{"data":[{"id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek: DeepSeek V4 Flash","created":1777000666,"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...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.000000028"},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1246,"win_rate":49.4,"rank":35},{"arena":"models","category":"asciiart","elo":1153,"win_rate":43.1,"rank":44},{"arena":"models","category":"codecategories","elo":1236,"win_rate":49.2,"rank":37},{"arena":"models","category":"dataviz","elo":1154,"win_rate":40.6,"rank":67},{"arena":"models","category":"gamedev","elo":1253,"win_rate":50.3,"rank":32},{"arena":"models","category":"svg","elo":1204,"win_rate":48.5,"rank":26},{"arena":"models","category":"uicomponent","elo":1200,"win_rate":44.9,"rank":50},{"arena":"models","category":"website","elo":1233,"win_rate":49.5,"rank":38}],"artificial_analysis":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek: DeepSeek V4 Pro","created":1777000679,"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,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000435","completion":"0.00000087","input_cache_read":"0.000000003625"},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":948,"win_rate":22.1,"rank":33},{"arena":"agents","category":"godotgamedev","elo":1059,"win_rate":34,"rank":27},{"arena":"agents","category":"webapps","elo":999,"win_rate":26.4,"rank":34},{"arena":"models","category":"3d","elo":1318,"win_rate":59.6,"rank":10},{"arena":"models","category":"asciiart","elo":1188,"win_rate":46.6,"rank":25},{"arena":"models","category":"codecategories","elo":1274,"win_rate":54.2,"rank":25},{"arena":"models","category":"dataviz","elo":1226,"win_rate":49.5,"rank":39},{"arena":"models","category":"gamedev","elo":1291,"win_rate":55.7,"rank":21},{"arena":"models","category":"svg","elo":1185,"win_rate":46.5,"rank":36},{"arena":"models","category":"uicomponent","elo":1261,"win_rate":52,"rank":31},{"arena":"models","category":"website","elo":1260,"win_rate":52.5,"rank":30}],"artificial_analysis":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"tencent/hy3","canonical_slug":"tencent/hy3-20260706","hugging_face_id":"tencent/Hy3","name":"Tencent: Hy3","created":1783344048,"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:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033"},"top_provider":{"context_length":262144,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy3-20260706/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1232,"win_rate":43.6,"rank":37},{"arena":"models","category":"codecategories","elo":1206,"win_rate":41.2,"rank":46},{"arena":"models","category":"dataviz","elo":1153,"win_rate":36.1,"rank":69},{"arena":"models","category":"gamedev","elo":1190,"win_rate":38.6,"rank":56},{"arena":"models","category":"uicomponent","elo":1197,"win_rate":40.2,"rank":52},{"arena":"models","category":"website","elo":1207,"win_rate":41.5,"rank":52}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"google/gemini-2.5-flash","canonical_slug":"google/gemini-2.5-flash","hugging_face_id":"","name":"Google: Gemini 2.5 Flash","created":1750172488,"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...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1128,"win_rate":47.4,"rank":75},{"arena":"models","category":"codecategories","elo":1135,"win_rate":46.9,"rank":79},{"arena":"models","category":"dataviz","elo":1156,"win_rate":48.4,"rank":66},{"arena":"models","category":"gamedev","elo":1122,"win_rate":44.3,"rank":79},{"arena":"models","category":"uicomponent","elo":1129,"win_rate":48.9,"rank":72},{"arena":"models","category":"website","elo":1140,"win_rate":47.1,"rank":78},{"arena":"models","category":"svg","elo":1070,"win_rate":43.1,"rank":61}]},"reasoning":{"mandatory":false}},{"id":"openai/gpt-oss-120b","canonical_slug":"openai/gpt-oss-120b","hugging_face_id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"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...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000000037","completion":"0.00000017"},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-120b/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":958,"win_rate":29.4,"rank":98},{"arena":"models","category":"codecategories","elo":994,"win_rate":33.4,"rank":104},{"arena":"models","category":"dataviz","elo":1029,"win_rate":45.1,"rank":94},{"arena":"models","category":"gamedev","elo":1049,"win_rate":40.6,"rank":92},{"arena":"models","category":"uicomponent","elo":961,"win_rate":35.5,"rank":99},{"arena":"models","category":"website","elo":993,"win_rate":32.5,"rank":107}],"artificial_analysis":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"google/gemini-2.5-flash-lite","canonical_slug":"google/gemini-2.5-flash-lite","hugging_face_id":"","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"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...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.00000008333333333333334"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-2.5-flash-lite/endpoints"},"reasoning":{"mandatory":false}},{"id":"google/gemini-3-flash-preview","canonical_slug":"google/gemini-3-flash-preview-20251217","hugging_face_id":"","name":"Google: Gemini 3 Flash Preview","created":1765987078,"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...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005","audio":"0.000001","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.000003","input_cache_read":"0.00000005","input_cache_write":"0.00000008333333333333334"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticslides","elo":1073,"win_rate":39.3,"rank":9},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1075,"win_rate":39.3,"rank":9},{"arena":"agents","category":"androidnative","elo":1034,"win_rate":48.1,"rank":29},{"arena":"agents","category":"fullstack","elo":1104,"win_rate":47.1,"rank":21},{"arena":"agents","category":"godotgamedev","elo":1161,"win_rate":50.6,"rank":15},{"arena":"agents","category":"mobileapps","elo":1173,"win_rate":49.1,"rank":22},{"arena":"agents","category":"python-pptxslides","elo":1014,"win_rate":38.3,"rank":18},{"arena":"agents","category":"webapps","elo":1167,"win_rate":49.3,"rank":24},{"arena":"models","category":"3d","elo":1241,"win_rate":62.7,"rank":36},{"arena":"models","category":"codecategories","elo":1220,"win_rate":57.6,"rank":40},{"arena":"models","category":"gamedev","elo":1222,"win_rate":58.3,"rank":43},{"arena":"models","category":"website","elo":1221,"win_rate":57,"rank":40}]},"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"google/gemma-4-31b-it","canonical_slug":"google/gemma-4-31b-it-20260402","hugging_face_id":"google/gemma-4-31B-it","name":"Google: Gemma 4 31B","created":1775148486,"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...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.0000004"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4}},"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"anthropic/claude-opus-4.8","canonical_slug":"anthropic/claude-4.8-opus-20260528","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.8","created":1779905091,"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_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1259,"win_rate":61.2,"rank":2},{"arena":"agents","category":"agentichtmlslides","elo":1227,"win_rate":55.6,"rank":4},{"arena":"agents","category":"agenticslides","elo":1294,"win_rate":64.8,"rank":2},{"arena":"agents","category":"agenticslides(html)","elo":1230,"win_rate":56,"rank":4},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":2},{"arena":"agents","category":"androidnative","elo":1340,"win_rate":68,"rank":1},{"arena":"agents","category":"fullstack","elo":1290,"win_rate":62.8,"rank":3},{"arena":"agents","category":"godotgamedev","elo":1253,"win_rate":58.5,"rank":5},{"arena":"agents","category":"htmlslides","elo":1237,"win_rate":57.1,"rank":3},{"arena":"agents","category":"mobileapps","elo":1270,"win_rate":58.1,"rank":2},{"arena":"agents","category":"pptxslides","elo":1306,"win_rate":67.9,"rank":2},{"arena":"agents","category":"python-pptxslides","elo":1298,"win_rate":65.9,"rank":4},{"arena":"agents","category":"webapps","elo":1270,"win_rate":53.2,"rank":6},{"arena":"models","category":"3d","elo":1278,"win_rate":53.4,"rank":24},{"arena":"models","category":"asciiart","elo":1303,"win_rate":62.8,"rank":4},{"arena":"models","category":"codecategories","elo":1270,"win_rate":53.6,"rank":28},{"arena":"models","category":"dataviz","elo":1264,"win_rate":54.4,"rank":25},{"arena":"models","category":"gamedev","elo":1299,"win_rate":54.8,"rank":17},{"arena":"models","category":"svg","elo":1227,"win_rate":53.3,"rank":18},{"arena":"models","category":"uicomponent","elo":1276,"win_rate":54.1,"rank":24},{"arena":"models","category":"website","elo":1269,"win_rate":54.1,"rank":28}],"artificial_analysis":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"amazon/nova-micro-v1","canonical_slug":"amazon/nova-micro-v1","hugging_face_id":"","name":"Amazon: Nova Micro 1.0","created":1733437237,"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...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.000000035","completion":"0.00000014"},"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-10-31","expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-micro-v1/endpoints"}},{"id":"z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2-20260616","hugging_face_id":"zai-org/GLM-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"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,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000728","completion":"0.000002288","input_cache_read":"0.0000001352"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.2-20260616/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1184,"win_rate":48,"rank":12},{"arena":"agents","category":"androidnative","elo":1231,"win_rate":54.8,"rank":9},{"arena":"agents","category":"fullstack","elo":1273,"win_rate":63.9,"rank":5},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":18},{"arena":"agents","category":"htmlslides","elo":1206,"win_rate":51.7,"rank":9},{"arena":"agents","category":"mobileapps","elo":1233,"win_rate":54.3,"rank":9},{"arena":"agents","category":"python-pptxslides","elo":1186,"win_rate":48,"rank":10},{"arena":"agents","category":"webapps","elo":1269,"win_rate":57,"rank":7},{"arena":"models","category":"3d","elo":1367,"win_rate":59.9,"rank":4},{"arena":"models","category":"asciiart","elo":1225,"win_rate":48.6,"rank":16},{"arena":"models","category":"codecategories","elo":1346,"win_rate":60.7,"rank":3},{"arena":"models","category":"dataviz","elo":1304,"win_rate":57.4,"rank":10},{"arena":"models","category":"gamedev","elo":1358,"win_rate":62,"rank":2},{"arena":"models","category":"svg","elo":1260,"win_rate":55.5,"rank":9},{"arena":"models","category":"uicomponent","elo":1332,"win_rate":59.7,"rank":5},{"arena":"models","category":"website","elo":1340,"win_rate":60.8,"rank":3}],"artificial_analysis":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"openai/gpt-4o-mini","canonical_slug":"openai/gpt-4o-mini","hugging_face_id":null,"name":"OpenAI: GPT-4o-mini","created":1721260800,"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. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":11.4,"agentic_index":1}}},{"id":"google/gemini-3.1-flash-lite","canonical_slug":"google/gemini-3.1-flash-lite-20260507","hugging_face_id":null,"name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"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...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","audio":"0.0000005","input_audio_cache":"0.00000005","web_search":"0.014","internal_reasoning":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.00000008333333333333334"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"}},{"id":"anthropic/claude-sonnet-4.6","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"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...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.01","input_cache_read":"0.0000003","input_cache_write":"0.00000375","input_cache_write_1h":"0.000006"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1203,"win_rate":53.8,"rank":7},{"arena":"agents","category":"androidnative","elo":1202,"win_rate":61.4,"rank":14},{"arena":"agents","category":"fullstack","elo":1251,"win_rate":63.9,"rank":8},{"arena":"agents","category":"godotgamedev","elo":1226,"win_rate":60.6,"rank":8},{"arena":"agents","category":"mobileapps","elo":1266,"win_rate":61.9,"rank":3},{"arena":"agents","category":"webapps","elo":1240,"win_rate":56.8,"rank":15},{"arena":"models","category":"3d","elo":1292,"win_rate":57.8,"rank":20},{"arena":"models","category":"asciiart","elo":1266,"win_rate":59.6,"rank":9},{"arena":"models","category":"codecategories","elo":1307,"win_rate":60.1,"rank":13},{"arena":"models","category":"dataviz","elo":1308,"win_rate":60.5,"rank":9},{"arena":"models","category":"gamedev","elo":1314,"win_rate":59,"rank":13},{"arena":"models","category":"svg","elo":1247,"win_rate":59,"rank":12},{"arena":"models","category":"uicomponent","elo":1309,"win_rate":60.5,"rank":11},{"arena":"models","category":"website","elo":1310,"win_rate":60.7,"rank":9}],"artificial_analysis":{"intelligence_index":47.2,"coding_index":63,"agentic_index":40.8}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low"],"default_effort":"medium"}},{"id":"google/gemma-4-26b-a4b-it","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","hugging_face_id":"google/gemma-4-26B-A4B-it","name":"Google: Gemma 4 26B A4B ","created":1775227989,"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...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000034"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11}},"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"openai/gpt-5.6-terra","canonical_slug":"openai/gpt-5.6-terra-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Terra","created":1783590857,"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...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.0000075","web_search":"0.005","input_cache_read":"0.000000125","input_cache_write":"0.0000015625","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000025","completion":"0.00001125","input_cache_read":"0.00000025","input_cache_write":"0.000003125"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":55,"coding_index":76.7,"agentic_index":47.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"anthropic/claude-sonnet-5","canonical_slug":"anthropic/claude-sonnet-5-20260630","hugging_face_id":null,"name":"Anthropic: Claude Sonnet 5","created":1782843083,"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,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1236,"win_rate":55.4,"rank":4},{"arena":"agents","category":"androidnative","elo":1238,"win_rate":53.9,"rank":8},{"arena":"agents","category":"fullstack","elo":1270,"win_rate":59.3,"rank":6},{"arena":"agents","category":"godotgamedev","elo":1268,"win_rate":59.8,"rank":4},{"arena":"agents","category":"htmlslides","elo":1231,"win_rate":54.1,"rank":4},{"arena":"agents","category":"mobileapps","elo":1230,"win_rate":52.6,"rank":10},{"arena":"agents","category":"python-pptxslides","elo":1246,"win_rate":55.1,"rank":7},{"arena":"agents","category":"webapps","elo":1303,"win_rate":58.4,"rank":4},{"arena":"models","category":"3d","elo":1313,"win_rate":57.2,"rank":12},{"arena":"models","category":"asciiart","elo":1238,"win_rate":52.5,"rank":12},{"arena":"models","category":"codecategories","elo":1304,"win_rate":55.9,"rank":14},{"arena":"models","category":"dataviz","elo":1268,"win_rate":53.1,"rank":22},{"arena":"models","category":"gamedev","elo":1351,"win_rate":59.5,"rank":3},{"arena":"models","category":"svg","elo":1241,"win_rate":53.7,"rank":14},{"arena":"models","category":"uicomponent","elo":1308,"win_rate":56.1,"rank":13},{"arena":"models","category":"website","elo":1301,"win_rate":56,"rank":12}],"artificial_analysis":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"minimax/minimax-m3","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3","created":1780245374,"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,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":524288,"max_completion_tokens":512000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1201,"win_rate":52.8,"rank":8},{"arena":"agents","category":"androidnative","elo":1119,"win_rate":36.3,"rank":20},{"arena":"agents","category":"fullstack","elo":1250,"win_rate":53,"rank":9},{"arena":"agents","category":"htmlslides","elo":1201,"win_rate":50.8,"rank":12},{"arena":"agents","category":"mobileapps","elo":1254,"win_rate":56.9,"rank":5},{"arena":"agents","category":"webapps","elo":1246,"win_rate":51.6,"rank":14},{"arena":"models","category":"3d","elo":1278,"win_rate":54.3,"rank":25},{"arena":"models","category":"asciiart","elo":1194,"win_rate":47.3,"rank":22},{"arena":"models","category":"codecategories","elo":1285,"win_rate":54.4,"rank":22},{"arena":"models","category":"dataviz","elo":1267,"win_rate":53.7,"rank":24},{"arena":"models","category":"gamedev","elo":1274,"win_rate":50.5,"rank":26},{"arena":"models","category":"svg","elo":1223,"win_rate":50.3,"rank":21},{"arena":"models","category":"uicomponent","elo":1282,"win_rate":53.7,"rank":23},{"arena":"models","category":"website","elo":1285,"win_rate":54.6,"rank":20}],"artificial_analysis":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4}},"reasoning":{"mandatory":false}},{"id":"google/gemini-3.5-flash","canonical_slug":"google/gemini-3.5-flash-20260519","hugging_face_id":null,"name":"Google: Gemini 3.5 Flash","created":1779193800,"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...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","audio":"0.000003","input_audio_cache":"0.0000003","web_search":"0.014","internal_reasoning":"0.000009","input_cache_read":"0.00000015","input_cache_write":"0.00000008333333333333334"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-01-01","expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1187,"win_rate":54,"rank":10},{"arena":"agents","category":"agentichtmlslides","elo":1162,"win_rate":45.8,"rank":7},{"arena":"agents","category":"agenticslides","elo":1244,"win_rate":57.5,"rank":4},{"arena":"agents","category":"agenticslides(html)","elo":1162,"win_rate":45.7,"rank":7},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1242,"win_rate":57.8,"rank":3},{"arena":"agents","category":"androidnative","elo":1210,"win_rate":51.5,"rank":13},{"arena":"agents","category":"fullstack","elo":1235,"win_rate":56.9,"rank":10},{"arena":"agents","category":"godotgamedev","elo":1136,"win_rate":42.6,"rank":21},{"arena":"agents","category":"htmlslides","elo":1172,"win_rate":46.6,"rank":15},{"arena":"agents","category":"mobileapps","elo":1239,"win_rate":54.9,"rank":8},{"arena":"agents","category":"pptxslides","elo":1244,"win_rate":57.7,"rank":3},{"arena":"agents","category":"python-pptxslides","elo":1247,"win_rate":57.4,"rank":6},{"arena":"agents","category":"webapps","elo":1248,"win_rate":53.4,"rank":13},{"arena":"models","category":"3d","elo":1294,"win_rate":57.5,"rank":19},{"arena":"models","category":"asciiart","elo":1295,"win_rate":60.3,"rank":6},{"arena":"models","category":"codecategories","elo":1289,"win_rate":56.6,"rank":19},{"arena":"models","category":"dataviz","elo":1260,"win_rate":54.6,"rank":28},{"arena":"models","category":"gamedev","elo":1318,"win_rate":57.6,"rank":12},{"arena":"models","category":"svg","elo":1297,"win_rate":62.2,"rank":3},{"arena":"models","category":"uicomponent","elo":1303,"win_rate":58.1,"rank":15},{"arena":"models","category":"website","elo":1283,"win_rate":55.8,"rank":21}],"artificial_analysis":{"intelligence_index":50.2,"coding_index":70.1,"agentic_index":37.4}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"anthropic/claude-haiku-4.5","canonical_slug":"anthropic/claude-4.5-haiku-20251001","hugging_face_id":"","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"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...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.00000125","input_cache_write_1h":"0.000002"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1129,"win_rate":41.1,"rank":74},{"arena":"models","category":"asciiart","elo":1177,"win_rate":49.3,"rank":36},{"arena":"models","category":"codecategories","elo":1145,"win_rate":44.9,"rank":73},{"arena":"models","category":"dataviz","elo":1153,"win_rate":45.6,"rank":68},{"arena":"models","category":"gamedev","elo":1153,"win_rate":44.6,"rank":66},{"arena":"models","category":"svg","elo":1075,"win_rate":39.1,"rank":60},{"arena":"models","category":"uicomponent","elo":1136,"win_rate":42.7,"rank":68},{"arena":"models","category":"website","elo":1147,"win_rate":45.1,"rank":73}],"artificial_analysis":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4}},"reasoning":{"mandatory":false}}],"total_count":20,"links":{"next":null}}