}}},"anthropic/claude-4.6-opus-20260205":{"da":{"default_elo":1314,"elo_by_category":{"models-3d":1320,"models-asciiart":1278,"models-codecategories":1314,"models-dataviz":1303,"models-gamedev":1315,"models-svg":1269,"models-uicomponent":1312,"models-website":1312}}},"qwen/qwen3-coder-next-2025-02-03":{"aa":{"intelligence_index":21.3,"coding_index":36.2,"agentic_index":8.9}},"moonshotai/kimi-k2.5-0127":{"aa":{"intelligence_index":36,"coding_index":46.8,"agentic_index":21.7},"da":{"default_elo":1262,"elo_by_category":{"models-3d":1251,"models-asciiart":1196,"models-codecategories":1262,"models-dataviz":1241,"models-gamedev":1243,"models-svg":1190,"models-uicomponent":1264,"models-website":1269}}},"upstage/solar-pro-3":{"aa":{"intelligence_index":14.5,"coding_index":16.2,"agentic_index":2.9}},"z-ai/glm-4.7-flash-20260119":{"da":{"default_elo":1202,"elo_by_category":{"models-3d":1166,"models-codecategories":1202,"models-dataviz":1145,"models-gamedev":1171,"models-svg":1079,"models-uicomponent":1235,"models-website":1214}}},"minimax/minimax-m2.1":{"da":{"default_elo":1215,"elo_by_category":{"models-3d":1211,"models-codecategories":1215,"models-dataviz":1228,"models-gamedev":1171,"models-svg":1173,"models-uicomponent":1250,"models-website":1221}}},"z-ai/glm-4.7-20251222":{"aa":{"intelligence_index":34.5,"coding_index":45.3,"agentic_index":26.2},"da":{"default_elo":1242,"elo_by_category":{"models-3d":1236,"models-asciiart":1192,"models-codecategories":1242,"models-dataviz":1217,"models-gamedev":1224,"models-svg":1184,"models-uicomponent":1227,"models-website":1246}}},"google/gemini-3-flash-preview-20251217":{"da":{"default_elo":1214,"elo_by_category":{"models-3d":1229,"models-codecategories":1214,"models-gamedev":1202,"models-website":1216}}},"nvidia/nemotron-3-nano-30b-a3b":{"aa":{"intelligence_index":14.5,"coding_index":14.4,"agentic_index":2}},"openai/gpt-5.2-20251211":{"da":{"default_elo":1195,"elo_by_category":{"models-website":1215,"models-3d":1125,"models-codecategories":1195,"models-dataviz":1222,"models-gamedev":1231,"models-uicomponent":1218,"models-asciiart":1178,"models-svg":1180}}},"mistralai/devstral-2512":{"aa":{"intelligence_index":19.2,"coding_index":31.3,"agentic_index":10.6}},"amazon/nova-2-lite-v1":{"aa":{"intelligence_index":null,"coding_index":23,"agentic_index":null}},"mistralai/ministral-14b-2512":{"aa":{"intelligence_index":11.2,"coding_index":14.4,"agentic_index":2.2},"da":{"default_elo":1090,"elo_by_category":{"models-3d":1036,"models-codecategories":1090,"models-gamedev":1074,"models-website":1101}}},"mistralai/ministral-8b-2512":{"aa":{"intelligence_index":9,"coding_index":9.7,"agentic_index":1.2},"da":{"default_elo":1078,"elo_by_category":{"models-3d":1077,"models-codecategories":1078,"models-gamedev":1026,"models-website":1085}}},"mistralai/ministral-3b-2512":{"aa":{"intelligence_index":7.1,"coding_index":4.8,"agentic_index":1.6},"da":{"default_elo":1035,"elo_by_category":{"models-3d":1008,"models-codecategories":1035,"models-gamedev":985,"models-website":1048}}},"mistralai/mistral-large-2512":{"aa":{"intelligence_index":15.9,"coding_index":20.1,"agentic_index":5.5},"da":{"default_elo":1167,"elo_by_category":{"models-3d":1145,"models-asciiart":1094,"models-codecategories":1167,"models-dataviz":1158,"models-gamedev":1116,"models-svg":1034,"models-uicomponent":1129,"models-website":1182}}},"deepseek/deepseek-v3.2-20251201":{"aa":{"intelligence_index":null,"coding_index":44.2,"agentic_index":null},"da":{"default_elo":1189,"elo_by_category":{"models-3d":1179,"models-asciiart":1108,"models-codecategories":1189,"models-dataviz":1180,"models-gamedev":1168,"models-svg":1073,"models-uicomponent":1176,"models-website":1195}}},"anthropic/claude-4.5-opus-20251124":{"da":{"default_elo":1267,"elo_by_category":{"models-3d":1260,"models-asciiart":1215,"models-codecategories":1267,"models-dataviz":1264,"models-gamedev":1265,"models-svg":1222,"models-uicomponent":1265,"models-website":1267}}},"google/gemini-3-pro-image-preview-20251120":{"da":{"default_elo":null,"elo_by_category":{"models-graphicdesign":1276,"models-image":1263,"models-logo":1253,"models-imageediting":1276}}},"openai/gpt-5.1-20251113":{"aa":{"intelligence_index":37.5,"coding_index":49.4,"agentic_index":21.6},"da":{"default_elo":1196,"elo_by_category":{"models-3d":1107,"models-asciiart":1144,"models-codecategories":1196,"models-dataviz":1226,"models-gamedev":1215,"models-svg":1190,"models-uicomponent":1194,"models-website":1207}}},"openai/gpt-5.1-codex-20251113":{"da":{"default_elo":1177,"elo_by_category":{"models-codecategories":1177,"models-dataviz":1235,"models-gamedev":1174,"models-uicomponent":1264,"models-website":1182}}},"openai/gpt-5.1-codex-mini-20251113":{"da":{"default_elo":1119,"elo_by_category":{"models-3d":1034,"models-asciiart":1130,"models-codecategories":1119,"models-dataviz":1119,"models-gamedev":1129,"models-svg":1019,"models-uicomponent":1108,"models-website":1131}}},"moonshotai/kimi-k2-thinking-20251106":{"aa":{"intelligence_index":null,"coding_index":21,"agentic_index":null},"da":{"default_elo":null,"elo_by_category":{"models-website":1133}}},"amazon/nova-premier-v1":{"da":{"default_elo":null,"elo_by_category":{"models-website":855}}},"minimax/minimax-m2":{"da":{"default_elo":1160,"elo_by_category":{"models-3d":1143,"models-codecategories":1160,"models-dataviz":1162,"models-gamedev":1154,"models-svg":1141,"models-uicomponent":1164,"models-website":1163}}},"openai/gpt-5-image-mini":{"da":{"default_elo":null,"elo_by_category":{"models-graphicdesign":1190,"models-image":1203,"models-logo":1221}}},"anthropic/claude-4.5-haiku-20251001":{"aa":{"intelligence_index":29.9,"coding_index":43.9,"agentic_index":16.5},"da":{"default_elo":1140,"elo_by_category":{"models-3d":1118,"models-asciiart":1166,"models-codecategories":1140,"models-dataviz":1146,"models-gamedev":1133,"models-svg":1066,"models-uicomponent":1127,"models-website":1142}}},"openai/gpt-5-image":{"da":{"default_elo":null,"elo_by_category":{"models-graphicdesign":1197,"models-image":1211,"models-logo":1214}}},"google/gemini-2.5-flash-image":{"da":{"default_elo":null,"elo_by_category":{"models-graphicdesign":1193,"models-image":1206,"models-logo":1181}}},"z-ai/glm-4.6":{"aa":{"intelligence_index":29.3,"coding_index":45.8,"agentic_index":18.6},"da":{"default_elo":1190,"elo_by_category":{"models-3d":1174,"models-codecategories":1190,"models-dataviz":1183,"models-gamedev":1187,"models-svg":1150,"models-uicomponent":1175,"models-website":1194}}},"anthropic/claude-4.5-sonnet-20250929":{"aa":{"intelligence_index":37.4,"coding_index":52.1,"agentic_index":26.4},"da":{"default_elo":1208,"elo_by_category":{"models-3d":1203,"models-asciiart":1231,"models-codecategories":1208,"models-dataviz":1189,"models-gamedev":1202,"models-svg":1156,"models-uicomponent":1200,"models-website":1210}}},"deepseek/deepseek-v3.2-exp":{"da":{"default_elo":1196,"elo_by_category":{"models-3d":1194,"models-codecategories":1196,"models-dataviz":1174,"models-gamedev":1181,"models-svg":1073,"models-uicomponent":1194,"models-website":1199}}},"qwen/qwen3-max":{"da":{"default_elo":1135,"elo_by_category":{"models-3d":1119,"models-asciiart":1153,"models-codecategories":1135,"models-dataviz":1122,"models-gamedev":1131,"models-svg":1052,"models-uicomponent":1105,"models-website":1139}}},"deepseek/deepseek-v3.1-terminus":{"aa":{"intelligence_index":31.4,"coding_index":43.5,"agentic_index":19.9},"da":{"default_elo":1200,"elo_by_category":{"models-3d":1186,"models-codecategories":1200,"models-dataviz":1189,"models-gamedev":1167,"models-svg":1106,"models-uicomponent":1210,"models-website":1207}}},"qwen/qwen3-next-80b-a3b-thinking-2509":{"aa":{"intelligence_index":16.9,"coding_index":17.4,"agentic_index":2.1}},"moonshotai/kimi-k2-0905":{"da":{"default_elo":1123,"elo_by_category":{"models-codecategories":1123,"models-website":1127}}},"qwen/qwen3-30b-a3b-thinking-2507":{"aa":{"intelligence_index":14.6,"coding_index":12.1,"agentic_index":1.8},"da":{"default_elo":null,"elo_by_category":{"models-dataviz":946,"models-website":950}}},"deepseek/deepseek-chat-v3.1":{"da":{"default_elo":1137,"elo_by_category":{"models-3d":1122,"models-codecategories":1137,"models-dataviz":1117,"models-gamedev":1120,"models-svg":1008,"models-uicomponent":1112,"models-website":1143}}},"mistralai/mistral-medium-3.1":{"aa":{"intelligence_index":14.7,"coding_index":20.5,"agentic_index":6.1},"da":{"default_elo":1145,"elo_by_category":{"models-3d":1127,"models-asciiart":1023,"models-codecategories":1145,"models-dataviz":1166,"models-gamedev":1110,"models-svg":1034,"models-uicomponent":1127,"models-website":1153}}},"openai/gpt-5-2025-08-07":{"aa":{"intelligence_index":35.3,"coding_index":37.8,"agentic_index":26.5},"da":{"default_elo":1193,"elo_by_category":{"models-3d":1101,"models-asciiart":1166,"models-codecategories":1193,"models-dataviz":1243,"models-gamedev":1221,"models-svg":1230,"models-uicomponent":1207,"models-website":1205}}},"openai/gpt-5-mini-2025-08-07":{"aa":{"intelligence_index":25.8,"coding_index":15.6,"agentic_index":19.6},"da":{"default_elo":1140,"elo_by_category":{"models-3d":1083,"models-asciiart":1148,"models-codecategories":1140,"models-dataviz":1152,"models-gamedev":1165,"models-svg":1132,"models-uicomponent":1133,"models-website":1145}}},"openai/gpt-5-nano-2025-08-07":{"da":{"default_elo":1109,"elo_by_category":{"models-3d":1011,"models-codecategories":1109,"models-dataviz":1077,"models-gamedev":1081,"models-uicomponent":1094,"models-website":1121}}},"openai/gpt-oss-120b":{"aa":{"intelligence_index":24.1,"coding_index":30.4,"agentic_index":13.4},"da":{"default_elo":988,"elo_by_category":{"models-3d":946,"models-codecategories":988,"models-dataviz":1008,"models-gamedev":1028,"models-uicomponent":954,"models-website":988}}},"openai/gpt-oss-20b":{"aa":{"intelligence_index":15.2,"coding_index":20.7,"agentic_index":3.1},"da":{"default_elo":null,"elo_by_category":{"models-dataviz":953,"models-website":873}}},"anthropic/claude-4.1-opus-20250805":{"da":{"default_elo":1196,"elo_by_category":{"models-3d":1199,"models-asciiart":1192,"models-codecategories":1196,"models-dataviz":1187,"models-gamedev":1207,"models-svg":1193,"models-uicomponent":1192,"models-website":1197}}},"mistralai/codestral-2508":{"da":{"default_elo":1032,"elo_by_category":{"models-codecategories":1032,"models-dataviz":1038,"models-gamedev":1004,"models-uicomponent":1044,"models-website":1033,"models-3d":1065}}},"qwen/qwen3-coder-30b-a3b-instruct":{"da":{"default_elo":null,"elo_by_category":{"models-dataviz":1104,"models-uicomponent":1073,"models-website":1107}}},"z-ai/glm-4.5":{"da":{"default_elo":1190,"elo_by_category":{"models-3d":1216,"models-codecategories":1190,"models-dataviz":1181,"models-gamedev":1181,"models-svg":1137,"models-uicomponent":1171,"models-website":1190}}},"z-ai/glm-4.5-air":{"da":{"default_elo":1162,"elo_by_category":{"models-3d":1168,"models-codecategories":1162,"models-dataviz":1208,"models-gamedev":1130,"models-svg":1112,"models-uicomponent":1150,"models-website":1167}}},"qwen/qwen3-235b-a22b-thinking-2507":{"aa":{"intelligence_index":19.9,"coding_index":22.1,"agentic_index":3.8},"da":{"default_elo":1058,"elo_by_category":{"models-3d":1043,"models-codecategories":1058,"models-dataviz":970,"models-gamedev":993,"models-uicomponent":972,"models-website":1073}}},"qwen/qwen3-coder-480b-a35b-07-25":{"da":{"default_elo":1168,"elo_by_category":{"models-codecategories":1168,"models-dataviz":1103,"models-gamedev":1135,"models-uicomponent":1140,"models-website":1179}}},"qwen/qwen3-235b-a22b-07-25":{"da":{"default_elo":1063,"elo_by_category":{"models-3d":1040,"models-codecategories":1063,"models-dataviz":1090,"models-gamedev":988,"models-uicomponent":992,"models-website":1078}}},"moonshotai/kimi-k2":{"da":{"default_elo":1058,"elo_by_category":{"models-codecategories":1058,"models-dataviz":1037,"models-gamedev":1010,"models-uicomponent":1057,"models-website":1070}}},"mistralai/mistral-small-3.2-24b-instruct-2506":{"da":{"default_elo":932,"elo_by_category":{"models-codecategories":932,"models-dataviz":949,"models-gamedev":925,"models-uicomponent":934,"models-website":916}}},"google/gemini-2.5-flash":{"da":{"default_elo":1129,"elo_by_category":{"models-3d":1117,"models-codecategories":1129,"models-dataviz":1155,"models-gamedev":1102,"models-uicomponent":1120,"models-website":1135,"models-svg":1061}}},"google/gemini-2.5-pro":{"aa":{"intelligence_index":25.9,"coding_index":33.3,"agentic_index":7.2},"da":{"default_elo":1177,"elo_by_category":{"models-3d":1126,"models-codecategories":1177,"models-dataviz":1243,"models-gamedev":1148,"models-uicomponent":1167,"models-website":1187}}},"deepseek/deepseek-r1-0528":{"da":{"default_elo":1163,"elo_by_category":{"models-3d":1157,"models-codecategories":1163,"models-dataviz":1203,"models-gamedev":1133,"models-svg":1080,"models-uicomponent":1130,"models-website":1169}}},"anthropic/claude-4-opus-20250522":{"da":{"default_elo":1186,"elo_by_category":{"models-3d":1184,"models-codecategories":1186,"models-dataviz":1167,"models-gamedev":1206,"models-svg":1168,"models-uicomponent":1180,"models-website":1185}}},"anthropic/claude-4-sonnet-20250522":{"aa":{"intelligence_index":29.8,"coding_index":37.6,"agentic_index":17.6},"da":{"default_elo":1166,"elo_by_category":{"models-3d":1185,"models-codecategories":1166,"models-dataviz":1179,"models-gamedev":1175,"models-svg":1119,"models-uicomponent":1156,"models-website":1166}}},"google/gemma-3n-e4b-it":{"aa":{"intelligence_index":null,"coding_index":3.2,"agentic_index":null}},"mistralai/mistral-medium-3":{"da":{"default_elo":1094,"elo_by_category":{"models-3d":1129,"models-codecategories":1094,"models-dataviz":1055,"models-gamedev":1054,"models-uicomponent":1052,"models-website":1099}}},"qwen/qwen3-30b-a3b-04-28":{"da":{"default_elo":967,"elo_by_category":{"models-codecategories":967,"models-dataviz":986,"models-gamedev":935,"models-uicomponent":973,"models-website":975}}},"qwen/qwen3-8b-04-28":{"aa":{"intelligence_index":8.3,"coding_index":9,"agentic_index":1.6}},"qwen/qwen3-14b-04-28":{"aa":{"intelligence_index":10.4,"coding_index":13.8,"agentic_index":1.9}},"qwen/qwen3-32b-04-28":{"aa":{"intelligence_index":11.4,"coding_index":15.3,"agentic_index":1.8}},"qwen/qwen3-235b-a22b-04-28":{"da":{"default_elo":1027,"elo_by_category":{"models-3d":904,"models-codecategories":1027,"models-dataviz":1016,"models-gamedev":964,"models-uicomponent":986,"models-website":1051}}},"openai/o3-2025-04-16":{"da":{"default_elo":1045,"elo_by_category":{"models-codecategories":1045,"models-dataviz":1200,"models-gamedev":1070,"models-uicomponent":1044,"models-website":1056}}},"openai/o4-mini-2025-04-16":{"da":{"default_elo":1001,"elo_by_category":{"models-3d":899,"models-codecategories":1001,"models-dataviz":1011,"models-gamedev":1039,"models-uicomponent":1010,"models-website":1005}}},"openai/gpt-4.1-2025-04-14":{"da":{"default_elo":1050,"elo_by_category":{"models-3d":895,"models-codecategories":1050,"models-dataviz":1124,"models-gamedev":1116,"models-uicomponent":1027,"models-website":1059}}},"openai/gpt-4.1-mini-2025-04-14":{"aa":{"intelligence_index":14.8,"coding_index":20.2,"agentic_index":1.8},"da":{"default_elo":1018,"elo_by_category":{"models-3d":882,"models-codecategories":1018,"models-dataviz":1053,"models-gamedev":1107,"models-uicomponent":988,"models-website":1017}}},"openai/gpt-4.1-nano-2025-04-14":{"aa":{"intelligence_index":9.6,"coding_index":11.1,"agentic_index":1.2},"da":{"default_elo":988,"elo_by_category":{"models-3d":970,"models-codecategories":988,"models-dataviz":911,"models-gamedev":1007,"models-uicomponent":943,"models-website":993}}},"meta-llama/llama-4-maverick-17b-128e-instruct":{"aa":{"intelligence_index":14.5,"coding_index":16.3,"agentic_index":1.2},"da":{"default_elo":904,"elo_by_category":{"models-3d":945,"models-codecategories":904,"models-dataviz":902,"models-gamedev":874,"models-uicomponent":926,"models-website":891}}},"meta-llama/llama-4-scout-17b-16e-instruct":{"aa":{"intelligence_index":10.3,"coding_index":8.2,"agentic_index":1.1},"da":{"default_elo":814,"elo_by_category":{"models-codecategories":814,"models-dataviz":915,"models-gamedev":809,"models-uicomponent":795,"models-website":770}}},"deepseek/deepseek-chat-v3-0324":{"aa":{"intelligence_index":15.2,"coding_index":21.2,"agentic_index":1.6}},"google/gemma-3-4b-it":{"aa":{"intelligence_index":null,"coding_index":2.7,"agentic_index":null}},"google/gemma-3-12b-it":{"aa":{"intelligence_index":5.5,"coding_index":5.8,"agentic_index":0.3}},"cohere/command-a-03-2025":{"aa":{"intelligence_index":22.8,"coding_index":27.8,"agentic_index":9.2}},"google/gemma-3-27b-it":{"aa":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3}},"openai/o3-mini-high-2025-01-31":{"aa":{"intelligence_index":15.7,"coding_index":16.3,"agentic_index":1.7}},"deepseek/deepseek-r1":{"aa":{"intelligence_index":18.6,"coding_index":24.6,"agentic_index":3.1}},"deepseek/deepseek-chat-v3":{"da":{"default_elo":1133,"elo_by_category":{"models-3d":1132,"models-codecategories":1133,"models-dataviz":1110,"models-gamedev":1090,"models-svg":1017,"models-uicomponent":1120,"models-website":1140}}},"openai/o1-2024-12-17":{"aa":{"intelligence_index":null,"coding_index":39.7,"agentic_index":null}},"meta-llama/llama-3.3-70b-instruct":{"aa":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null}},"amazon/nova-pro-v1":{"da":{"default_elo":null,"elo_by_category":{"models-website":816}}},"meta-llama/llama-3.1-8b-instruct":{"aa":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null}},"openai/gpt-4o-mini":{"aa":{"intelligence_index":null,"coding_index":11.4,"agentic_index":1}},"openai/gpt-4o":{"da":{"default_elo":885,"elo_by_category":{"models-3d":914,"models-codecategories":885,"models-dataviz":877,"models-gamedev":942,"models-uicomponent":912,"models-website":851}}},"openai/gpt-4o-2024-05-13":{"aa":{"intelligence_index":null,"coding_index":24.2,"agentic_index":null}},"openai/gpt-4-turbo":{"aa":{"intelligence_index":null,"coding_index":21.5,"agentic_index":null}},"openai/gpt-3.5-turbo":{"aa":{"intelligence_index":null,"coding_index":10.7,"agentic_index":null}},"openai/gpt-4":{"aa":{"intelligence_index":null,"coding_index":13.1,"agentic_index":null}}},"endpoint_perf":{"91327d91-f7af-4acb-81fe-4eafab2a4012":{"endpoint_id":"91327d91-f7af-4acb-81fe-4eafab2a4012","request_count":29769,"window_minutes":30,"p50_throughput":128,"p75_throughput":153,"p90_throughput":181,"p99_throughput":264,"p50_latency":3165,"p75_latency":4975,"p90_latency":6378.800000000001,"p99_latency":15718.18},"d6cd6c56-b90c-4328-8901-2774024bc62f":{"endpoint_id":"d6cd6c56-b90c-4328-8901-2774024bc62f","request_count":7841,"window_minutes":30,"p50_throughput":100,"p75_throughput":116,"p90_throughput":124,"p99_throughput":131,"p50_latency":967,"p75_latency":1420,"p90_latency":2221,"p99_latency":9331.800000000027},"da0a73a5-417d-4684-afbb-92e9e826e084":{"endpoint_id":"da0a73a5-417d-4684-afbb-92e9e826e084","request_count":1509417,"window_minutes":30,"p50_throughput":27,"p75_throughput":36,"p90_throughput":43,"p99_throughput":64,"p50_latency":3463,"p75_latency":7205.25,"p90_latency":14453.100000000006,"p99_latency":65268.75000000028},"da6a7d6d-fab7-4273-a9ed-488d61d19477":{"endpoint_id":"da6a7d6d-fab7-4273-a9ed-488d61d19477","request_count":981,"window_minutes":30,"p50_throughput":19,"p75_throughput":19,"p90_throughput":21,"p99_throughput":83.40000000000009,"p50_latency":593,"p75_latency":644,"p90_latency":845,"p99_latency":1890.8000000000038},"16cf5d0b-f9e4-45c2-acb3-47ca2adb0159":{"endpoint_id":"16cf5d0b-f9e4-45c2-acb3-47ca2adb0159","request_count":540,"window_minutes":30,"p50_throughput":14,"p75_throughput":28.25,"p90_throughput":149.10000000000002,"p99_throughput":175,"p50_latency":636.5,"p75_latency":661.25,"p90_latency":781.7000000000002,"p99_latency":2066.6100000000015},"f8e78ec2-a9f6-4437-91e7-2e76267afdb7":{"endpoint_id":"f8e78ec2-a9f6-4437-91e7-2e76267afdb7","request_count":68,"window_minutes":30,"p50_throughput":22.5,"p75_throughput":37.5,"p90_throughput":50.300000000000004,"p99_throughput":81.22999999999995,"p50_latency":1375.5,"p75_latency":1651.5,"p90_latency":1948.2,"p99_latency":2196.1299999999997},"db975786-e7f6-4838-9e56-3e0b77f1bdc2":{"endpoint_id":"db975786-e7f6-4838-9e56-3e0b77f1bdc2","request_count":39144,"window_minutes":30,"p50_throughput":52,"p75_throughput":71,"p90_throughput":83,"p99_throughput":114,"p50_latency":2141,"p75_latency":3631.75,"p90_latency":5091.900000000001,"p99_latency":12818.440000000017},"864c5d5b-af7f-4dda-a797-eb7d1e566f2f":{"endpoint_id":"864c5d5b-af7f-4dda-a797-eb7d1e566f2f","request_count":6654,"window_minutes":30,"p50_throughput":14,"p75_throughput":20,"p90_throughput":25,"p99_throughput":35,"p50_latency":8666.5,"p75_latency":16683.5,"p90_latency":25714.8,"p99_latency":46717.570000000036},"2b0adee4-4900-4027-98f1-e49712ae42b8":{"endpoint_id":"2b0adee4-4900-4027-98f1-e49712ae42b8","request_count":9529,"window_minutes":30,"p50_throughput":57,"p75_throughput":88,"p90_throughput":108,"p99_throughput":136.09000000000015,"p50_latency":1048.5,"p75_latency":1635.25,"p90_latency":2541.800000000001,"p99_latency":8364.340000000004},"e28074f6-26f6-4ba2-adf9-0bb807bc970e":{"endpoint_id":"e28074f6-26f6-4ba2-adf9-0bb807bc970e","request_count":239772,"window_minutes":30,"p50_throughput":68,"p75_throughput":110,"p90_throughput":142,"p99_throughput":183,"p50_latency":2170,"p75_latency":2874,"p90_latency":4398.900000000001,"p99_latency":19714.070000000032},"d4339029-2784-4408-bd78-2d9f6193b667":{"endpoint_id":"d4339029-2784-4408-bd78-2d9f6193b667","request_count":85,"window_minutes":30,"p50_throughput":56,"p75_throughput":61,"p90_throughput":67.60000000000001,"p99_throughput":71.63999999999999,"p50_latency":4320,"p75_latency":5968,"p90_latency":9762.000000000004,"p99_latency":16587.559999999998},"57870cab-954a-44ee-8231-e525460f55a9":{"endpoint_id":"57870cab-954a-44ee-8231-e525460f55a9","request_count":503,"window_minutes":30,"p50_throughput":55,"p75_throughput":66,"p90_throughput":75,"p99_throughput":99.98000000000002,"p50_latency":1444,"p75_latency":1770.5,"p90_latency":2221.8,"p99_latency":6680.680000000007},"c8534af4-90fc-4a27-9f4e-de565f89a92b":{"endpoint_id":"c8534af4-90fc-4a27-9f4e-de565f89a92b","request_count":101,"window_minutes":30,"p50_throughput":5,"p75_throughput":5,"p90_throughput":24,"p99_throughput":48,"p50_latency":472,"p75_latency":580,"p90_latency":826,"p99_latency":2479},"e719d276-b080-47ee-ae4f-63ed656a0b7a":{"endpoint_id":"e719d276-b080-47ee-ae4f-63ed656a0b7a","request_count":10870,"window_minutes":30,"p50_throughput":53,"p75_throughput":61,"p90_throughput":68,"p99_throughput":86,"p50_latency":1329.5,"p75_latency":2043.75,"p90_latency":3725.600000000002,"p99_latency":7834.450000000001},"67ed3d9b-4f05-4e79-9bb6-1e8423a6c276":{"endpoint_id":"67ed3d9b-4f05-4e79-9bb6-1e8423a6c276","request_count":9505,"window_minutes":30,"p50_throughput":54,"p75_throughput":59,"p90_throughput":67,"p99_throughput":82,"p50_latency":1122,"p75_latency":1826,"p90_latency":3806,"p99_latency":21070.36},"789f02b8-56f5-48d0-bae5-91b4957376c7":{"endpoint_id":"789f02b8-56f5-48d0-bae5-91b4957376c7","request_count":3890,"window_minutes":30,"p50_throughput":161,"p75_throughput":247,"p90_throughput":349,"p99_throughput":517.2200000000003,"p50_latency":2813,"p75_latency":5292.5,"p90_latency":9229.4,"p99_latency":25513.160000000033},"022e8198-179c-47a3-a359-9147cb1b8909":{"endpoint_id":"022e8198-179c-47a3-a359-9147cb1b8909","request_count":54789,"window_minutes":30,"p50_throughput":33,"p75_throughput":42,"p90_throughput":51,"p99_throughput":111,"p50_latency":1275,"p75_latency":2059.5,"p90_latency":4898.900000000001,"p99_latency":19663.790000000048},"9675f992-cf53-4946-a49b-e4f5a3e82584":{"endpoint_id":"9675f992-cf53-4946-a49b-e4f5a3e82584","request_count":2045,"window_minutes":30,"p50_throughput":169,"p75_throughput":292,"p90_throughput":453.60000000000014,"p99_throughput":798,"p50_latency":455,"p75_latency":718,"p90_latency":1260,"p99_latency":3450.24},"7c5c9b97-46c3-439c-8c85-d7844c95fa22":{"endpoint_id":"7c5c9b97-46c3-439c-8c85-d7844c95fa22","request_count":9,"window_minutes":30,"p50_throughput":27,"p75_throughput":178,"p90_throughput":201.6,"p99_throughput":221.76,"p50_latency":1057,"p75_latency":1121,"p90_latency":1132,"p99_latency":1164.4},"000381e4-18ad-455e-937b-ceeb3863fd67":{"endpoint_id":"000381e4-18ad-455e-937b-ceeb3863fd67","request_count":31898,"window_minutes":30,"p50_throughput":40,"p75_throughput":62,"p90_throughput":84,"p99_throughput":128,"p50_latency":2248,"p75_latency":4635.75,"p90_latency":7872,"p99_latency":15225.880000000005},"6244f10e-1e45-488b-a47f-f575e0edd12b":{"endpoint_id":"6244f10e-1e45-488b-a47f-f575e0edd12b","request_count":877,"window_minutes":30,"p50_throughput":58,"p75_throughput":61,"p90_throughput":63,"p99_throughput":68.24000000000001,"p50_latency":503,"p75_latency":969,"p90_latency":1485.599999999999,"p99_latency":2523.8000000000006},"ffc8e76e-808a-44d2-bd21-c6ac16e721cb":{"endpoint_id":"ffc8e76e-808a-44d2-bd21-c6ac16e721cb","request_count":3300,"window_minutes":30,"p50_throughput":98,"p75_throughput":126,"p90_throughput":161,"p99_throughput":254.0299999999993,"p50_latency":8755,"p75_latency":16603.25,"p90_latency":28941.899999999994,"p99_latency":77255},"6332e9fd-e0c4-4cae-8c17-d25bc774864a":{"endpoint_id":"6332e9fd-e0c4-4cae-8c17-d25bc774864a","request_count":16617,"window_minutes":30,"p50_throughput":36,"p75_throughput":46,"p90_throughput":55,"p99_throughput":80,"p50_latency":1472,"p75_latency":2370.75,"p90_latency":4593.10000000001,"p99_latency":24893.69000000002},"57c1bfab-049c-4d6a-ab34-ac1007a6043b":{"endpoint_id":"57c1bfab-049c-4d6a-ab34-ac1007a6043b","request_count":220860,"window_minutes":30,"p50_throughput":43,"p75_throughput":54,"p90_throughput":66,"p99_throughput":88,"p50_latency":1141,"p75_latency":2127,"p90_latency":3907.7000000000016,"p99_latency":8678.97000000002},"e27a9a6d-1451-4be4-876e-292ffcbf1e71":{"endpoint_id":"e27a9a6d-1451-4be4-876e-292ffcbf1e71","request_count":4591,"window_minutes":30,"p50_throughput":118,"p75_throughput":216,"p90_throughput":295,"p99_throughput":383,"p50_latency":1025,"p75_latency":1582.5,"p90_latency":2268,"p99_latency":4934.000000000022},"d1d9657b-3c3a-49b5-8f81-33204e7c71c3":{"endpoint_id":"d1d9657b-3c3a-49b5-8f81-33204e7c71c3","request_count":224,"window_minutes":30,"p50_throughput":209.5,"p75_throughput":250,"p90_throughput":291.40000000000003,"p99_throughput":331.47000000000014,"p50_latency":581,"p75_latency":661.25,"p90_latency":1134.2000000000003,"p99_latency":13486.810000000003},"5a9a0ee6-874a-4d03-92be-e5094c0df4e7":{"endpoint_id":"5a9a0ee6-874a-4d03-92be-e5094c0df4e7","request_count":155206,"window_minutes":30,"p50_throughput":68,"p75_throughput":108,"p90_throughput":161,"p99_throughput":206,"p50_latency":676,"p75_latency":1228,"p90_latency":1757.9000000000005,"p99_latency":12136.54},"a42a3d15-779d-403b-b151-d3482546b474":{"endpoint_id":"a42a3d15-779d-403b-b151-d3482546b474","request_count":348,"window_minutes":30,"p50_throughput":80,"p75_throughput":136,"p90_throughput":194.60000000000002,"p99_throughput":263.64999999999986,"p50_latency":3217.5,"p75_latency":4102.25,"p90_latency":5568.1,"p99_latency":10845.519999999982},"2edf66f3-04ad-4c38-b05a-bc69cf1a29ef":{"endpoint_id":"2edf66f3-04ad-4c38-b05a-bc69cf1a29ef","request_count":40929,"window_minutes":30,"p50_throughput":63,"p75_throughput":78,"p90_throughput":92.90000000000055,"p99_throughput":108,"p50_latency":4840.5,"p75_latency":5898,"p90_latency":6551.900000000001,"p99_latency":9238.080000000002},"ad853a79-97b2-4260-8163-fbe2a796cebf":{"endpoint_id":"ad853a79-97b2-4260-8163-fbe2a796cebf","request_count":52549,"window_minutes":30,"p50_throughput":202,"p75_throughput":268,"p90_throughput":315,"p99_throughput":377,"p50_latency":743,"p75_latency":909.5,"p90_latency":1420.9000000000005,"p99_latency":7909.050000000007},"1671d9aa-18c8-444a-96c7-f5f6231591bb":{"endpoint_id":"1671d9aa-18c8-444a-96c7-f5f6231591bb","request_count":47745,"window_minutes":30,"p50_throughput":39,"p75_throughput":50,"p90_throughput":57,"p99_throughput":69,"p50_latency":1407,"p75_latency":2003,"p90_latency":2798.9000000000005,"p99_latency":5978.09},"ab7f9e97-1af5-4b81-b099-cc932f54234e":{"endpoint_id":"ab7f9e97-1af5-4b81-b099-cc932f54234e","request_count":1395,"window_minutes":30,"p50_throughput":81,"p75_throughput":114,"p90_throughput":124,"p99_throughput":146,"p50_latency":513,"p75_latency":1854.5,"p90_latency":2928.600000000001,"p99_latency":6677.699999999997},"5d6d133d-a953-4781-a835-7ee76f4e1388":{"endpoint_id":"5d6d133d-a953-4781-a835-7ee76f4e1388","request_count":14563,"window_minutes":30,"p50_throughput":122,"p75_throughput":152,"p90_throughput":178,"p99_throughput":222,"p50_latency":1848.5,"p75_latency":2587,"p90_latency":3784.800000000001,"p99_latency":9686.51000000002},"6bd8f433-79e1-416c-b407-1772eb796c9a":{"endpoint_id":"6bd8f433-79e1-416c-b407-1772eb796c9a","request_count":37690,"window_minutes":30,"p50_throughput":58,"p75_throughput":146,"p90_throughput":254,"p99_throughput":393,"p50_latency":665,"p75_latency":1049.25,"p90_latency":1516.9000000000005,"p99_latency":3334.720000000001},"1c1713d4-6398-47a1-9ff7-a6488c16e6c0":{"endpoint_id":"1c1713d4-6398-47a1-9ff7-a6488c16e6c0","request_count":365,"window_minutes":30,"p50_throughput":23,"p75_throughput":32,"p90_throughput":39,"p99_throughput":46,"p50_latency":2753,"p75_latency":4784,"p90_latency":6483.4000000000015,"p99_latency":51850.200000000004},"89249263-425e-4099-a555-ea5c9698ba76":{"endpoint_id":"89249263-425e-4099-a555-ea5c9698ba76","request_count":6714,"window_minutes":30,"p50_throughput":63,"p75_throughput":98,"p90_throughput":134,"p99_throughput":205,"p50_latency":1041,"p75_latency":1733.75,"p90_latency":2981.499999999999,"p99_latency":9565.239999999994},"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e":{"endpoint_id":"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e","request_count":633,"window_minutes":30,"p50_throughput":50,"p75_throughput":56,"p90_throughput":98.80000000000007,"p99_throughput":199.7199999999998,"p50_latency":496,"p75_latency":607,"p90_latency":854.6000000000005,"p99_latency":12552.879999999966},"57615dec-899a-41e7-8cab-1e2914497f0c":{"endpoint_id":"57615dec-899a-41e7-8cab-1e2914497f0c","request_count":1863,"window_minutes":30,"p50_throughput":35,"p75_throughput":63,"p90_throughput":97,"p99_throughput":158.75999999999976,"p50_latency":1678,"p75_latency":3778,"p90_latency":13188.199999999997,"p99_latency":107626.23999999985},"b2b9f6f9-8880-41c1-bd0c-867650fd5238":{"endpoint_id":"b2b9f6f9-8880-41c1-bd0c-867650fd5238","request_count":1680,"window_minutes":30,"p50_throughput":200,"p75_throughput":229,"p90_throughput":264,"p99_throughput":338.21000000000004,"p50_latency":2849.5,"p75_latency":6030.75,"p90_latency":9056.900000000001,"p99_latency":19038.480000000014},"9af3f328-0015-4f68-9057-1caf8620d313":{"endpoint_id":"9af3f328-0015-4f68-9057-1caf8620d313","request_count":75,"window_minutes":30,"p50_throughput":108,"p75_throughput":149.5,"p90_throughput":171.20000000000002,"p99_throughput":201.78000000000003,"p50_latency":1262,"p75_latency":1582.5,"p90_latency":2300.4000000000005,"p99_latency":2780.6800000000003},"f8bf6b99-c193-48c5-ba1f-133c503de185":{"endpoint_id":"f8bf6b99-c193-48c5-ba1f-133c503de185","request_count":23,"window_minutes":30,"p50_throughput":29,"p75_throughput":62.5,"p90_throughput":87.2,"p99_throughput":94.56,"p50_latency":724,"p75_latency":1351.5,"p90_latency":1609.6,"p99_latency":3487.6200000000026},"0ffa892c-07fc-43d2-8bf5-ba0892060aa3":{"endpoint_id":"0ffa892c-07fc-43d2-8bf5-ba0892060aa3","request_count":889,"window_minutes":30,"p50_throughput":113,"p75_throughput":131,"p90_throughput":149,"p99_throughput":196.32000000000005,"p50_latency":13407,"p75_latency":16627,"p90_latency":29237.400000000012,"p99_latency":82086.24},"3e1fe018-94f7-4499-874b-34254ca271a7":{"endpoint_id":"3e1fe018-94f7-4499-874b-34254ca271a7","request_count":40896,"window_minutes":30,"p50_throughput":60,"p75_throughput":87,"p90_throughput":102,"p99_throughput":119,"p50_latency":4011,"p75_latency":5575,"p90_latency":7650.900000000001,"p99_latency":16688.12000000001},"3cc89000-ae34-4dde-9c7d-5ce009c8af0b":{"endpoint_id":"3cc89000-ae34-4dde-9c7d-5ce009c8af0b","request_count":62313,"window_minutes":30,"p50_throughput":41,"p75_throughput":57,"p90_throughput":84,"p99_throughput":132,"p50_latency":2428,"p75_latency":3866.25,"p90_latency":5696.900000000001,"p99_latency":14549.890000000003},"24801a82-7216-49bb-89a6-5480320ae736":{"endpoint_id":"24801a82-7216-49bb-89a6-5480320ae736","request_count":3282,"window_minutes":30,"p50_throughput":98,"p75_throughput":107,"p90_throughput":116,"p99_throughput":145,"p50_latency":53179.5,"p75_latency":70034.75,"p90_latency":85720.6,"p99_latency":129003.87000000046},"a54c5de0-89bf-4ad7-a212-cf977eed918a":{"endpoint_id":"a54c5de0-89bf-4ad7-a212-cf977eed918a","request_count":157378,"window_minutes":30,"p50_throughput":41,"p75_throughput":62,"p90_throughput":86,"p99_throughput":114,"p50_latency":2522.5,"p75_latency":4386.25,"p90_latency":8041.700000000007,"p99_latency":29674.250000000004},"78a73286-52c4-4d1d-9d13-c1870c25b143":{"endpoint_id":"78a73286-52c4-4d1d-9d13-c1870c25b143","request_count":11390,"window_minutes":30,"p50_throughput":53,"p75_throughput":59,"p90_throughput":66,"p99_throughput":87.09000000000015,"p50_latency":827,"p75_latency":1190.25,"p90_latency":2344.800000000001,"p99_latency":9888.030000000039},"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3":{"endpoint_id":"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3","request_count":993,"window_minutes":30,"p50_throughput":46,"p75_throughput":63,"p90_throughput":70.80000000000007,"p99_throughput":82,"p50_latency":827,"p75_latency":1018,"p90_latency":1348.8000000000002,"p99_latency":11322.560000000001},"8c8f827d-2bef-468a-8f9e-8e27b470de5e":{"endpoint_id":"8c8f827d-2bef-468a-8f9e-8e27b470de5e","request_count":1655,"window_minutes":30,"p50_throughput":44,"p75_throughput":49,"p90_throughput":54,"p99_throughput":63,"p50_latency":1305,"p75_latency":2158.5,"p90_latency":3166,"p99_latency":6907.440000000002},"b57b0bfd-2bf0-47b6-9445-8263b3b0fa91":{"endpoint_id":"b57b0bfd-2bf0-47b6-9445-8263b3b0fa91","request_count":1238,"window_minutes":30,"p50_throughput":68,"p75_throughput":75,"p90_throughput":81,"p99_throughput":91,"p50_latency":943,"p75_latency":2079.5,"p90_latency":3931.2,"p99_latency":8211.929999999917},"9c35bcfc-edcc-405a-acee-a0b991ec61cb":{"endpoint_id":"9c35bcfc-edcc-405a-acee-a0b991ec61cb","request_count":5447,"window_minutes":30,"p50_throughput":60,"p75_throughput":90,"p90_throughput":116.40000000000055,"p99_throughput":175,"p50_latency":769,"p75_latency":1739,"p90_latency":4266.000000000003,"p99_latency":10458.779999999999},"089ec178-f6dc-4450-aff5-46f68798ce97":{"endpoint_id":"089ec178-f6dc-4450-aff5-46f68798ce97","request_count":706,"window_minutes":30,"p50_throughput":107,"p75_throughput":148.75,"p90_throughput":189,"p99_throughput":258.6500000000003,"p50_latency":287.5,"p75_latency":387.5,"p90_latency":549.5,"p99_latency":2077.9},"0a2a206f-95f6-4173-9475-fe65a9a36171":{"endpoint_id":"0a2a206f-95f6-4173-9475-fe65a9a36171","request_count":10724,"window_minutes":30,"p50_throughput":55,"p75_throughput":76,"p90_throughput":92,"p99_throughput":125,"p50_latency":2411,"p75_latency":4599,"p90_latency":6294.600000000002,"p99_latency":13866.650000000012},"55b53628-1e94-4ee3-9494-2c04e7f2c43a":{"endpoint_id":"55b53628-1e94-4ee3-9494-2c04e7f2c43a","request_count":2533,"window_minutes":30,"p50_throughput":436,"p75_throughput":548,"p90_throughput":613,"p99_throughput":686,"p50_latency":3076,"p75_latency":3750,"p90_latency":4399.6,"p99_latency":6169.159999999991},"14abef89-df95-4906-bb3f-df4ce3614212":{"endpoint_id":"14abef89-df95-4906-bb3f-df4ce3614212","request_count":13062,"window_minutes":30,"p50_throughput":38,"p75_throughput":49,"p90_throughput":58,"p99_throughput":77,"p50_latency":1054,"p75_latency":1537.25,"p90_latency":2227.800000000001,"p99_latency":5537.27},"99a9a85f-3c29-4b33-a21c-e5becb008160":{"endpoint_id":"99a9a85f-3c29-4b33-a21c-e5becb008160","request_count":21,"window_minutes":30,"p50_throughput":64,"p75_throughput":71,"p90_throughput":76,"p99_throughput":81.19999999999999,"p50_latency":34813,"p75_latency":55000,"p90_latency":78467,"p99_latency":253382.2000000001},"275d7d39-ae50-4df3-8140-5dd69c3ab883":{"endpoint_id":"275d7d39-ae50-4df3-8140-5dd69c3ab883","request_count":1383,"window_minutes":30,"p50_throughput":93,"p75_throughput":104,"p90_throughput":114,"p99_throughput":187.36000000000013,"p50_latency":10787,"p75_latency":12478,"p90_latency":14824.8,"p99_latency":22578.540000000037},"459bc165-dafa-4e03-9fd0-bdd22c19d516":{"endpoint_id":"459bc165-dafa-4e03-9fd0-bdd22c19d516","request_count":388,"window_minutes":30,"p50_throughput":55,"p75_throughput":63,"p90_throughput":68.30000000000001,"p99_throughput":79.25999999999999,"p50_latency":3212.5,"p75_latency":3865.75,"p90_latency":4716.5,"p99_latency":14777.219999999921},"d3a18412-b833-40de-bc07-c4ba9a1dea53":{"endpoint_id":"d3a18412-b833-40de-bc07-c4ba9a1dea53","request_count":14363,"window_minutes":30,"p50_throughput":25,"p75_throughput":31,"p90_throughput":39,"p99_throughput":53,"p50_latency":1169,"p75_latency":3154,"p90_latency":3656,"p99_latency":14209.400000000052},"036a9487-617f-45a2-b0e1-bc5e48a20284":{"endpoint_id":"036a9487-617f-45a2-b0e1-bc5e48a20284","request_count":1618,"window_minutes":30,"p50_throughput":154.5,"p75_throughput":276.75,"p90_throughput":394.29999999999995,"p99_throughput":663.6599999999999,"p50_latency":2624.5,"p75_latency":4468.25,"p90_latency":12738.399999999998,"p99_latency":25471.119999999995},"515ff417-d0f5-4455-9f58-b5a82be6d842":{"endpoint_id":"515ff417-d0f5-4455-9f58-b5a82be6d842","request_count":31633,"window_minutes":30,"p50_throughput":57,"p75_throughput":66,"p90_throughput":77,"p99_throughput":99,"p50_latency":1169,"p75_latency":1602,"p90_latency":2298.9000000000005,"p99_latency":6785.320000000007},"7371d3a6-b4b2-4175-9efa-7f75319aa509":{"endpoint_id":"7371d3a6-b4b2-4175-9efa-7f75319aa509","request_count":1995,"window_minutes":30,"p50_throughput":78,"p75_throughput":103,"p90_throughput":127,"p99_throughput":173.05999999999995,"p50_latency":715,"p75_latency":1074,"p90_latency":1801.8000000000004,"p99_latency":7936.279999999995},"cd63e693-ab16-4d13-a92f-60c998be2ada":{"endpoint_id":"cd63e693-ab16-4d13-a92f-60c998be2ada","request_count":23,"window_minutes":30,"p50_throughput":18,"p75_throughput":86.5,"p90_throughput":132.8,"p99_throughput":149.56,"p50_latency":1009,"p75_latency":1506,"p90_latency":2076.6,"p99_latency":2164.44},"e1bc6262-4e47-42c0-9b9b-00236a52a01a":{"endpoint_id":"e1bc6262-4e47-42c0-9b9b-00236a52a01a","request_count":1353,"window_minutes":30,"p50_throughput":62,"p75_throughput":73,"p90_throughput":78,"p99_throughput":83,"p50_latency":335,"p75_latency":1015,"p90_latency":1790.399999999999,"p99_latency":6303.6},"72416acd-887a-4940-9ccc-1f22d9e17dbc":{"endpoint_id":"72416acd-887a-4940-9ccc-1f22d9e17dbc","request_count":143334,"window_minutes":30,"p50_throughput":26,"p75_throughput":44,"p90_throughput":65,"p99_throughput":110,"p50_latency":2564.5,"p75_latency":5616.5,"p90_latency":12931.7,"p99_latency":39470.600000000006},"7d4f9061-1fd5-46d6-b439-e85b0b9fcd87":{"endpoint_id":"7d4f9061-1fd5-46d6-b439-e85b0b9fcd87","request_count":1367,"window_minutes":30,"p50_throughput":65,"p75_throughput":96,"p90_throughput":133,"p99_throughput":192.33999999999992,"p50_latency":2288,"p75_latency":5683,"p90_latency":10482.000000000004,"p99_latency":42469.17999999997},"b77fd6ef-e2e0-4e92-96e1-8ffbf62d9792":{"endpoint_id":"b77fd6ef-e2e0-4e92-96e1-8ffbf62d9792","request_count":39133,"window_minutes":30,"p50_throughput":13,"p75_throughput":18,"p90_throughput":39,"p99_throughput":58,"p50_latency":677.5,"p75_latency":803,"p90_latency":1110,"p99_latency":3219.980000000003},"b4c27216-5aed-4eac-ac2e-e3109cc778e7":{"endpoint_id":"b4c27216-5aed-4eac-ac2e-e3109cc778e7","request_count":1520,"window_minutes":30,"p50_throughput":110,"p75_throughput":160,"p90_throughput":213,"p99_throughput":286.0499999999997,"p50_latency":503,"p75_latency":664,"p90_latency":941.1000000000015,"p99_latency":4352.929999999986},"1e380b07-8052-4bd4-bd89-f20790fb0996":{"endpoint_id":"1e380b07-8052-4bd4-bd89-f20790fb0996","request_count":24530,"window_minutes":30,"p50_throughput":44,"p75_throughput":70,"p90_throughput":86,"p99_throughput":111,"p50_latency":4790,"p75_latency":6310.25,"p90_latency":8348.900000000001,"p99_latency":16430.640000000014},"07b9c653-6817-4555-9013-1039f33e17e8":{"endpoint_id":"07b9c653-6817-4555-9013-1039f33e17e8","request_count":287,"window_minutes":30,"p50_throughput":121,"p75_throughput":164.5,"p90_throughput":198.80000000000007,"p99_throughput":263.41999999999996,"p50_latency":1174,"p75_latency":2999.5,"p90_latency":4128.400000000001,"p99_latency":6814.719999999999},"37ca59bb-cb63-4806-a46e-7ad51de3ec2f":{"endpoint_id":"37ca59bb-cb63-4806-a46e-7ad51de3ec2f","request_count":5193,"window_minutes":30,"p50_throughput":61,"p75_throughput":75,"p90_throughput":87,"p99_throughput":110,"p50_latency":1693,"p75_latency":3692,"p90_latency":4894.800000000001,"p99_latency":7956.279999999993},"6d30fdc6-f2a7-4bdf-b6ba-32353496d723":{"endpoint_id":"6d30fdc6-f2a7-4bdf-b6ba-32353496d723","request_count":2030,"window_minutes":30,"p50_throughput":56,"p75_throughput":66,"p90_throughput":72,"p99_throughput":82,"p50_latency":1114,"p75_latency":1686.75,"p90_latency":2552.500000000001,"p99_latency":13597.180000000024},"2d3cdd47-cfc2-4372-96bb-82980f6a032d":{"endpoint_id":"2d3cdd47-cfc2-4372-96bb-82980f6a032d","request_count":551,"window_minutes":30,"p50_throughput":76,"p75_throughput":94,"p90_throughput":110,"p99_throughput":156.5,"p50_latency":879,"p75_latency":1494.5,"p90_latency":1720,"p99_latency":4288.5},"bd50061c-e1d8-469e-96b1-d322e77378f8":{"endpoint_id":"bd50061c-e1d8-469e-96b1-d322e77378f8","request_count":3634,"window_minutes":30,"p50_throughput":183,"p75_throughput":235,"p90_throughput":278,"p99_throughput":320,"p50_latency":1762,"p75_latency":2315.75,"p90_latency":3525.5000000000014,"p99_latency":11464.700000000023},"92521bd2-ad85-4d32-bc48-34528189a0de":{"endpoint_id":"92521bd2-ad85-4d32-bc48-34528189a0de","request_count":44,"window_minutes":30,"p50_throughput":15,"p75_throughput":24.5,"p90_throughput":36.10000000000001,"p99_throughput":45.42,"p50_latency":991,"p75_latency":1719.25,"p90_latency":2135.4,"p99_latency":3400.46},"0d6ee1b8-2f68-491f-9707-4febcfa3a6c4":{"endpoint_id":"0d6ee1b8-2f68-491f-9707-4febcfa3a6c4","request_count":152830,"window_minutes":30,"p50_throughput":53,"p75_throughput":128,"p90_throughput":211,"p99_throughput":321.1800000000003,"p50_latency":910.5,"p75_latency":1458,"p90_latency":1944,"p99_latency":4779.250000000004},"144906de-89e6-4ba4-a986-640af2562cfa":{"endpoint_id":"144906de-89e6-4ba4-a986-640af2562cfa","request_count":224,"window_minutes":30,"p50_throughput":41,"p75_throughput":64,"p90_throughput":82.70000000000002,"p99_throughput":142.55000000000015,"p50_latency":921,"p75_latency":1172.5,"p90_latency":1914.3000000000006,"p99_latency":5481.8300000000045},"5110cba8-da2e-4c85-be65-837bdfbedafe":{"endpoint_id":"5110cba8-da2e-4c85-be65-837bdfbedafe","request_count":4108,"window_minutes":30,"p50_throughput":97,"p75_throughput":115,"p90_throughput":136,"p99_throughput":174,"p50_latency":608.5,"p75_latency":803,"p90_latency":1187.9000000000005,"p99_latency":2845.409999999994},"c7587631-66c2-46d5-a5c9-b50cb6d230dc":{"endpoint_id":"c7587631-66c2-46d5-a5c9-b50cb6d230dc","request_count":1237,"window_minutes":30,"p50_throughput":117,"p75_throughput":130,"p90_throughput":133,"p99_throughput":158,"p50_latency":137,"p75_latency":190,"p90_latency":252.4000000000001,"p99_latency":707.8400000000006},"38ef23a9-5cb3-46fa-85ec-7aed174f04eb":{"endpoint_id":"38ef23a9-5cb3-46fa-85ec-7aed174f04eb","request_count":330,"window_minutes":30,"p50_throughput":66.5,"p75_throughput":128.75,"p90_throughput":197,"p99_throughput":231.12999999999994,"p50_latency":770.5,"p75_latency":1546,"p90_latency":3805.7000000000025,"p99_latency":17498.21999999998},"36402cf4-40a3-4188-b964-5625d8052cc0":{"endpoint_id":"36402cf4-40a3-4188-b964-5625d8052cc0","request_count":5010,"window_minutes":30,"p50_throughput":54,"p75_throughput":70,"p90_throughput":103,"p99_throughput":160,"p50_latency":458,"p75_latency":1325,"p90_latency":2444.1000000000004,"p99_latency":12898.969999999976},"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc":{"endpoint_id":"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc","request_count":66,"window_minutes":30,"p50_throughput":43,"p75_throughput":48.75,"p90_throughput":58,"p99_throughput":70.39999999999998,"p50_latency":2267,"p75_latency":7213.25,"p90_latency":8545.5,"p99_latency":8968.099999999999},"2435bec9-c808-4f27-9fc8-12f3460d7b66":{"endpoint_id":"2435bec9-c808-4f27-9fc8-12f3460d7b66","request_count":5550,"window_minutes":30,"p50_throughput":63,"p75_throughput":118,"p90_throughput":158.10000000000036,"p99_throughput":205,"p50_latency":380,"p75_latency":547,"p90_latency":1082.1000000000004,"p99_latency":4076.630000000003},"babd4746-9e93-4855-8578-4b40539a5f4a":{"endpoint_id":"babd4746-9e93-4855-8578-4b40539a5f4a","request_count":7475,"window_minutes":30,"p50_throughput":16,"p75_throughput":33,"p90_throughput":55,"p99_throughput":93,"p50_latency":8792,"p75_latency":13280.5,"p90_latency":18303.800000000003,"p99_latency":27835.040000000008},"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787":{"endpoint_id":"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787","request_count":205,"window_minutes":30,"p50_throughput":54,"p75_throughput":63,"p90_throughput":66,"p99_throughput":69.96000000000001,"p50_latency":984,"p75_latency":1324,"p90_latency":2125,"p99_latency":2887.4400000000014},"328bee10-7e34-44f8-a7cc-c33c8f8775ed":{"endpoint_id":"328bee10-7e34-44f8-a7cc-c33c8f8775ed","request_count":1441,"window_minutes":30,"p50_throughput":15,"p75_throughput":21,"p90_throughput":26,"p99_throughput":32,"p50_latency":3124,"p75_latency":7242,"p90_latency":11487,"p99_latency":26449.59999999999},"947d13c4-fbd4-48d6-8bf3-c923edab343e":{"endpoint_id":"947d13c4-fbd4-48d6-8bf3-c923edab343e","request_count":740,"window_minutes":30,"p50_throughput":5,"p75_throughput":34.25,"p90_throughput":41,"p99_throughput":48.610000000000014,"p50_latency":4698,"p75_latency":34730.25,"p90_latency":40602.4,"p99_latency":62983.66000000003},"42da77cc-cd0e-43a4-923a-3b742f7b124d":{"endpoint_id":"42da77cc-cd0e-43a4-923a-3b742f7b124d","request_count":2976,"window_minutes":30,"p50_throughput":44,"p75_throughput":71,"p90_throughput":104,"p99_throughput":122,"p50_latency":2996,"p75_latency":6577.25,"p90_latency":13554,"p99_latency":48531.25},"48f7c1a9-3b0c-4f31-a55b-4650d37e35f3":{"endpoint_id":"48f7c1a9-3b0c-4f31-a55b-4650d37e35f3","request_count":76544,"window_minutes":30,"p50_throughput":45,"p75_throughput":54,"p90_throughput":61,"p99_throughput":78,"p50_latency":1160.5,"p75_latency":1964,"p90_latency":2748,"p99_latency":5557.09},"fa22fe84-7ea9-49b0-a8eb-4d87ede9de31":{"endpoint_id":"fa22fe84-7ea9-49b0-a8eb-4d87ede9de31","request_count":325570,"window_minutes":30,"p50_throughput":71,"p75_throughput":87,"p90_throughput":98,"p99_throughput":115,"p50_latency":811,"p75_latency":1217,"p90_latency":2107.800000000001,"p99_latency":6277.950000000008},"e062ae6d-577e-4d12-8232-8eabc472c4ec":{"endpoint_id":"e062ae6d-577e-4d12-8232-8eabc472c4ec","request_count":7035,"window_minutes":30,"p50_throughput":55,"p75_throughput":63,"p90_throughput":87,"p99_throughput":172,"p50_latency":2024,"p75_latency":2372,"p90_latency":4189.000000000002,"p99_latency":24202.759999999995},"362a7650-63ed-41d8-b74e-1886ad31b3d9":{"endpoint_id":"362a7650-63ed-41d8-b74e-1886ad31b3d9","request_count":453,"window_minutes":30,"p50_throughput":30,"p75_throughput":39,"p90_throughput":43,"p99_throughput":66,"p50_latency":3332,"p75_latency":4354,"p90_latency":5105.2,"p99_latency":6602.320000000003},"fb34a890-eaa9-428e-8fc4-4ad0fdcba2ff":{"endpoint_id":"fb34a890-eaa9-428e-8fc4-4ad0fdcba2ff","request_count":12134,"window_minutes":30,"p50_throughput":31,"p75_throughput":47,"p90_throughput":56,"p99_throughput":68,"p50_latency":3457,"p75_latency":4506.25,"p90_latency":5652.900000000001,"p99_latency":8265.430000000004},"5acf5b3b-66dd-4ee8-8db2-2eed7d795b17":{"endpoint_id":"5acf5b3b-66dd-4ee8-8db2-2eed7d795b17","request_count":459,"window_minutes":30,"p50_throughput":54,"p75_throughput":69,"p90_throughput":86.19999999999999,"p99_throughput":114.10000000000008,"p50_latency":394,"p75_latency":683,"p90_latency":1161.8,"p99_latency":7735.120000000117},"78cbd7eb-84cd-46ea-8347-0578e3415f83":{"endpoint_id":"78cbd7eb-84cd-46ea-8347-0578e3415f83","request_count":5602,"window_minutes":30,"p50_throughput":48,"p75_throughput":61,"p90_throughput":71,"p99_throughput":89,"p50_latency":1053.5,"p75_latency":1699,"p90_latency":2628.9000000000005,"p99_latency":6204.9299999999985},"0fa65117-00d9-4835-808d-9b68041d9ce4":{"endpoint_id":"0fa65117-00d9-4835-808d-9b68041d9ce4","request_count":1023,"window_minutes":30,"p50_throughput":45,"p75_throughput":69,"p90_throughput":83,"p99_throughput":123.77999999999997,"p50_latency":1244,"p75_latency":2389,"p90_latency":3816.800000000001,"p99_latency":5786.319999999999},"44b42eb7-1926-4e06-99ce-29b6f710b86f":{"endpoint_id":"44b42eb7-1926-4e06-99ce-29b6f710b86f","request_count":1342,"window_minutes":30,"p50_throughput":62,"p75_throughput":79,"p90_throughput":86,"p99_throughput":93.58999999999992,"p50_latency":1211,"p75_latency":1825.5,"p90_latency":2559.5000000000005,"p99_latency":5237.949999999992},"9d057a54-dce2-49d5-af13-f063a029b2ef":{"endpoint_id":"9d057a54-dce2-49d5-af13-f063a029b2ef","request_count":649,"window_minutes":30,"p50_throughput":40,"p75_throughput":43,"p90_throughput":45,"p99_throughput":47,"p50_latency":1019,"p75_latency":1516,"p90_latency":2594.8000000000006,"p99_latency":10573.559999999958},"0e9b72a2-e1eb-45bd-adc5-81f0f31e185f":{"endpoint_id":"0e9b72a2-e1eb-45bd-adc5-81f0f31e185f","request_count":32174,"window_minutes":30,"p50_throughput":19,"p75_throughput":43,"p90_throughput":59,"p99_throughput":80,"p50_latency":1718,"p75_latency":3037.5,"p90_latency":5353.600000000002,"p99_latency":14921.600000000006},"65b19119-a8d5-427b-9cbd-03329ef0d939":{"endpoint_id":"65b19119-a8d5-427b-9cbd-03329ef0d939","request_count":1336,"window_minutes":30,"p50_throughput":22,"p75_throughput":30,"p90_throughput":33,"p99_throughput":35,"p50_latency":1337.5,"p75_latency":6244,"p90_latency":14205,"p99_latency":36732.350000000326},"6498d998-23ad-4dc5-b98f-9dee5a48d290":{"endpoint_id":"6498d998-23ad-4dc5-b98f-9dee5a48d290","request_count":12549,"window_minutes":30,"p50_throughput":16,"p75_throughput":25,"p90_throughput":37,"p99_throughput":60,"p50_latency":1302.5,"p75_latency":3028.5,"p90_latency":25512.20000000003,"p99_latency":45532.56000000001},"2102b4bc-ef48-4aab-964c-33e043b3f3f2":{"endpoint_id":"2102b4bc-ef48-4aab-964c-33e043b3f3f2","request_count":12699,"window_minutes":30,"p50_throughput":39,"p75_throughput":49,"p90_throughput":57,"p99_throughput":59,"p50_latency":776,"p75_latency":1032,"p90_latency":1441.9000000000005,"p99_latency":15017.620000000003},"a3b0220b-6a75-47bd-aa99-70f955e5b84d":{"endpoint_id":"a3b0220b-6a75-47bd-aa99-70f955e5b84d","request_count":1798,"window_minutes":30,"p50_throughput":43,"p75_throughput":71,"p90_throughput":97,"p99_throughput":138.02999999999997,"p50_latency":2533.5,"p75_latency":4171.5,"p90_latency":6324.099999999999,"p99_latency":16806.139999999996},"c6203380-90d0-4ded-be03-0fbcf3aad22c":{"endpoint_id":"c6203380-90d0-4ded-be03-0fbcf3aad22c","request_count":1182,"window_minutes":30,"p50_throughput":69,"p75_throughput":74,"p90_throughput":80,"p99_throughput":159,"p50_latency":155,"p75_latency":166,"p90_latency":194.9000000000001,"p99_latency":464.0900000000006},"5f5b5f6c-e80d-4b77-9c06-d1cb35452bab":{"endpoint_id":"5f5b5f6c-e80d-4b77-9c06-d1cb35452bab","request_count":34,"window_minutes":30,"p50_throughput":161,"p75_throughput":169,"p90_throughput":174.8,"p99_throughput":314.7900000000001,"p50_latency":33926,"p75_latency":40717,"p90_latency":50576.5,"p99_latency":71950.73000000005},"b17f55ac-e8fa-47ef-9e2e-5081c2124c7d":{"endpoint_id":"b17f55ac-e8fa-47ef-9e2e-5081c2124c7d","request_count":681,"window_minutes":30,"p50_throughput":79,"p75_throughput":95,"p90_throughput":120,"p99_throughput":170.00000000000023,"p50_latency":614,"p75_latency":796,"p90_latency":1177,"p99_latency":3456.2000000000044},"82959141-f095-4f8f-92ce-f9b751be41e6":{"endpoint_id":"82959141-f095-4f8f-92ce-f9b751be41e6","request_count":70,"window_minutes":30,"p50_throughput":9,"p75_throughput":12,"p90_throughput":15.100000000000001,"p99_throughput":26.620000000000005,"p50_latency":9002.5,"p75_latency":10137,"p90_latency":11427.2,"p99_latency":14600.960000000005},"3aa2798e-0bbd-44f0-89a9-e949e169633d":{"endpoint_id":"3aa2798e-0bbd-44f0-89a9-e949e169633d","request_count":55,"window_minutes":30,"p50_throughput":2,"p75_throughput":6.5,"p90_throughput":10,"p99_throughput":22.440000000000012,"p50_latency":2808,"p75_latency":3135,"p90_latency":3504.8,"p99_latency":3918.38},"aa630b00-cc39-41e5-b1cd-de31a1b95d43":{"endpoint_id":"aa630b00-cc39-41e5-b1cd-de31a1b95d43","request_count":386,"window_minutes":30,"p50_throughput":15,"p75_throughput":22,"p90_throughput":26,"p99_throughput":87.59999999999991,"p50_latency":630,"p75_latency":685.75,"p90_latency":1077.5,"p99_latency":3644.499999999993},"0cd3013f-24e9-467d-a617-6232877aedb9":{"endpoint_id":"0cd3013f-24e9-467d-a617-6232877aedb9","request_count":31,"window_minutes":30,"p50_throughput":5,"p75_throughput":31,"p90_throughput":67,"p99_throughput":123.6,"p50_latency":938,"p75_latency":1289.5,"p90_latency":1789,"p99_latency":2309.5},"00366232-455a-441e-906a-4da12292f801":{"endpoint_id":"00366232-455a-441e-906a-4da12292f801","request_count":778,"window_minutes":30,"p50_throughput":65,"p75_throughput":135,"p90_throughput":187,"p99_throughput":309.69000000000005,"p50_latency":2355,"p75_latency":4691,"p90_latency":7852.400000000005,"p99_latency":18082.990000000027},"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f":{"endpoint_id":"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f","request_count":56310,"window_minutes":30,"p50_throughput":67,"p75_throughput":107,"p90_throughput":134,"p99_throughput":163,"p50_latency":803,"p75_latency":1427.25,"p90_latency":2541.9000000000005,"p99_latency":5423.4200000000055},"689cfb85-f673-4da5-961a-4f4711cc7d88":{"endpoint_id":"689cfb85-f673-4da5-961a-4f4711cc7d88","request_count":6334,"window_minutes":30,"p50_throughput":48,"p75_throughput":68,"p90_throughput":94,"p99_throughput":174,"p50_latency":1937.5,"p75_latency":3391,"p90_latency":5040.4,"p99_latency":10383.10000000001},"9ce3b132-3a17-4fea-8092-0e8e519ed32b":{"endpoint_id":"9ce3b132-3a17-4fea-8092-0e8e519ed32b","request_count":303,"window_minutes":30,"p50_throughput":24,"p75_throughput":32,"p90_throughput":41.80000000000001,"p99_throughput":58.960000000000036,"p50_latency":1972,"p75_latency":6080.5,"p90_latency":30895.600000000002,"p99_latency":140448.1000000003},"970aecad-f13b-4ec3-9362-e1758aea3e56":{"endpoint_id":"970aecad-f13b-4ec3-9362-e1758aea3e56","request_count":28777,"window_minutes":30,"p50_throughput":65.5,"p75_throughput":92,"p90_throughput":114,"p99_throughput":146,"p50_latency":1243,"p75_latency":2242.25,"p90_latency":4439,"p99_latency":14249.39000000001},"b893e351-21c8-4215-8f36-c761298acf9e":{"endpoint_id":"b893e351-21c8-4215-8f36-c761298acf9e","request_count":3139,"window_minutes":30,"p50_throughput":44,"p75_throughput":51,"p90_throughput":56,"p99_throughput":63,"p50_latency":2666,"p75_latency":6890,"p90_latency":12933.000000000005,"p99_latency":79855.93999999997},"bf1a3473-7a0a-46d3-aaa5-adb8f876a697":{"endpoint_id":"bf1a3473-7a0a-46d3-aaa5-adb8f876a697","request_count":220,"window_minutes":30,"p50_throughput":43,"p75_throughput":49,"p90_throughput":59,"p99_throughput":79.05000000000001,"p50_latency":1899,"p75_latency":2305,"p90_latency":2813.3,"p99_latency":4299.040000000001},"073a2dde-9ebc-4ae0-840f-c84fc8f72247":{"endpoint_id":"073a2dde-9ebc-4ae0-840f-c84fc8f72247","request_count":3383,"window_minutes":30,"p50_throughput":26,"p75_throughput":29,"p90_throughput":34,"p99_throughput":39,"p50_latency":500,"p75_latency":653,"p90_latency":973.4000000000005,"p99_latency":1729.0399999999954},"9ff5625c-403f-4d7f-b895-58ac7295062c":{"endpoint_id":"9ff5625c-403f-4d7f-b895-58ac7295062c","request_count":23931,"window_minutes":30,"p50_throughput":40,"p75_throughput":61,"p90_throughput":80,"p99_throughput":131,"p50_latency":1196,"p75_latency":1984.25,"p90_latency":3294.9000000000005,"p99_latency":11885.700000000004},"c2a24e34-c306-4b4d-9e2f-b162c2d8bf0e":{"endpoint_id":"c2a24e34-c306-4b4d-9e2f-b162c2d8bf0e","request_count":2799,"window_minutes":30,"p50_throughput":242,"p75_throughput":349,"p90_throughput":496.2000000000003,"p99_throughput":967.0799999999999,"p50_latency":1104,"p75_latency":2851.5,"p90_latency":9646.200000000012,"p99_latency":31257.65999999999},"e004ce39-eb0c-4474-93d5-55072e725970":{"endpoint_id":"e004ce39-eb0c-4474-93d5-55072e725970","request_count":67646,"window_minutes":30,"p50_throughput":72,"p75_throughput":147,"p90_throughput":218,"p99_throughput":333,"p50_latency":785,"p75_latency":1116,"p90_latency":1480,"p99_latency":3954.800000000003},"9265aa87-9657-4d40-b9d7-2a70318e57d9":{"endpoint_id":"9265aa87-9657-4d40-b9d7-2a70318e57d9","request_count":8807,"window_minutes":30,"p50_throughput":84,"p75_throughput":113,"p90_throughput":125,"p99_throughput":136,"p50_latency":1367.5,"p75_latency":2314,"p90_latency":3149.9000000000005,"p99_latency":5435.810000000001},"2d3e3ef1-e1fb-4515-b5c8-6f0779b0e7aa":{"endpoint_id":"2d3e3ef1-e1fb-4515-b5c8-6f0779b0e7aa","request_count":1937,"window_minutes":30,"p50_throughput":157,"p75_throughput":171,"p90_throughput":185,"p99_throughput":221.63999999999987,"p50_latency":8697,"p75_latency":9954,"p90_latency":12545.2,"p99_latency":22567.159999999996},"098f81e1-07f9-4f7c-a006-65c81138ddea":{"endpoint_id":"098f81e1-07f9-4f7c-a006-65c81138ddea","request_count":386,"window_minutes":30,"p50_throughput":83.5,"p75_throughput":109,"p90_throughput":120,"p99_throughput":159.04999999999984,"p50_latency":375.5,"p75_latency":645.75,"p90_latency":4991,"p99_latency":15340.649999999947},"f3f88554-0c22-4d57-973b-0dec948808e8":{"endpoint_id":"f3f88554-0c22-4d57-973b-0dec948808e8","request_count":2249,"window_minutes":30,"p50_throughput":22,"p75_throughput":57,"p90_throughput":64,"p99_throughput":82.51999999999998,"p50_latency":591,"p75_latency":995,"p90_latency":1424.8000000000002,"p99_latency":3835.1599999999994},"0a90a7cd-5063-4bcf-a228-e51ebb87feee":{"endpoint_id":"0a90a7cd-5063-4bcf-a228-e51ebb87feee","request_count":667,"window_minutes":30,"p50_throughput":21,"p75_throughput":78,"p90_throughput":116,"p99_throughput":143.0200000000001,"p50_latency":2580,"p75_latency":3337.5,"p90_latency":4746.799999999999,"p99_latency":7549.060000000016},"5f6b71b5-8672-4b27-8b2d-f674429f9e63":{"endpoint_id":"5f6b71b5-8672-4b27-8b2d-f674429f9e63","request_count":89539,"window_minutes":30,"p50_throughput":43,"p75_throughput":78,"p90_throughput":94,"p99_throughput":145,"p50_latency":584,"p75_latency":677,"p90_latency":872,"p99_latency":1902.3600000000006},"3ccc4f6d-d337-43ed-9c40-bb43618ba0ca":{"endpoint_id":"3ccc4f6d-d337-43ed-9c40-bb43618ba0ca","request_count":111,"window_minutes":30,"p50_throughput":62,"p75_throughput":86.5,"p90_throughput":104,"p99_throughput":119.80000000000001,"p50_latency":3762,"p75_latency":4608,"p90_latency":5670,"p99_latency":16678.400000000034},"75bb5ca0-7b08-4f1a-aca5-aa2bbf44d98e":{"endpoint_id":"75bb5ca0-7b08-4f1a-aca5-aa2bbf44d98e","request_count":1864,"window_minutes":30,"p50_throughput":64,"p75_throughput":92,"p90_throughput":113.70000000000005,"p99_throughput":157.3699999999999,"p50_latency":2156.5,"p75_latency":3500.25,"p90_latency":6887,"p99_latency":21540.439999999944},"1e93b0bb-eb0f-49bc-8fda-947105413b86":{"endpoint_id":"1e93b0bb-eb0f-49bc-8fda-947105413b86","request_count":468,"window_minutes":30,"p50_throughput":53,"p75_throughput":63,"p90_throughput":71,"p99_throughput":86.32999999999998,"p50_latency":744,"p75_latency":1070.25,"p90_latency":1659.2000000000005,"p99_latency":8832.819999999996},"2abf5677-0826-45d9-8470-3d62c31d54a1":{"endpoint_id":"2abf5677-0826-45d9-8470-3d62c31d54a1","request_count":3479,"window_minutes":30,"p50_throughput":83,"p75_throughput":100,"p90_throughput":114.20000000000027,"p99_throughput":140,"p50_latency":3420,"p75_latency":4311.5,"p90_latency":8414.400000000009,"p99_latency":56521.659999999916},"3ad4538c-bdd2-4161-86d8-8350c2bb8efa":{"endpoint_id":"3ad4538c-bdd2-4161-86d8-8350c2bb8efa","request_count":54312,"window_minutes":30,"p50_throughput":41,"p75_throughput":47,"p90_throughput":59,"p99_throughput":109,"p50_latency":1085,"p75_latency":1307,"p90_latency":1659,"p99_latency":4160.21000000001},"71e0f6c3-7815-4734-92d3-8a04f3b0ca91":{"endpoint_id":"71e0f6c3-7815-4734-92d3-8a04f3b0ca91","request_count":448,"window_minutes":30,"p50_throughput":51,"p75_throughput":56.25,"p90_throughput":66,"p99_throughput":151.52999999999997,"p50_latency":1681,"p75_latency":2368.25,"p90_latency":2820,"p99_latency":3878.629999999993},"180484a2-e24b-495a-ba41-b34b680d5a9f":{"endpoint_id":"180484a2-e24b-495a-ba41-b34b680d5a9f","request_count":9183,"window_minutes":30,"p50_throughput":49,"p75_throughput":59,"p90_throughput":103,"p99_throughput":134,"p50_latency":1028,"p75_latency":1425.25,"p90_latency":1980.9000000000005,"p99_latency":3110.9900000000016},"3146f103-e8d8-4832-851c-2a0284feec7c":{"endpoint_id":"3146f103-e8d8-4832-851c-2a0284feec7c","request_count":44,"window_minutes":30,"p50_throughput":15,"p75_throughput":22.75,"p90_throughput":35.400000000000006,"p99_throughput":71.55000000000001,"p50_latency":2215,"p75_latency":3992.25,"p90_latency":10427.100000000008,"p99_latency":33933.83},"a9ca9362-3ad6-458a-bd00-a9f09e42796c":{"endpoint_id":"a9ca9362-3ad6-458a-bd00-a9f09e42796c","request_count":1334,"window_minutes":30,"p50_throughput":59,"p75_throughput":69,"p90_throughput":80,"p99_throughput":115.01000000000022,"p50_latency":1126,"p75_latency":1417,"p90_latency":2065.6000000000004,"p99_latency":4986.130000000003},"0c13d1a9-ea55-4e4f-ad48-55e6319c0a3e":{"endpoint_id":"0c13d1a9-ea55-4e4f-ad48-55e6319c0a3e","request_count":65,"window_minutes":30,"p50_throughput":57,"p75_throughput":67,"p90_throughput":69.6,"p99_throughput":73,"p50_latency":931,"p75_latency":1137,"p90_latency":1445,"p99_latency":2255.0799999999995},"5bc0e1b6-d533-4cd1-ad21-20009af0a6d7":{"endpoint_id":"5bc0e1b6-d533-4cd1-ad21-20009af0a6d7","request_count":48,"window_minutes":30,"p50_throughput":29,"p75_throughput":37,"p90_throughput":41,"p99_throughput":54.30000000000001,"p50_latency":2690,"p75_latency":3479,"p90_latency":6468.000000000002,"p99_latency":14686.07},"abacc5e9-91e6-40bf-93c6-9112334a4042":{"endpoint_id":"abacc5e9-91e6-40bf-93c6-9112334a4042","request_count":3758,"window_minutes":30,"p50_throughput":45,"p75_throughput":60,"p90_throughput":74,"p99_throughput":93,"p50_latency":1002,"p75_latency":1372,"p90_latency":1789.3000000000002,"p99_latency":3487.6599999999735},"24266140-f37e-4c0f-8898-30821cb00ae3":{"endpoint_id":"24266140-f37e-4c0f-8898-30821cb00ae3","request_count":272,"window_minutes":30,"p50_throughput":75,"p75_throughput":81,"p90_throughput":86,"p99_throughput":99.4500000000001,"p50_latency":1186,"p75_latency":1402,"p90_latency":1735.9,"p99_latency":6507.870000000008},"a1659736-3cfc-47d9-b48f-303c93c57b11":{"endpoint_id":"a1659736-3cfc-47d9-b48f-303c93c57b11","request_count":2308,"window_minutes":30,"p50_throughput":45,"p75_throughput":68,"p90_throughput":90,"p99_throughput":128.92999999999984,"p50_latency":787,"p75_latency":1150.25,"p90_latency":2207.4000000000015,"p99_latency":17892.709999999846},"64e8da4e-6768-4de2-a17d-8dba04f8cdac":{"endpoint_id":"64e8da4e-6768-4de2-a17d-8dba04f8cdac","request_count":23,"window_minutes":30,"p50_throughput":82,"p75_throughput":125,"p90_throughput":140.8,"p99_throughput":141.78,"p50_latency":982,"p75_latency":1224,"p90_latency":2295.6000000000004,"p99_latency":3254.080000000001},"38c32567-be85-4c82-a6d8-592a4158d436":{"endpoint_id":"38c32567-be85-4c82-a6d8-592a4158d436","request_count":270,"window_minutes":30,"p50_throughput":24,"p75_throughput":35,"p90_throughput":45.099999999999994,"p99_throughput":59.31,"p50_latency":812.5,"p75_latency":1051.75,"p90_latency":1523.8999999999999,"p99_latency":2696.41},"c684c4e7-1b77-4ca5-9516-7ecc66e2c455":{"endpoint_id":"c684c4e7-1b77-4ca5-9516-7ecc66e2c455","request_count":68,"window_minutes":30,"p50_throughput":17,"p75_throughput":68.25,"p90_throughput":74,"p99_throughput":77,"p50_latency":564,"p75_latency":4001.5,"p90_latency":10335.400000000001,"p99_latency":17524.469999999994},"df1ccb5f-8dce-4d7e-8a34-5a6613b65995":{"endpoint_id":"df1ccb5f-8dce-4d7e-8a34-5a6613b65995","request_count":46,"window_minutes":30,"p50_throughput":85.5,"p75_throughput":113.75,"p90_throughput":118.5,"p99_throughput":122,"p50_latency":485.5,"p75_latency":612.5,"p90_latency":832.5,"p99_latency":2208.399999999996},"53417803-f19f-4905-af00-f7e023d09858":{"endpoint_id":"53417803-f19f-4905-af00-f7e023d09858","request_count":65054,"window_minutes":30,"p50_throughput":102,"p75_throughput":127,"p90_throughput":147,"p99_throughput":183,"p50_latency":442,"p75_latency":490,"p90_latency":568,"p99_latency":1686.7100000000028},"6efb5994-8fcb-4300-9c64-ba393193f5f6":{"endpoint_id":"6efb5994-8fcb-4300-9c64-ba393193f5f6","request_count":5909,"window_minutes":30,"p50_throughput":37,"p75_throughput":65,"p90_throughput":84,"p99_throughput":113,"p50_latency":392,"p75_latency":645,"p90_latency":1456,"p99_latency":4167.9200000000055},"112d4970-7f22-40d4-8ddb-3ca917583981":{"endpoint_id":"112d4970-7f22-40d4-8ddb-3ca917583981","request_count":504,"window_minutes":30,"p50_throughput":49,"p75_throughput":62.25,"p90_throughput":71,"p99_throughput":98.93999999999994,"p50_latency":3822.5,"p75_latency":6009.75,"p90_latency":10318.499999999996,"p99_latency":24731.649999999998},"e01a1227-001b-44d4-a376-90850668fa84":{"endpoint_id":"e01a1227-001b-44d4-a376-90850668fa84","request_count":4715,"window_minutes":30,"p50_throughput":64,"p75_throughput":77,"p90_throughput":93,"p99_throughput":119,"p50_latency":840,"p75_latency":1028,"p90_latency":1726.0000000000018,"p99_latency":3999.4199999999846},"d85c3862-4e0d-4f8d-955b-babc62f98124":{"endpoint_id":"d85c3862-4e0d-4f8d-955b-babc62f98124","request_count":25,"window_minutes":30,"p50_throughput":43,"p75_throughput":45,"p90_throughput":50.800000000000004,"p99_throughput":57.03999999999999,"p50_latency":2338,"p75_latency":13466,"p90_latency":27241.6,"p99_latency":39095.51999999997},"a300fcbb-ec0e-4c1f-a4d4-d06dc8c19cf9":{"endpoint_id":"a300fcbb-ec0e-4c1f-a4d4-d06dc8c19cf9","request_count":26,"window_minutes":30,"p50_throughput":69.5,"p75_throughput":87.5,"p90_throughput":118.5,"p99_throughput":146,"p50_latency":1598,"p75_latency":1905.75,"p90_latency":2490.5,"p99_latency":6820.25},"ab79ffa8-8dcc-41c4-9a9f-6cc408135243":{"endpoint_id":"ab79ffa8-8dcc-41c4-9a9f-6cc408135243","request_count":1259,"window_minutes":30,"p50_throughput":16,"p75_throughput":21,"p90_throughput":35,"p99_throughput":69.84000000000015,"p50_latency":1950,"p75_latency":7255,"p90_latency":17285.000000000007,"p99_latency":42530.34000000001},"6e82f652-2693-4b60-bbe0-7362d6e345f0":{"endpoint_id":"6e82f652-2693-4b60-bbe0-7362d6e345f0","request_count":81378,"window_minutes":30,"p50_throughput":68,"p75_throughput":104,"p90_throughput":149,"p99_throughput":266.09000000000015,"p50_latency":1224.5,"p75_latency":1728.25,"p90_latency":2411,"p99_latency":9153.400000000009},"2bd3912d-8b35-4818-b873-24ccfefa6cf9":{"endpoint_id":"2bd3912d-8b35-4818-b873-24ccfefa6cf9","request_count":293,"window_minutes":30,"p50_throughput":118,"p75_throughput":205,"p90_throughput":251.40000000000003,"p99_throughput":296.79999999999984,"p50_latency":1011,"p75_latency":4260,"p90_latency":7071.800000000001,"p99_latency":17346.799999999963},"1abae580-6f7a-4092-ae6c-b87ce6067f61":{"endpoint_id":"1abae580-6f7a-4092-ae6c-b87ce6067f61","request_count":19,"window_minutes":30,"p50_throughput":2,"p75_throughput":2,"p90_throughput":3,"p99_throughput":7.100000000000001,"p50_latency":3285,"p75_latency":4826,"p90_latency":5619.399999999999,"p99_latency":9376.02},"1b754062-b0f3-4cab-89d6-48b43782a25d":{"endpoint_id":"1b754062-b0f3-4cab-89d6-48b43782a25d","request_count":502,"window_minutes":30,"p50_throughput":35,"p75_throughput":49,"p90_throughput":71,"p99_throughput":138.97000000000003,"p50_latency":3240,"p75_latency":5347.75,"p90_latency":9844.300000000007,"p99_latency":29261.90000000001},"fbf41fc0-742d-4108-b97e-147ee85eff31":{"endpoint_id":"fbf41fc0-742d-4108-b97e-147ee85eff31","request_count":12,"window_minutes":30,"p50_throughput":5,"p75_throughput":21.25,"p90_throughput":121.00000000000003,"p99_throughput":144.13,"p50_latency":564.5,"p75_latency":659.75,"p90_latency":905.6000000000001,"p99_latency":1348.4100000000003},"a44ea9fe-fc2b-4765-804b-2e31215b5ca5":{"endpoint_id":"a44ea9fe-fc2b-4765-804b-2e31215b5ca5","request_count":1871,"window_minutes":30,"p50_throughput":6,"p75_throughput":18,"p90_throughput":34,"p99_throughput":72,"p50_latency":2795,"p75_latency":4604.5,"p90_latency":10404,"p99_latency":56865.29999999999},"40b40238-5f11-44f4-b56b-0c702bd6c5b2":{"endpoint_id":"40b40238-5f11-44f4-b56b-0c702bd6c5b2","request_count":13,"window_minutes":30,"p50_throughput":54,"p75_throughput":69,"p90_throughput":85.4,"p99_throughput":91.39999999999999,"p50_latency":2863,"p75_latency":3521,"p90_latency":4807.200000000001,"p99_latency":7373.319999999998},"b1b489e5-7029-4ab2-9e12-5415b55b4afa":{"endpoint_id":"b1b489e5-7029-4ab2-9e12-5415b55b4afa","request_count":284,"window_minutes":30,"p50_throughput":22,"p75_throughput":80,"p90_throughput":128.70000000000002,"p99_throughput":270.91000000000037,"p50_latency":464.5,"p75_latency":554,"p90_latency":704.5000000000002,"p99_latency":1835.140000000023},"4a4416f7-de7b-42d6-982d-3ab52d67a775":{"endpoint_id":"4a4416f7-de7b-42d6-982d-3ab52d67a775","request_count":2999,"window_minutes":30,"p50_throughput":28,"p75_throughput":35,"p90_throughput":44,"p99_throughput":62,"p50_latency":2710,"p75_latency":3951.5,"p90_latency":5419.200000000001,"p99_latency":12002.499999999998},"f5a725e2-8f66-4754-9232-7550685ab3d0":{"endpoint_id":"f5a725e2-8f66-4754-9232-7550685ab3d0","request_count":678,"window_minutes":30,"p50_throughput":79,"p75_throughput":87,"p90_throughput":93,"p99_throughput":108.23000000000002,"p50_latency":3491.5,"p75_latency":4278,"p90_latency":6063.500000000007,"p99_latency":38655.72000000003},"764eb97f-8bab-4326-b29b-7a8799b00a70":{"endpoint_id":"764eb97f-8bab-4326-b29b-7a8799b00a70","request_count":6250,"window_minutes":30,"p50_throughput":52,"p75_throughput":74,"p90_throughput":91,"p99_throughput":124,"p50_latency":915,"p75_latency":1606,"p90_latency":3572.600000000006,"p99_latency":32097.690000000002},"6cbf24ac-808c-4cbf-9e6c-c971f69c4de6":{"endpoint_id":"6cbf24ac-808c-4cbf-9e6c-c971f69c4de6","request_count":380,"window_minutes":30,"p50_throughput":62,"p75_throughput":86,"p90_throughput":100.10000000000002,"p99_throughput":114,"p50_latency":3403,"p75_latency":4949.75,"p90_latency":7144.7000000000035,"p99_latency":14414.02999999998},"cdb3ebc6-45e5-40ec-b586-48336ea95841":{"endpoint_id":"cdb3ebc6-45e5-40ec-b586-48336ea95841","request_count":114,"window_minutes":30,"p50_throughput":41.5,"p75_throughput":92.75,"p90_throughput":118,"p99_throughput":156.09000000000003,"p50_latency":3442.5,"p75_latency":7848.75,"p90_latency":16253.7,"p99_latency":92847.72000000023},"a5cbd682-c60f-49d4-afda-520de76d9435":{"endpoint_id":"a5cbd682-c60f-49d4-afda-520de76d9435","request_count":108,"window_minutes":30,"p50_throughput":37.5,"p75_throughput":42,"p90_throughput":46.3,"p99_throughput":64.85999999999999,"p50_latency":1470.5,"p75_latency":2083.5,"p90_latency":4060.499999999999,"p99_latency":70196.77999999955},"6e4da481-6c8d-45d0-a3f5-11a9ba527485":{"endpoint_id":"6e4da481-6c8d-45d0-a3f5-11a9ba527485","request_count":28,"window_minutes":30,"p50_throughput":21.5,"p75_throughput":32.25,"p90_throughput":36.3,"p99_throughput":52.60000000000001,"p50_latency":493.5,"p75_latency":661.25,"p90_latency":2513.100000000002,"p99_latency":32564.110000000004},"c78926bd-fa25-4883-8794-22de8c1ce79c":{"endpoint_id":"c78926bd-fa25-4883-8794-22de8c1ce79c","request_count":319,"window_minutes":30,"p50_throughput":67,"p75_throughput":97,"p90_throughput":113.19999999999999,"p99_throughput":152.45999999999998,"p50_latency":5174,"p75_latency":12970,"p90_latency":26293.8,"p99_latency":57075.039999999964},"814f9be0-e226-4b8c-bb5d-bf684359da13":{"endpoint_id":"814f9be0-e226-4b8c-bb5d-bf684359da13","request_count":1126,"window_minutes":30,"p50_throughput":40,"p75_throughput":69,"p90_throughput":99,"p99_throughput":131.75,"p50_latency":501,"p75_latency":716.5,"p90_latency":1031.5,"p99_latency":1642.5},"d83e34dd-4624-428d-8c3e-524be778e27f":{"endpoint_id":"d83e34dd-4624-428d-8c3e-524be778e27f","request_count":8141,"window_minutes":30,"p50_throughput":347,"p75_throughput":565,"p90_throughput":821,"p99_throughput":1513.800000000003,"p50_latency":296,"p75_latency":389,"p90_latency":527,"p99_latency":1059.800000000001},"46585386-044e-4e91-852c-f56bf056e1af":{"endpoint_id":"46585386-044e-4e91-852c-f56bf056e1af","request_count":70,"window_minutes":30,"p50_throughput":40.5,"p75_throughput":54,"p90_throughput":73.10000000000001,"p99_throughput":101.93,"p50_latency":1299.5,"p75_latency":1915.5,"p90_latency":2511.1000000000004,"p99_latency":3178.7200000000003},"5e9377cb-bd6f-4940-8a25-c787a4ccec95":{"endpoint_id":"5e9377cb-bd6f-4940-8a25-c787a4ccec95","request_count":12853,"window_minutes":30,"p50_throughput":47,"p75_throughput":62,"p90_throughput":70,"p99_throughput":80,"p50_latency":754,"p75_latency":1109,"p90_latency":1662.9000000000005,"p99_latency":4265.350000000002},"99acb983-d859-4f77-bb89-5d9f05985bbe":{"endpoint_id":"99acb983-d859-4f77-bb89-5d9f05985bbe","request_count":660,"window_minutes":30,"p50_throughput":32,"p75_throughput":35,"p90_throughput":36,"p99_throughput":38,"p50_latency":421,"p75_latency":622,"p90_latency":904.1000000000003,"p99_latency":2218.8399999999992},"7c09094a-64ec-4d53-bd69-c165ac31c465":{"endpoint_id":"7c09094a-64ec-4d53-bd69-c165ac31c465","request_count":58,"window_minutes":30,"p50_throughput":114,"p75_throughput":120.75,"p90_throughput":126,"p99_throughput":155.9,"p50_latency":597.5,"p75_latency":6773,"p90_latency":8550.2,"p99_latency":23076.189999999995},"41d2915a-92e6-4993-b537-210b4e10cba8":{"endpoint_id":"41d2915a-92e6-4993-b537-210b4e10cba8","request_count":16784,"window_minutes":30,"p50_throughput":61,"p75_throughput":87,"p90_throughput":113,"p99_throughput":184.09000000000015,"p50_latency":686,"p75_latency":890,"p90_latency":1253.9000000000005,"p99_latency":7366.200000000012},"6cb46014-347b-4d67-aefa-7b83e065b8c3":{"endpoint_id":"6cb46014-347b-4d67-aefa-7b83e065b8c3","request_count":24,"window_minutes":30,"p50_throughput":131,"p75_throughput":139.25,"p90_throughput":142,"p99_throughput":162.25,"p50_latency":410.5,"p75_latency":470.25,"p90_latency":515.4,"p99_latency":820.8199999999998},"0122dcb7-c876-4445-8a8e-610a7b44d12b":{"endpoint_id":"0122dcb7-c876-4445-8a8e-610a7b44d12b","request_count":11419,"window_minutes":30,"p50_throughput":54,"p75_throughput":92,"p90_throughput":111,"p99_throughput":131,"p50_latency":541,"p75_latency":803,"p90_latency":1144.9000000000005,"p99_latency":2751.09},"be0ed145-8bfc-4aec-a62d-685ed334fe17":{"endpoint_id":"be0ed145-8bfc-4aec-a62d-685ed334fe17","request_count":48,"window_minutes":30,"p50_throughput":92.5,"p75_throughput":120.25,"p90_throughput":149.9,"p99_throughput":168.53,"p50_latency":6537,"p75_latency":12815.75,"p90_latency":20282.10000000001,"p99_latency":25441.89},"2341e1bc-99ea-46ab-ae2d-9a83846afb43":{"endpoint_id":"2341e1bc-99ea-46ab-ae2d-9a83846afb43","request_count":131,"window_minutes":30,"p50_throughput":200,"p75_throughput":217,"p90_throughput":246,"p99_throughput":291.9999999999999,"p50_latency":5790,"p75_latency":6443,"p90_latency":7131,"p99_latency":10589.599999999977},"bad35a82-60b3-4cbb-ad64-fb0fa0e25318":{"endpoint_id":"bad35a82-60b3-4cbb-ad64-fb0fa0e25318","request_count":44,"window_minutes":30,"p50_throughput":109,"p75_throughput":121,"p90_throughput":125,"p99_throughput":131.28,"p50_latency":683.5,"p75_latency":1014,"p90_latency":1591.6000000000013,"p99_latency":2551.9},"27e433ca-988e-4aaa-902a-37bc06c59e3b":{"endpoint_id":"27e433ca-988e-4aaa-902a-37bc06c59e3b","request_count":4914,"window_minutes":30,"p50_throughput":17,"p75_throughput":39,"p90_throughput":56,"p99_throughput":115,"p50_latency":522,"p75_latency":601,"p90_latency":872.0999999999995,"p99_latency":1945.87},"86e3e664-d291-415d-a769-8e08b96a79e9":{"endpoint_id":"86e3e664-d291-415d-a769-8e08b96a79e9","request_count":6,"window_minutes":30,"p50_throughput":5.5,"p75_throughput":21,"p90_throughput":28,"p99_throughput":29.800000000000004,"p50_latency":21227,"p75_latency":105673.5,"p90_latency":266225.5,"p99_latency":386216.65},"76fb879b-32f4-4ac0-8020-d29c0f9c60fa":{"endpoint_id":"76fb879b-32f4-4ac0-8020-d29c0f9c60fa","request_count":1431,"window_minutes":30,"p50_throughput":32,"p75_throughput":39,"p90_throughput":49,"p99_throughput":70,"p50_latency":1059,"p75_latency":1476,"p90_latency":2021,"p99_latency":6235.3000000000075},"3a2c65ff-b039-4459-804a-9aafcb4d693c":{"endpoint_id":"3a2c65ff-b039-4459-804a-9aafcb4d693c","request_count":1574,"window_minutes":30,"p50_throughput":35,"p75_throughput":41,"p90_throughput":51,"p99_throughput":74,"p50_latency":1129,"p75_latency":1509.75,"p90_latency":2254.1000000000004,"p99_latency":4158.529999999999},"1b484aef-be8f-4016-8762-2e3caabbab9f":{"endpoint_id":"1b484aef-be8f-4016-8762-2e3caabbab9f","request_count":22297,"window_minutes":30,"p50_throughput":22,"p75_throughput":32,"p90_throughput":35,"p99_throughput":38,"p50_latency":1546,"p75_latency":1880,"p90_latency":2501.800000000001,"p99_latency":4270.09},"4d46db86-63fe-47eb-85f1-6a7567af190c":{"endpoint_id":"4d46db86-63fe-47eb-85f1-6a7567af190c","request_count":908,"window_minutes":30,"p50_throughput":12,"p75_throughput":15,"p90_throughput":17,"p99_throughput":20,"p50_latency":997.5,"p75_latency":1845.25,"p90_latency":2847.5000000000005,"p99_latency":10473.329999999976},"a4766f32-79c6-485a-8371-bff388d93df8":{"endpoint_id":"a4766f32-79c6-485a-8371-bff388d93df8","request_count":157,"window_minutes":30,"p50_throughput":58,"p75_throughput":60,"p90_throughput":62,"p99_throughput":64,"p50_latency":590,"p75_latency":721,"p90_latency":2217.600000000006,"p99_latency":12711.6},"a352cc82-2bdb-411b-9f99-bd7829655412":{"endpoint_id":"a352cc82-2bdb-411b-9f99-bd7829655412","request_count":6680,"window_minutes":30,"p50_throughput":6,"p75_throughput":11,"p90_throughput":18,"p99_throughput":35,"p50_latency":711.5,"p75_latency":2364.25,"p90_latency":4047.300000000001,"p99_latency":10312.170000000002},"5e31ba3c-d5bf-4ced-a52d-96e2e6635f95":{"endpoint_id":"5e31ba3c-d5bf-4ced-a52d-96e2e6635f95","request_count":1013,"window_minutes":30,"p50_throughput":44,"p75_throughput":52,"p90_throughput":57,"p99_throughput":63.879999999999995,"p50_latency":912,"p75_latency":1132,"p90_latency":1476.6000000000004,"p99_latency":2342.2},"bc011219-e28e-416d-9cca-9aaf022f227e":{"endpoint_id":"bc011219-e28e-416d-9cca-9aaf022f227e","request_count":173,"window_minutes":30,"p50_throughput":38,"p75_throughput":67,"p90_throughput":89.80000000000001,"p99_throughput":117.56,"p50_latency":1230,"p75_latency":1339,"p90_latency":1565.0000000000005,"p99_latency":2706.4},"812bc18a-5b61-42d0-a550-f9ed8c2164c5":{"endpoint_id":"812bc18a-5b61-42d0-a550-f9ed8c2164c5","request_count":865,"window_minutes":30,"p50_throughput":24,"p75_throughput":28,"p90_throughput":32,"p99_throughput":38,"p50_latency":2237,"p75_latency":3063,"p90_latency":4559.200000000001,"p99_latency":10686.600000000006},"ded5f1ed-4249-476c-a19e-df63b005a8b7":{"endpoint_id":"ded5f1ed-4249-476c-a19e-df63b005a8b7","request_count":958,"window_minutes":30,"p50_throughput":57,"p75_throughput":63.75,"p90_throughput":70,"p99_throughput":91,"p50_latency":776.5,"p75_latency":881.75,"p90_latency":937.3000000000001,"p99_latency":1330.4299999999998},"1b075e5f-051b-4d60-9bc3-20f69ff6355d":{"endpoint_id":"1b075e5f-051b-4d60-9bc3-20f69ff6355d","request_count":31,"window_minutes":30,"p50_throughput":189,"p75_throughput":237,"p90_throughput":257,"p99_throughput":263,"p50_latency":489,"p75_latency":708,"p90_latency":746,"p99_latency":864.3},"74635ab6-7ba2-4cd7-8f2f-10651305385a":{"endpoint_id":"74635ab6-7ba2-4cd7-8f2f-10651305385a","request_count":1452,"window_minutes":30,"p50_throughput":89,"p75_throughput":150,"p90_throughput":205,"p99_throughput":312.49,"p50_latency":346,"p75_latency":527.5,"p90_latency":746.7000000000003,"p99_latency":2576.5300000000025},"23a86833-b536-4529-94c4-a18746e95c60":{"endpoint_id":"23a86833-b536-4529-94c4-a18746e95c60","request_count":54,"window_minutes":30,"p50_throughput":57,"p75_throughput":80.5,"p90_throughput":85.7,"p99_throughput":88.94,"p50_latency":622,"p75_latency":758,"p90_latency":1508.1,"p99_latency":3848.8099999999968},"3d871d0b-eade-4fd4-95b3-1d5f25e2b0c3":{"endpoint_id":"3d871d0b-eade-4fd4-95b3-1d5f25e2b0c3","request_count":23,"window_minutes":30,"p50_throughput":62,"p75_throughput":66.5,"p90_throughput":70.60000000000001,"p99_throughput":102.18000000000004,"p50_latency":351,"p75_latency":389.5,"p90_latency":459.8,"p99_latency":663.8000000000003},"262402a8-8891-4131-bc3c-a76c4bb9b391":{"endpoint_id":"262402a8-8891-4131-bc3c-a76c4bb9b391","request_count":6156,"window_minutes":30,"p50_throughput":19,"p75_throughput":30,"p90_throughput":38,"p99_throughput":43,"p50_latency":642,"p75_latency":726,"p90_latency":891,"p99_latency":2424.0999999999967},"86834360-63c5-482a-8ef9-85b22ddf0980":{"endpoint_id":"86834360-63c5-482a-8ef9-85b22ddf0980","request_count":26,"window_minutes":30,"p50_throughput":136,"p75_throughput":140.75,"p90_throughput":144.5,"p99_throughput":152,"p50_latency":314.5,"p75_latency":329.75,"p90_latency":358.5,"p99_latency":4302.5},"9e1bd3ed-059c-4fcf-9435-c1993ef564db":{"endpoint_id":"9e1bd3ed-059c-4fcf-9435-c1993ef564db","request_count":3209,"window_minutes":30,"p50_throughput":78,"p75_throughput":88,"p90_throughput":95,"p99_throughput":107.92000000000007,"p50_latency":190,"p75_latency":301,"p90_latency":466.8000000000011,"p99_latency":1770.520000000006},"c575da03-bbd8-4d9e-963d-497ea0ffcb13":{"endpoint_id":"c575da03-bbd8-4d9e-963d-497ea0ffcb13","request_count":343,"window_minutes":30,"p50_throughput":35,"p75_throughput":39,"p90_throughput":41,"p99_throughput":45,"p50_latency":462,"p75_latency":758.5,"p90_latency":1850.4000000000008,"p99_latency":5143.239999999994},"012f7d1f-23d4-4d03-9aa3-432d8ad82757":{"endpoint_id":"012f7d1f-23d4-4d03-9aa3-432d8ad82757","request_count":7156,"window_minutes":30,"p50_throughput":11,"p75_throughput":13,"p90_throughput":15,"p99_throughput":22,"p50_latency":805,"p75_latency":1180,"p90_latency":1903,"p99_latency":5938.399999999976},"13c5002b-8c5b-490c-8a5f-52ec0242804f":{"endpoint_id":"13c5002b-8c5b-490c-8a5f-52ec0242804f","request_count":954,"window_minutes":30,"p50_throughput":54,"p75_throughput":65,"p90_throughput":88,"p99_throughput":132.94000000000005,"p50_latency":498,"p75_latency":977,"p90_latency":1717.7,"p99_latency":9643.530000000002},"30f10717-f218-430f-a3d7-858bf5fdf303":{"endpoint_id":"30f10717-f218-430f-a3d7-858bf5fdf303","request_count":25,"window_minutes":30,"p50_throughput":67,"p75_throughput":78,"p90_throughput":91.2,"p99_throughput":119.35999999999999,"p50_latency":1439,"p75_latency":2000,"p90_latency":4593.600000000002,"p99_latency":9018.399999999998},"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4":{"endpoint_id":"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4","request_count":6269,"window_minutes":30,"p50_throughput":64,"p75_throughput":82,"p90_throughput":97,"p99_throughput":124,"p50_latency":3632,"p75_latency":6426,"p90_latency":12874.4,"p99_latency":34231.719999999994},"2609e67e-dcd4-401e-ae80-014ea7f111d8":{"endpoint_id":"2609e67e-dcd4-401e-ae80-014ea7f111d8","request_count":2467,"window_minutes":30,"p50_throughput":71,"p75_throughput":96,"p90_throughput":116,"p99_throughput":137.34000000000015,"p50_latency":4267,"p75_latency":6831.5,"p90_latency":11638.400000000001,"p99_latency":31878.66000000002},"36b76b2b-0b8d-423c-9e90-a8bba875ef45":{"endpoint_id":"36b76b2b-0b8d-423c-9e90-a8bba875ef45","request_count":1671,"window_minutes":30,"p50_throughput":84,"p75_throughput":105,"p90_throughput":125,"p99_throughput":158.29999999999995,"p50_latency":3142,"p75_latency":5244,"p90_latency":10107,"p99_latency":24521.6},"5595698f-9ce8-4aa8-8037-f0d7d3c13d2a":{"endpoint_id":"5595698f-9ce8-4aa8-8037-f0d7d3c13d2a","request_count":40539,"window_minutes":30,"p50_throughput":33,"p75_throughput":40,"p90_throughput":47,"p99_throughput":58,"p50_latency":486.5,"p75_latency":653,"p90_latency":1225.9000000000005,"p99_latency":10534.870000000006},"e668be79-ecd1-4163-9cec-7a3664486541":{"endpoint_id":"e668be79-ecd1-4163-9cec-7a3664486541","request_count":29152,"window_minutes":30,"p50_throughput":71,"p75_throughput":82,"p90_throughput":91,"p99_throughput":103,"p50_latency":290,"p75_latency":449,"p90_latency":849,"p99_latency":11910.800000000032},"ece5c3c6-e437-4297-92fc-150a1771ec56":{"endpoint_id":"ece5c3c6-e437-4297-92fc-150a1771ec56","request_count":63,"window_minutes":30,"p50_throughput":6,"p75_throughput":10.5,"p90_throughput":15.600000000000009,"p99_throughput":27.800000000000026,"p50_latency":3349,"p75_latency":4084,"p90_latency":5336.400000000001,"p99_latency":7451.18},"dfdc2841-297c-4de9-96fe-eab0ccfa25a6":{"endpoint_id":"dfdc2841-297c-4de9-96fe-eab0ccfa25a6","request_count":549,"window_minutes":30,"p50_throughput":49,"p75_throughput":88,"p90_throughput":155,"p99_throughput":193.51999999999998,"p50_latency":338,"p75_latency":411,"p90_latency":543.8,"p99_latency":984.9999999999995},"ded7fa7f-5261-4772-87fb-96994d95c6b9":{"endpoint_id":"ded7fa7f-5261-4772-87fb-96994d95c6b9","request_count":167,"window_minutes":30,"p50_throughput":29,"p75_throughput":43,"p90_throughput":61.20000000000002,"p99_throughput":105,"p50_latency":952,"p75_latency":1235,"p90_latency":1599.8000000000002,"p99_latency":2061.68},"4ea9b8c2-e4a8-4707-8e4b-a8693745edbe":{"endpoint_id":"4ea9b8c2-e4a8-4707-8e4b-a8693745edbe","request_count":14368,"window_minutes":30,"p50_throughput":16,"p75_throughput":52,"p90_throughput":107,"p99_throughput":183,"p50_latency":1568,"p75_latency":2392,"p90_latency":2920,"p99_latency":10879.590000000022},"48b95ad9-4c60-411f-8b5b-c3f1745c4f62":{"endpoint_id":"48b95ad9-4c60-411f-8b5b-c3f1745c4f62","request_count":155,"window_minutes":30,"p50_throughput":42,"p75_throughput":49.5,"p90_throughput":55,"p99_throughput":71.38000000000002,"p50_latency":3108,"p75_latency":5730,"p90_latency":9607.199999999999,"p99_latency":21768.88},"90fc9bb3-01bb-419f-bb58-dea60a80d201":{"endpoint_id":"90fc9bb3-01bb-419f-bb58-dea60a80d201","request_count":729,"window_minutes":30,"p50_throughput":51,"p75_throughput":63,"p90_throughput":71,"p99_throughput":81,"p50_latency":590,"p75_latency":860,"p90_latency":1396.0000000000005,"p99_latency":8704.96000000001},"f246192a-ff8f-4b6c-b2ac-62b3bd24c455":{"endpoint_id":"f246192a-ff8f-4b6c-b2ac-62b3bd24c455","request_count":67,"window_minutes":30,"p50_throughput":68,"p75_throughput":79.5,"p90_throughput":84.4,"p99_throughput":96.02000000000001,"p50_latency":771,"p75_latency":1803,"p90_latency":3770.4,"p99_latency":13245.100000000028},"803d4906-0d0b-49b6-8705-7ae0a4d45217":{"endpoint_id":"803d4906-0d0b-49b6-8705-7ae0a4d45217","request_count":503,"window_minutes":30,"p50_throughput":59,"p75_throughput":88,"p90_throughput":117,"p99_throughput":154.98000000000002,"p50_latency":954,"p75_latency":1585,"p90_latency":2470.6000000000004,"p99_latency":8363.18},"22a474a1-cb4e-42d2-b19a-c1be103f5abd":{"endpoint_id":"22a474a1-cb4e-42d2-b19a-c1be103f5abd","request_count":240,"window_minutes":30,"p50_throughput":9.5,"p75_throughput":26,"p90_throughput":42,"p99_throughput":60.609999999999985,"p50_latency":1492.5,"p75_latency":4826.5,"p90_latency":13203.999999999998,"p99_latency":31017.459999999977},"6b2ea9bc-3a79-441d-97a4-9b7d33210122":{"endpoint_id":"6b2ea9bc-3a79-441d-97a4-9b7d33210122","request_count":450449,"window_minutes":30,"p50_throughput":101,"p75_throughput":205,"p90_throughput":253,"p99_throughput":418.09000000000015,"p50_latency":377,"p75_latency":625,"p90_latency":1170,"p99_latency":2930.1600000000035},"7f8598e4-091b-424e-a9c2-158532af1537":{"endpoint_id":"7f8598e4-091b-424e-a9c2-158532af1537","request_count":15346,"window_minutes":30,"p50_throughput":27,"p75_throughput":37,"p90_throughput":44,"p99_throughput":52,"p50_latency":1291,"p75_latency":1554,"p90_latency":1949,"p99_latency":4392.150000000005},"f5265deb-6c78-49da-97e8-0f0b3dae6c5b":{"endpoint_id":"f5265deb-6c78-49da-97e8-0f0b3dae6c5b","request_count":1012,"window_minutes":30,"p50_throughput":31,"p75_throughput":38,"p90_throughput":52,"p99_throughput":76,"p50_latency":886.5,"p75_latency":1284,"p90_latency":2557.8999999999996,"p99_latency":38704.419999999984},"7e8cc035-ab66-4fe4-a484-657a83d1be50":{"endpoint_id":"7e8cc035-ab66-4fe4-a484-657a83d1be50","request_count":728,"window_minutes":30,"p50_throughput":46,"p75_throughput":79,"p90_throughput":111.30000000000007,"p99_throughput":268.22000000000025,"p50_latency":774,"p75_latency":1258,"p90_latency":1688,"p99_latency":4906.750000000007},"519e0e1e-7254-41de-abe1-2e0ebf026ce9":{"endpoint_id":"519e0e1e-7254-41de-abe1-2e0ebf026ce9","request_count":30,"window_minutes":30,"p50_throughput":41,"p75_throughput":44,"p90_throughput":45.1,"p99_throughput":46.71,"p50_latency":1341,"p75_latency":1402.5,"p90_latency":1529.4000000000003,"p99_latency":2339.7700000000004},"df8da1e4-a390-4020-a25f-d12d77f65b22":{"endpoint_id":"df8da1e4-a390-4020-a25f-d12d77f65b22","request_count":20,"window_minutes":30,"p50_throughput":4.5,"p75_throughput":44.75,"p90_throughput":4189.700000000001,"p99_throughput":4505.78,"p50_latency":422.5,"p75_latency":515,"p90_latency":1169.2,"p99_latency":2782.0899999999974},"1fe59382-263d-4107-a768-d7d2007bd3b6":{"endpoint_id":"1fe59382-263d-4107-a768-d7d2007bd3b6","request_count":45,"window_minutes":30,"p50_throughput":25,"p75_throughput":27,"p90_throughput":33.6,"p99_throughput":45.120000000000005,"p50_latency":1647,"p75_latency":2794,"p90_latency":3134.8,"p99_latency":10379.44},"0ebc91cd-74bd-44ab-9c9a-c1f17d19f128":{"endpoint_id":"0ebc91cd-74bd-44ab-9c9a-c1f17d19f128","request_count":21786,"window_minutes":30,"p50_throughput":34,"p75_throughput":46,"p90_throughput":61,"p99_throughput":85,"p50_latency":303,"p75_latency":441,"p90_latency":695,"p99_latency":2546.670000000009},"dd5bc8d5-68a7-48a7-a680-db37579d5c14":{"endpoint_id":"dd5bc8d5-68a7-48a7-a680-db37579d5c14","request_count":29,"window_minutes":30,"p50_throughput":78,"p75_throughput":100,"p90_throughput":118.4,"p99_throughput":133.2,"p50_latency":793,"p75_latency":963,"p90_latency":1282.6,"p99_latency":2000.0399999999995},"b9b095f0-6448-46bb-8e4c-0111ba2bf1b0":{"endpoint_id":"b9b095f0-6448-46bb-8e4c-0111ba2bf1b0","request_count":277699,"window_minutes":30,"p50_throughput":81,"p75_throughput":128,"p90_throughput":173,"p99_throughput":254.09000000000015,"p50_latency":718,"p75_latency":1417,"p90_latency":2398,"p99_latency":7481.990000000002},"43106252-bd69-498f-84f5-1fde678783f7":{"endpoint_id":"43106252-bd69-498f-84f5-1fde678783f7","request_count":13183,"window_minutes":30,"p50_throughput":89,"p75_throughput":106,"p90_throughput":114,"p99_throughput":129,"p50_latency":2339,"p75_latency":3752.75,"p90_latency":5842.900000000001,"p99_latency":9880.45},"0f47837d-9d06-4c68-a93c-29b0c7cd9027":{"endpoint_id":"0f47837d-9d06-4c68-a93c-29b0c7cd9027","request_count":1339,"window_minutes":30,"p50_throughput":19,"p75_throughput":21,"p90_throughput":23,"p99_throughput":26,"p50_latency":734,"p75_latency":1011,"p90_latency":1527.6000000000004,"p99_latency":21479.95999999994},"02160c8a-a3b3-4958-bbb4-47c83f0376d5":{"endpoint_id":"02160c8a-a3b3-4958-bbb4-47c83f0376d5","request_count":57,"window_minutes":30,"p50_throughput":23,"p75_throughput":28,"p90_throughput":38,"p99_throughput":51.39999999999998,"p50_latency":2138,"p75_latency":2527,"p90_latency":3408.6,"p99_latency":4274.119999999997},"3a66dd68-b711-4d75-bbea-56012edd68bb":{"endpoint_id":"3a66dd68-b711-4d75-bbea-56012edd68bb","request_count":671,"window_minutes":30,"p50_throughput":41,"p75_throughput":45,"p90_throughput":50,"p99_throughput":85.29999999999995,"p50_latency":766,"p75_latency":1102.5,"p90_latency":1444,"p99_latency":2988.4999999999986},"2fbebc5f-9439-4d6d-af69-0c7aec1c4392":{"endpoint_id":"2fbebc5f-9439-4d6d-af69-0c7aec1c4392","request_count":9975,"window_minutes":30,"p50_throughput":39,"p75_throughput":48,"p90_throughput":54,"p99_throughput":64,"p50_latency":241,"p75_latency":391,"p90_latency":1550,"p99_latency":5802.440000000002},"850b84c3-42a7-4cec-99c0-b5582d0da66b":{"endpoint_id":"850b84c3-42a7-4cec-99c0-b5582d0da66b","request_count":5496,"window_minutes":30,"p50_throughput":6,"p75_throughput":9,"p90_throughput":13,"p99_throughput":25,"p50_latency":448,"p75_latency":791.25,"p90_latency":1450,"p99_latency":3804.9000000000033},"efdfff77-9574-4695-8e08-32d968a43376":{"endpoint_id":"efdfff77-9574-4695-8e08-32d968a43376","request_count":419,"window_minutes":30,"p50_throughput":42,"p75_throughput":59,"p90_throughput":77,"p99_throughput":102.45999999999998,"p50_latency":322,"p75_latency":515,"p90_latency":1149.1999999999998,"p99_latency":4107.859999999999},"633e82ca-271e-48a2-a8b3-9b69db4e2311":{"endpoint_id":"633e82ca-271e-48a2-a8b3-9b69db4e2311","request_count":7150,"window_minutes":30,"p50_throughput":58,"p75_throughput":62,"p90_throughput":66,"p99_throughput":75,"p50_latency":642,"p75_latency":772,"p90_latency":1042.1000000000004,"p99_latency":4047.040000000001},"c399a914-434e-4f21-b11b-8f4b3b2ec72c":{"endpoint_id":"c399a914-434e-4f21-b11b-8f4b3b2ec72c","request_count":2171,"window_minutes":30,"p50_throughput":53,"p75_throughput":61,"p90_throughput":64,"p99_throughput":67,"p50_latency":717,"p75_latency":974.5,"p90_latency":1251,"p99_latency":4066.7000000000016},"6b8c829d-3094-45e7-8139-0a67e09060c3":{"endpoint_id":"6b8c829d-3094-45e7-8139-0a67e09060c3","request_count":36168,"window_minutes":30,"p50_throughput":25,"p75_throughput":30,"p90_throughput":51,"p99_throughput":68,"p50_latency":459,"p75_latency":987.25,"p90_latency":1597.9000000000005,"p99_latency":3435.0800000000017},"6f60fa24-0b39-42e2-a3ce-b524504c5cfa":{"endpoint_id":"6f60fa24-0b39-42e2-a3ce-b524504c5cfa","request_count":2733,"window_minutes":30,"p50_throughput":48,"p75_throughput":54,"p90_throughput":59,"p99_throughput":67,"p50_latency":673,"p75_latency":1136,"p90_latency":1786.6000000000013,"p99_latency":6650.359999999975},"60020533-2fb2-4aa1-9454-181029fd52de":{"endpoint_id":"60020533-2fb2-4aa1-9454-181029fd52de","request_count":32,"window_minutes":30,"p50_throughput":105.5,"p75_throughput":113.5,"p90_throughput":121.50000000000001,"p99_throughput":133.97000000000003,"p50_latency":3313,"p75_latency":5578.25,"p90_latency":7892.000000000002,"p99_latency":27960.200000000015},"42e72619-d01c-411c-a201-f991644768b7":{"endpoint_id":"42e72619-d01c-411c-a201-f991644768b7","request_count":350,"window_minutes":30,"p50_throughput":68,"p75_throughput":83,"p90_throughput":98,"p99_throughput":135.03999999999996,"p50_latency":4360,"p75_latency":6326.5,"p90_latency":9055.2,"p99_latency":24638.309999999954},"bd121898-b27c-4e2c-bc92-278627465a54":{"endpoint_id":"bd121898-b27c-4e2c-bc92-278627465a54","request_count":293,"window_minutes":30,"p50_throughput":91,"p75_throughput":112,"p90_throughput":126,"p99_throughput":148.31999999999994,"p50_latency":4658,"p75_latency":7364,"p90_latency":11204.400000000003,"p99_latency":24757.519999999997},"c235abe8-11cc-42d3-95ad-72f4d198287a":{"endpoint_id":"c235abe8-11cc-42d3-95ad-72f4d198287a","request_count":39445,"window_minutes":30,"p50_throughput":37,"p75_throughput":63,"p90_throughput":87,"p99_throughput":136,"p50_latency":751,"p75_latency":1003.25,"p90_latency":1543,"p99_latency":4465.170000000002},"1551aa56-4221-448a-b280-f862f73c27de":{"endpoint_id":"1551aa56-4221-448a-b280-f862f73c27de","request_count":6264,"window_minutes":30,"p50_throughput":32,"p75_throughput":50.25,"p90_throughput":64,"p99_throughput":90,"p50_latency":726,"p75_latency":953.25,"p90_latency":1458.3999999999996,"p99_latency":4025.7599999999948},"1826e686-ee39-4fdd-af2b-6e0c6fb2e6da":{"endpoint_id":"1826e686-ee39-4fdd-af2b-6e0c6fb2e6da","request_count":1781,"window_minutes":30,"p50_throughput":63,"p75_throughput":137,"p90_throughput":171,"p99_throughput":212.20000000000005,"p50_latency":685,"p75_latency":1148,"p90_latency":2484,"p99_latency":10330.600000000046},"caa850a1-e628-41bd-8585-9b3076efea90":{"endpoint_id":"caa850a1-e628-41bd-8585-9b3076efea90","request_count":4051,"window_minutes":30,"p50_throughput":21,"p75_throughput":28,"p90_throughput":34,"p99_throughput":52,"p50_latency":529,"p75_latency":699,"p90_latency":950,"p99_latency":2070.5},"9cf05ded-eefe-41b4-8c08-0c6460feffea":{"endpoint_id":"9cf05ded-eefe-41b4-8c08-0c6460feffea","request_count":11319,"window_minutes":30,"p50_throughput":31,"p75_throughput":44,"p90_throughput":58,"p99_throughput":84,"p50_latency":379,"p75_latency":575,"p90_latency":885,"p99_latency":2203.09},"820376cb-f110-4d56-ab52-5bd6ca269420":{"endpoint_id":"820376cb-f110-4d56-ab52-5bd6ca269420","request_count":814,"window_minutes":30,"p50_throughput":28,"p75_throughput":36,"p90_throughput":42,"p99_throughput":52,"p50_latency":685.5,"p75_latency":1701.25,"p90_latency":4775.900000000003,"p99_latency":11763.780000000002},"35a93f0c-ce8f-4475-a6db-a383cc128360":{"endpoint_id":"35a93f0c-ce8f-4475-a6db-a383cc128360","request_count":596,"window_minutes":30,"p50_throughput":36,"p75_throughput":44.25,"p90_throughput":51,"p99_throughput":60,"p50_latency":531.5,"p75_latency":873.25,"p90_latency":1556,"p99_latency":3581.049999999996},"eb06dc92-5a16-47ec-a776-6ef956457c47":{"endpoint_id":"eb06dc92-5a16-47ec-a776-6ef956457c47","request_count":62066,"window_minutes":30,"p50_throughput":5,"p75_throughput":15,"p90_throughput":32,"p99_throughput":49,"p50_latency":602,"p75_latency":850,"p90_latency":1216,"p99_latency":2676.4400000000023},"2e152629-dac1-41b0-8f4f-f8c449d2d504":{"endpoint_id":"2e152629-dac1-41b0-8f4f-f8c449d2d504","request_count":109,"window_minutes":30,"p50_throughput":17,"p75_throughput":60,"p90_throughput":69,"p99_throughput":85.12000000000002,"p50_latency":197,"p75_latency":238,"p90_latency":320.4,"p99_latency":4839.920000000007},"8f22002c-c045-446f-a1b9-9896133536b8":{"endpoint_id":"8f22002c-c045-446f-a1b9-9896133536b8","request_count":10670,"window_minutes":30,"p50_throughput":20,"p75_throughput":28,"p90_throughput":34.900000000000546,"p99_throughput":46,"p50_latency":674,"p75_latency":1596,"p90_latency":2759.9000000000005,"p99_latency":5763.9000000000015},"1eb01ded-ae11-49e6-8aa6-3067584070bd":{"endpoint_id":"1eb01ded-ae11-49e6-8aa6-3067584070bd","request_count":970,"window_minutes":30,"p50_throughput":49,"p75_throughput":56,"p90_throughput":62,"p99_throughput":68.30999999999995,"p50_latency":427.5,"p75_latency":478.75,"p90_latency":716.6000000000001,"p99_latency":1854.7099999999978},"0d28660e-435a-4853-a2c6-9d916df28fc7":{"endpoint_id":"0d28660e-435a-4853-a2c6-9d916df28fc7","request_count":103,"window_minutes":30,"p50_throughput":9,"p75_throughput":18.5,"p90_throughput":45.599999999999994,"p99_throughput":91.4800000000001,"p50_latency":13883,"p75_latency":18630.5,"p90_latency":25147,"p99_latency":52341.98000000002},"e19b1036-fab9-4f97-9579-8ea67959cc9b":{"endpoint_id":"e19b1036-fab9-4f97-9579-8ea67959cc9b","request_count":1831,"window_minutes":30,"p50_throughput":56,"p75_throughput":78,"p90_throughput":101,"p99_throughput":139.70000000000005,"p50_latency":3223,"p75_latency":4216.5,"p90_latency":5175,"p99_latency":9548.400000000005},"c5a8bebe-8564-47ed-9d05-4151aa3c6e3a":{"endpoint_id":"c5a8bebe-8564-47ed-9d05-4151aa3c6e3a","request_count":55,"window_minutes":30,"p50_throughput":71,"p75_throughput":82.5,"p90_throughput":113.6,"p99_throughput":136.92000000000002,"p50_latency":483,"p75_latency":630.5,"p90_latency":793.6000000000001,"p99_latency":1426.2400000000007},"fd456f92-a506-4249-8527-988e9c1d84b3":{"endpoint_id":"fd456f92-a506-4249-8527-988e9c1d84b3","request_count":16,"window_minutes":30,"p50_throughput":15.5,"p75_throughput":29,"p90_throughput":36.5,"p99_throughput":37,"p50_latency":793.5,"p75_latency":1091.5,"p90_latency":1241.5,"p99_latency":1388.5500000000002},"c61ab1c0-3660-4391-8385-773c7a3d1de8":{"endpoint_id":"c61ab1c0-3660-4391-8385-773c7a3d1de8","request_count":6173,"window_minutes":30,"p50_throughput":1,"p75_throughput":1,"p90_throughput":5,"p99_throughput":21,"p50_latency":4008,"p75_latency":8210,"p90_latency":11260.8,"p99_latency":13886.239999999993},"47e88ae3-94ed-4d6a-96bb-a150dd354853":{"endpoint_id":"47e88ae3-94ed-4d6a-96bb-a150dd354853","request_count":821,"window_minutes":30,"p50_throughput":53,"p75_throughput":54,"p90_throughput":55,"p99_throughput":55,"p50_latency":490,"p75_latency":541,"p90_latency":670,"p99_latency":1079.599999999998},"e93c942e-7f8f-410d-8478-21ec37bc6b0d":{"endpoint_id":"e93c942e-7f8f-410d-8478-21ec37bc6b0d","request_count":46,"window_minutes":30,"p50_throughput":120,"p75_throughput":146.75,"p90_throughput":166.5,"p99_throughput":176.1,"p50_latency":2528.5,"p75_latency":3862,"p90_latency":5689.5,"p99_latency":11881.299999999996},"a911739a-dc2e-424d-a221-5c776f1552f0":{"endpoint_id":"a911739a-dc2e-424d-a221-5c776f1552f0","request_count":18027,"window_minutes":30,"p50_throughput":36,"p75_throughput":48,"p90_throughput":61,"p99_throughput":89,"p50_latency":372,"p75_latency":583,"p90_latency":853,"p99_latency":1939.7100000000028},"5f831e7a-c555-4d3a-b228-88286347558a":{"endpoint_id":"5f831e7a-c555-4d3a-b228-88286347558a","request_count":3655,"window_minutes":30,"p50_throughput":49,"p75_throughput":67,"p90_throughput":84,"p99_throughput":112,"p50_latency":3058,"p75_latency":3772,"p90_latency":5048.799999999999,"p99_latency":9673.54},"797ebc09-6e53-4795-9d9e-2669ce7aee03":{"endpoint_id":"797ebc09-6e53-4795-9d9e-2669ce7aee03","request_count":428,"window_minutes":30,"p50_throughput":20,"p75_throughput":22.25,"p90_throughput":24,"p99_throughput":27.730000000000018,"p50_latency":822,"p75_latency":1018.75,"p90_latency":1269.6000000000001,"p99_latency":15609.180000000015},"cca51d1b-db1d-44d2-bc90-268311214746":{"endpoint_id":"cca51d1b-db1d-44d2-bc90-268311214746","request_count":2917,"window_minutes":30,"p50_throughput":13,"p75_throughput":20,"p90_throughput":22,"p99_throughput":26,"p50_latency":994,"p75_latency":1268,"p90_latency":1711.2000000000003,"p99_latency":4736.200000000008},"352546d2-3758-4aa1-9e98-e1a83748aa4e":{"endpoint_id":"352546d2-3758-4aa1-9e98-e1a83748aa4e","request_count":255,"window_minutes":30,"p50_throughput":24,"p75_throughput":26,"p90_throughput":28.599999999999994,"p99_throughput":34.380000000000024,"p50_latency":998,"p75_latency":1260.5,"p90_latency":1795.8,"p99_latency":5900.120000000001},"8e48942d-17fc-4d00-a234-4723034fd971":{"endpoint_id":"8e48942d-17fc-4d00-a234-4723034fd971","request_count":21209,"window_minutes":30,"p50_throughput":13,"p75_throughput":18,"p90_throughput":59,"p99_throughput":74,"p50_latency":158,"p75_latency":202,"p90_latency":255,"p99_latency":899.4500000000007},"511ddb79-1d9e-4f5f-9863-c12b0f9b80ba":{"endpoint_id":"511ddb79-1d9e-4f5f-9863-c12b0f9b80ba","request_count":9750,"window_minutes":30,"p50_throughput":33,"p75_throughput":40,"p90_throughput":46,"p99_throughput":59,"p50_latency":1588,"p75_latency":2014.25,"p90_latency":2609,"p99_latency":4989.360000000001},"fde3788e-a185-4487-93a7-10fb4412d412":{"endpoint_id":"fde3788e-a185-4487-93a7-10fb4412d412","request_count":190,"window_minutes":30,"p50_throughput":5,"p75_throughput":12.75,"p90_throughput":18,"p99_throughput":23,"p50_latency":6678.5,"p75_latency":22638,"p90_latency":34464.49999999999,"p99_latency":187568.00999999876},"82738f61-f3cb-44a5-b5d1-e6787ae64e3b":{"endpoint_id":"82738f61-f3cb-44a5-b5d1-e6787ae64e3b","request_count":17,"window_minutes":30,"p50_throughput":70,"p75_throughput":102,"p90_throughput":123,"p99_throughput":130.56,"p50_latency":2125,"p75_latency":3749,"p90_latency":5209.6,"p99_latency":6027.16},"d4a57205-8124-413a-ab4e-5ae94eb7aa9d":{"endpoint_id":"d4a57205-8124-413a-ab4e-5ae94eb7aa9d","request_count":90,"window_minutes":30,"p50_throughput":65,"p75_throughput":75,"p90_throughput":83.10000000000001,"p99_throughput":117.42999999999999,"p50_latency":231,"p75_latency":285.75,"p90_latency":528.1000000000025,"p99_latency":980.4399999999999},"e3b0a527-44d6-4ea6-9ec2-6a6416a84c7c":{"endpoint_id":"e3b0a527-44d6-4ea6-9ec2-6a6416a84c7c","request_count":19072,"window_minutes":30,"p50_throughput":15,"p75_throughput":20,"p90_throughput":24,"p99_throughput":31,"p50_latency":375,"p75_latency":730,"p90_latency":2158,"p99_latency":7003.890000000003},"72eda073-d180-4482-8e4f-81051cb66f7e":{"endpoint_id":"72eda073-d180-4482-8e4f-81051cb66f7e","request_count":408,"window_minutes":30,"p50_throughput":87,"p75_throughput":110.25,"p90_throughput":143.3,"p99_throughput":197.58000000000004,"p50_latency":647.5,"p75_latency":1027.5,"p90_latency":1270.3,"p99_latency":2569.3800000000015},"474f0074-66f9-42f0-a866-81a2ffebb001":{"endpoint_id":"474f0074-66f9-42f0-a866-81a2ffebb001","request_count":69853,"window_minutes":30,"p50_throughput":64,"p75_throughput":122,"p90_throughput":172,"p99_throughput":265,"p50_latency":1799.5,"p75_latency":3393.75,"p90_latency":5028.900000000001,"p99_latency":9142.720000000001},"959381a4-8054-450f-9daf-5fcab64ba9aa":{"endpoint_id":"959381a4-8054-450f-9daf-5fcab64ba9aa","request_count":13,"window_minutes":30,"p50_throughput":38,"p75_throughput":116,"p90_throughput":138.60000000000002,"p99_throughput":171.03999999999996,"p50_latency":423,"p75_latency":463,"p90_latency":682.6000000000001,"p99_latency":754.4},"3e86b7c5-bffe-4b60-a3dd-b36451978775":{"endpoint_id":"3e86b7c5-bffe-4b60-a3dd-b36451978775","request_count":1257,"window_minutes":30,"p50_throughput":37,"p75_throughput":73,"p90_throughput":100,"p99_throughput":147.44000000000005,"p50_latency":655,"p75_latency":1064,"p90_latency":1630.8000000000002,"p99_latency":4114.280000000001},"4a128170-b056-42d7-8462-a5cea647f9ad":{"endpoint_id":"4a128170-b056-42d7-8462-a5cea647f9ad","request_count":15,"window_minutes":30,"p50_throughput":7,"p75_throughput":29.5,"p90_throughput":38,"p99_throughput":44.019999999999996,"p50_latency":546,"p75_latency":662,"p90_latency":1522.3999999999999,"p99_latency":4936.699999999998},"3ad816a5-5e65-4f9a-8d4b-da3c1ddb20fe":{"endpoint_id":"3ad816a5-5e65-4f9a-8d4b-da3c1ddb20fe","request_count":181,"window_minutes":30,"p50_throughput":30,"p75_throughput":31,"p90_throughput":32,"p99_throughput":33,"p50_latency":484,"p75_latency":580,"p90_latency":721,"p99_latency":1030.7999999999988},"08cb2fef-fad6-4a41-b292-b2d79f782a08":{"endpoint_id":"08cb2fef-fad6-4a41-b292-b2d79f782a08","request_count":183,"window_minutes":30,"p50_throughput":70,"p75_throughput":83,"p90_throughput":91,"p99_throughput":104.18,"p50_latency":762,"p75_latency":1199.5,"p90_latency":2181.2000000000003,"p99_latency":9658.660000000007},"7f8d0c76-0eab-4606-9f4c-d0b4414e2cf1":{"endpoint_id":"7f8d0c76-0eab-4606-9f4c-d0b4414e2cf1","request_count":68,"window_minutes":30,"p50_throughput":16,"p75_throughput":17,"p90_throughput":18,"p99_throughput":18,"p50_latency":934,"p75_latency":1489.5,"p90_latency":2240.900000000001,"p99_latency":3226.5899999999997},"3a6186c9-0ece-4797-9f97-45d7fab8c546":{"endpoint_id":"3a6186c9-0ece-4797-9f97-45d7fab8c546","request_count":21662,"window_minutes":30,"p50_throughput":38,"p75_throughput":50,"p90_throughput":60,"p99_throughput":83,"p50_latency":318,"p75_latency":360.25,"p90_latency":447,"p99_latency":1113.170000000002},"6a1461d2-2074-404f-8202-bd5d52971983":{"endpoint_id":"6a1461d2-2074-404f-8202-bd5d52971983","request_count":697,"window_minutes":30,"p50_throughput":96,"p75_throughput":160,"p90_throughput":180,"p99_throughput":207,"p50_latency":245,"p75_latency":286,"p90_latency":329,"p99_latency":844.3199999999997},"87c79cad-7b66-421b-82a0-b6026faef55f":{"endpoint_id":"87c79cad-7b66-421b-82a0-b6026faef55f","request_count":1344,"window_minutes":30,"p50_throughput":126,"p75_throughput":148,"p90_throughput":169,"p99_throughput":305.56999999999994,"p50_latency":299,"p75_latency":320,"p90_latency":446.10000000000014,"p99_latency":1172.549999999999},"8b6b26e9-621a-4b31-b55a-c9aaa7482ede":{"endpoint_id":"8b6b26e9-621a-4b31-b55a-c9aaa7482ede","request_count":1498,"window_minutes":30,"p50_throughput":29,"p75_throughput":35,"p90_throughput":38,"p99_throughput":42,"p50_latency":406.5,"p75_latency":831.75,"p90_latency":2753.5999999999995,"p99_latency":37935.22999999996},"3d8c4986-1fc9-4ce1-b07d-d379bb75eb36":{"endpoint_id":"3d8c4986-1fc9-4ce1-b07d-d379bb75eb36","request_count":125,"window_minutes":30,"p50_throughput":22,"p75_throughput":37,"p90_throughput":53.60000000000001,"p99_throughput":60.280000000000015,"p50_latency":302,"p75_latency":543,"p90_latency":1146.0000000000007,"p99_latency":22720.640000000003},"cd63714a-d459-4806-bdf2-0dfea4f6614c":{"endpoint_id":"cd63714a-d459-4806-bdf2-0dfea4f6614c","request_count":9,"window_minutes":30,"p50_throughput":6,"p75_throughput":9,"p90_throughput":15.6,"p99_throughput":17.759999999999998,"p50_latency":536,"p75_latency":704,"p90_latency":735.2,"p99_latency":815.12},"7ab4ba43-98eb-4842-9046-f7f1822ab3a2":{"endpoint_id":"7ab4ba43-98eb-4842-9046-f7f1822ab3a2","request_count":146,"window_minutes":30,"p50_throughput":41.5,"p75_throughput":46,"p90_throughput":50,"p99_throughput":58.650000000000034,"p50_latency":293.5,"p75_latency":398.75,"p90_latency":821.5,"p99_latency":1986.200000000013},"2151651b-f4e9-4db7-b20d-8b91fb524bf8":{"endpoint_id":"2151651b-f4e9-4db7-b20d-8b91fb524bf8","request_count":979,"window_minutes":30,"p50_throughput":23,"p75_throughput":29,"p90_throughput":32,"p99_throughput":36,"p50_latency":768,"p75_latency":1237,"p90_latency":1866.0000000000011,"p99_latency":3380.4400000000014},"3280e8f8-0960-400c-8284-2e03a0bcb446":{"endpoint_id":"3280e8f8-0960-400c-8284-2e03a0bcb446","request_count":861,"window_minutes":30,"p50_throughput":19,"p75_throughput":23,"p90_throughput":26,"p99_throughput":30,"p50_latency":346,"p75_latency":834,"p90_latency":1858,"p99_latency":7763.5999999999985},"802c16d5-fb79-4761-93e1-b40d07fc7a1b":{"endpoint_id":"802c16d5-fb79-4761-93e1-b40d07fc7a1b","request_count":1840,"window_minutes":30,"p50_throughput":34,"p75_throughput":41,"p90_throughput":46,"p99_throughput":52,"p50_latency":564.5,"p75_latency":739,"p90_latency":937.1000000000001,"p99_latency":1854.61},"59ea8d2a-1b1b-47f1-83de-a358a724caeb":{"endpoint_id":"59ea8d2a-1b1b-47f1-83de-a358a724caeb","request_count":447,"window_minutes":30,"p50_throughput":4,"p75_throughput":5,"p90_throughput":74,"p99_throughput":194.02000000000027,"p50_latency":634,"p75_latency":772,"p90_latency":1043,"p99_latency":5263.660000000014},"036dfa0a-ebbb-4a51-aa90-091a75c2cadb":{"endpoint_id":"036dfa0a-ebbb-4a51-aa90-091a75c2cadb","request_count":8627,"window_minutes":30,"p50_throughput":9,"p75_throughput":14,"p90_throughput":20,"p99_throughput":30,"p50_latency":521,"p75_latency":920.25,"p90_latency":1897,"p99_latency":4790.880000000005},"d7de0517-e8de-4f1b-b4bc-c5ebd29a0315":{"endpoint_id":"d7de0517-e8de-4f1b-b4bc-c5ebd29a0315","request_count":52203,"window_minutes":30,"p50_throughput":32,"p75_throughput":38,"p90_throughput":43,"p99_throughput":56,"p50_latency":412,"p75_latency":527,"p90_latency":738.9000000000005,"p99_latency":4122.09},"3e0aa374-de51-4cd0-911b-29ae65067e21":{"endpoint_id":"3e0aa374-de51-4cd0-911b-29ae65067e21","request_count":288955,"window_minutes":30,"p50_throughput":23,"p75_throughput":27,"p90_throughput":32,"p99_throughput":46,"p50_latency":504,"p75_latency":1149.25,"p90_latency":2055.9000000000005,"p99_latency":3957.9900000000016},"ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15":{"endpoint_id":"ebcc1f0a-6621-4cdc-a93f-88a6e2cc2e15","request_count":14370,"window_minutes":30,"p50_throughput":51,"p75_throughput":70,"p90_throughput":81,"p99_throughput":101,"p50_latency":577,"p75_latency":654,"p90_latency":773.9000000000005,"p99_latency":2093.5100000000057},"685e6cfb-ecef-4c83-8e2d-aa1ba667d744":{"endpoint_id":"685e6cfb-ecef-4c83-8e2d-aa1ba667d744","request_count":171993,"window_minutes":30,"p50_throughput":27,"p75_throughput":41,"p90_throughput":55,"p99_throughput":74.09000000000015,"p50_latency":1542,"p75_latency":1827.25,"p90_latency":2168.9000000000005,"p99_latency":3702.9900000000016},"03a23b91-c1f2-4a5e-891b-df7e13c87472":{"endpoint_id":"03a23b91-c1f2-4a5e-891b-df7e13c87472","request_count":939,"window_minutes":30,"p50_throughput":40,"p75_throughput":43,"p90_throughput":44,"p99_throughput":55,"p50_latency":593,"p75_latency":771,"p90_latency":997,"p99_latency":1308.62},"452a72a0-2c24-4e31-98cb-d6cc1084fb99":{"endpoint_id":"452a72a0-2c24-4e31-98cb-d6cc1084fb99","request_count":10350,"window_minutes":30,"p50_throughput":47,"p75_throughput":69,"p90_throughput":87,"p99_throughput":120,"p50_latency":639,"p75_latency":838.25,"p90_latency":1404,"p99_latency":4747.27},"3d6584e7-a2bb-48d6-903d-24e3d90e7e55":{"endpoint_id":"3d6584e7-a2bb-48d6-903d-24e3d90e7e55","request_count":17,"window_minutes":30,"p50_throughput":57,"p75_throughput":89,"p90_throughput":104,"p99_throughput":141.56,"p50_latency":912,"p75_latency":1025,"p90_latency":1707.2000000000003,"p99_latency":3689.96},"e55a0c16-08a0-4871-ae6a-97482cc3231a":{"endpoint_id":"e55a0c16-08a0-4871-ae6a-97482cc3231a","request_count":82,"window_minutes":30,"p50_throughput":85,"p75_throughput":116.75,"p90_throughput":134.9,"p99_throughput":164.38,"p50_latency":536,"p75_latency":669,"p90_latency":1015.9000000000002,"p99_latency":2227.21},"92d0658f-b48a-4746-96e7-75ea71d5e060":{"endpoint_id":"92d0658f-b48a-4746-96e7-75ea71d5e060","request_count":172,"window_minutes":30,"p50_throughput":0,"p75_throughput":2,"p90_throughput":3,"p99_throughput":4,"p50_latency":91042.5,"p75_latency":181631.25,"p90_latency":244895.50000000003,"p99_latency":282401.95999999996},"da16824f-3ba0-43a1-86f8-a6131837f457":{"endpoint_id":"da16824f-3ba0-43a1-86f8-a6131837f457","request_count":104,"window_minutes":30,"p50_throughput":26,"p75_throughput":30,"p90_throughput":39,"p99_throughput":46,"p50_latency":1023,"p75_latency":1166.5,"p90_latency":1367.1,"p99_latency":2427.3399999999997},"401c6f0f-caeb-4c84-92b7-e163dbccf7c2":{"endpoint_id":"401c6f0f-caeb-4c84-92b7-e163dbccf7c2","request_count":2303,"window_minutes":30,"p50_throughput":54,"p75_throughput":74,"p90_throughput":93.80000000000018,"p99_throughput":134.98000000000002,"p50_latency":487,"p75_latency":799.5,"p90_latency":1191,"p99_latency":3435.3000000000006},"f1a57233-f872-4fa0-ad37-66c9a6b00469":{"endpoint_id":"f1a57233-f872-4fa0-ad37-66c9a6b00469","request_count":225,"window_minutes":30,"p50_throughput":43,"p75_throughput":51,"p90_throughput":57.599999999999994,"p99_throughput":73.75999999999999,"p50_latency":629,"p75_latency":1036,"p90_latency":2997.199999999998,"p99_latency":11330.919999999998},"f29e5bba-56f3-408a-a036-185e3dc20be3":{"endpoint_id":"f29e5bba-56f3-408a-a036-185e3dc20be3","request_count":37,"window_minutes":30,"p50_throughput":30,"p75_throughput":68,"p90_throughput":76.19999999999999,"p99_throughput":86.48,"p50_latency":1005,"p75_latency":1382,"p90_latency":1825.3999999999999,"p99_latency":3801.3600000000006},"39594b4d-6c7e-4ccd-aeed-79f9b3ca5819":{"endpoint_id":"39594b4d-6c7e-4ccd-aeed-79f9b3ca5819","request_count":35,"window_minutes":30,"p50_throughput":39,"p75_throughput":82.5,"p90_throughput":101.80000000000001,"p99_throughput":112.57999999999996,"p50_latency":1634,"p75_latency":1746.5,"p90_latency":1915.6000000000001,"p99_latency":5155.719999999985},"8c793d52-3eea-429a-8524-bf4899ce050a":{"endpoint_id":"8c793d52-3eea-429a-8524-bf4899ce050a","request_count":65,"window_minutes":30,"p50_throughput":42,"p75_throughput":59,"p90_throughput":77.6,"p99_throughput":86.36,"p50_latency":1138,"p75_latency":1661,"p90_latency":2526.6,"p99_latency":6749.08},"c8fb1a1b-9f2c-4dc6-b2be-43b25f999502":{"endpoint_id":"c8fb1a1b-9f2c-4dc6-b2be-43b25f999502","request_count":8,"window_minutes":30,"p50_throughput":11,"p75_throughput":23,"p90_throughput":60.8,"p99_throughput":77.17999999999998,"p50_latency":645.5,"p75_latency":708,"p90_latency":757.1999999999999,"p99_latency":835.3199999999999},"061b3f45-8511-4ad9-8537-a5ac7aeeb163":{"endpoint_id":"061b3f45-8511-4ad9-8537-a5ac7aeeb163","request_count":111,"window_minutes":30,"p50_throughput":19,"p75_throughput":22,"p90_throughput":23,"p99_throughput":25,"p50_latency":1220,"p75_latency":1584,"p90_latency":1892,"p99_latency":5557.2000000000035},"3a9bbd50-68e9-4ebf-92e4-faa0395a1229":{"endpoint_id":"3a9bbd50-68e9-4ebf-92e4-faa0395a1229","request_count":687,"window_minutes":30,"p50_throughput":42,"p75_throughput":52,"p90_throughput":62,"p99_throughput":71.13999999999999,"p50_latency":715,"p75_latency":1003,"p90_latency":1357.9999999999998,"p99_latency":1942.54},"3a632f37-731d-4200-9e38-413a5f5dd39d":{"endpoint_id":"3a632f37-731d-4200-9e38-413a5f5dd39d","request_count":1874,"window_minutes":30,"p50_throughput":77,"p75_throughput":88,"p90_throughput":95,"p99_throughput":139.53999999999996,"p50_latency":530,"p75_latency":814.75,"p90_latency":920.7,"p99_latency":1945.5599999999995},"355b1df4-06c8-4c36-a091-3d50477095fb":{"endpoint_id":"355b1df4-06c8-4c36-a091-3d50477095fb","request_count":27,"window_minutes":30,"p50_throughput":33,"p75_throughput":41,"p90_throughput":52,"p99_throughput":53.48,"p50_latency":713,"p75_latency":933.5,"p90_latency":1239.6000000000004,"p99_latency":1594.04}},"benchmark_ranges":{"tool_success_rate":{"min":0.27800361336946705,"max":1},"intelligence_index":{"min":5.5,"max":63.1},"coding_index":{"min":2.7,"max":78},"agentic_index":{"min":0.3,"max":59.2},"da_elo":{"models-3d":{"min":882,"max":1445},"models-codecategories":{"min":814,"max":1407},"models-dataviz":{"min":529,"max":1375},"models-gamedev":{"min":809,"max":1431},"models-uicomponent":{"min":795,"max":1377},"models-website":{"min":770,"max":1372},"models-asciiart":{"min":1006,"max":1367},"models-svg":{"min":928,"max":1364},"models-imageediting":{"min":1077,"max":1380},"models-graphicdesign":{"min":1028,"max":1466},"models-image":{"min":1082,"max":1404},"models-logo":{"min":1070,"max":1305},"models-audiorealism":{"min":1223,"max":1223},"models-text-to-speech":{"min":1195,"max":1195}}}}}