{"data":[{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000042","input_cache_read":"0.0000000042"},"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_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":24.7,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"openai/gpt-6-luna","canonical_slug":"openai/gpt-6-luna-20260922","hugging_face_id":null,"name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight 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":"0.0000001","completion":"0.0000005","web_search":"0.01","input_cache_read":"0.00000001","input_cache_write":"0.000000125","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.00000075","input_cache_read":"0.00000002","input_cache_write":"0.00000025"}]},"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","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/openai/gpt-6-luna-20260922/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":38.1,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash-20260826","hugging_face_id":"zai-org/GLM-5.3-Flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003"},"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"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},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1314,"win_rate":56.2,"rank":18},{"arena":"models","category":"asciiart","elo":1271,"win_rate":55.2,"rank":11},{"arena":"models","category":"codecategories","elo":1279,"win_rate":49.2,"rank":25},{"arena":"models","category":"dataviz","elo":1260,"win_rate":50.1,"rank":33},{"arena":"models","category":"gamedev","elo":1276,"win_rate":46.8,"rank":23},{"arena":"models","category":"svg","elo":1280,"win_rate":56.4,"rank":13},{"arena":"models","category":"uicomponent","elo":1309,"win_rate":54.1,"rank":16},{"arena":"models","category":"website","elo":1270,"win_rate":48.4,"rank":29}],"artificial_analysis":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"deepseek/deepseek-v4.1-flash-1017","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003","overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":0,"utc_end":100,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":100,"utc_end":400,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":400,"utc_end":600,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":600,"utc_end":1000,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":1000,"utc_end":0,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"}]},"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_completion_tokens","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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"spreadsheet","elo":1280,"win_rate":51.2,"rank":6},{"arena":"models","category":"3d","elo":1362,"win_rate":46.7,"rank":10},{"arena":"models","category":"asciiart","elo":1220,"win_rate":50.8,"rank":20},{"arena":"models","category":"codecategories","elo":1289,"win_rate":47.8,"rank":20},{"arena":"models","category":"dataviz","elo":1277,"win_rate":51.2,"rank":24},{"arena":"models","category":"gamedev","elo":1263,"win_rate":43.3,"rank":32},{"arena":"models","category":"svg","elo":1243,"win_rate":51.6,"rank":16},{"arena":"models","category":"uicomponent","elo":1300,"win_rate":53.4,"rank":18},{"arena":"models","category":"website","elo":1299,"win_rate":52.8,"rank":15}],"artificial_analysis":{"intelligence_index":39.5,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"openai/gpt-6.1-sol","canonical_slug":"openai/gpt-6.1-sol-20260929","hugging_face_id":null,"name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000002","input_cache_write":"0.000005"}]},"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","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"blender3d","elo":1362,"win_rate":71.7,"rank":2},{"arena":"agents","category":"mobileapps","elo":1233,"win_rate":52.8,"rank":8},{"arena":"agents","category":"spreadsheet","elo":1287,"win_rate":52.5,"rank":5},{"arena":"agents","category":"webapps","elo":1305,"win_rate":60,"rank":4},{"arena":"models","category":"3d","elo":1437,"win_rate":59.6,"rank":4},{"arena":"models","category":"codecategories","elo":1358,"win_rate":57,"rank":4},{"arena":"models","category":"dataviz","elo":1291,"win_rate":53.5,"rank":16},{"arena":"models","category":"gamedev","elo":1408,"win_rate":61,"rank":4},{"arena":"models","category":"uicomponent","elo":1344,"win_rate":58.6,"rank":6},{"arena":"models","category":"website","elo":1315,"win_rate":54.1,"rank":8}],"artificial_analysis":{"intelligence_index":51.8,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Luna","created":1783590864,"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...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"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","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":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"anthropic/claude-opus-5.5","canonical_slug":"anthropic/claude-opus-5.5-20260921","hugging_face_id":null,"name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.000005","input_cache_write_1h":"0.000008"},"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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5.5-20260921/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"blender3d","elo":1273,"win_rate":58.7,"rank":4},{"arena":"agents","category":"mobileapps","elo":1305,"win_rate":62,"rank":2},{"arena":"agents","category":"spreadsheet","elo":1395,"win_rate":69.3,"rank":2},{"arena":"agents","category":"webapps","elo":1319,"win_rate":61.1,"rank":1},{"arena":"models","category":"3d","elo":1468,"win_rate":65,"rank":1},{"arena":"models","category":"asciiart","elo":1351,"win_rate":65,"rank":2},{"arena":"models","category":"codecategories","elo":1386,"win_rate":61.5,"rank":1},{"arena":"models","category":"dataviz","elo":1397,"win_rate":64.6,"rank":1},{"arena":"models","category":"gamedev","elo":1438,"win_rate":66.4,"rank":1},{"arena":"models","category":"svg","elo":1323,"win_rate":52.2,"rank":3},{"arena":"models","category":"uicomponent","elo":1377,"win_rate":63.5,"rank":2},{"arena":"models","category":"website","elo":1326,"win_rate":55.5,"rank":4}],"artificial_analysis":{"intelligence_index":57.6,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"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":"0.0000000765","completion":"0.000000255","input_cache_read":"0.0000000425"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","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":16.7,"coding_index":39.3,"agentic_index":2.9}},"reasoning":{"mandatory":false,"default_enabled":false}},{"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 0423","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":"0.00000004732","completion":"0.00000009464","input_cache_read":"0.000000009464"},"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_completion_tokens","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":{},"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":1186,"win_rate":49.3,"rank":56},{"arena":"models","category":"asciiart","elo":1107,"win_rate":42.7,"rank":59},{"arena":"models","category":"codecategories","elo":1204,"win_rate":48.9,"rank":62},{"arena":"models","category":"dataviz","elo":1127,"win_rate":40.7,"rank":93},{"arena":"models","category":"gamedev","elo":1197,"win_rate":50.2,"rank":58},{"arena":"models","category":"svg","elo":1152,"win_rate":48.4,"rank":45},{"arena":"models","category":"uicomponent","elo":1159,"win_rate":44.7,"rank":75},{"arena":"models","category":"website","elo":1206,"win_rate":49.1,"rank":63}],"artificial_analysis":{"intelligence_index":24.4,"coding_index":52,"agentic_index":26.3}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"anthropic/claude-haiku-5.5","canonical_slug":"anthropic/claude-haiku-5.5-20261007","hugging_face_id":null,"name":"Anthropic: Claude Haiku 5.5","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000005","web_search":"0.01","input_cache_read":"0.00000001","input_cache_write":"0.000000125","input_cache_write_1h":"0.0000002","overrides":[{"min_prompt_tokens":100000,"prompt":"0.0000005","completion":"0.0000025","input_cache_read":"0.00000005","input_cache_write":"0.000000625","input_cache_write_1h":"0.000001"}]},"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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-haiku-5.5-20261007/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1344,"win_rate":58.2,"rank":11},{"arena":"models","category":"codecategories","elo":1280,"win_rate":50.6,"rank":24},{"arena":"models","category":"dataviz","elo":1291,"win_rate":54.3,"rank":15},{"arena":"models","category":"gamedev","elo":1322,"win_rate":54.9,"rank":12},{"arena":"models","category":"uicomponent","elo":1278,"win_rate":50.9,"rank":26},{"arena":"models","category":"website","elo":1262,"win_rate":48.6,"rank":36}],"artificial_analysis":{"intelligence_index":43.4,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"meta/muse-spark-1.3-contributor","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","hugging_face_id":null,"name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","web_search":"0.0025","input_cache_read":"0.000000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-20260731","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"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....","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000119","completion":"0.000000238","input_cache_read":"0.0000000238"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"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_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":[],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1206,"win_rate":48.7,"rank":46},{"arena":"models","category":"asciiart","elo":1088,"win_rate":33.3,"rank":64},{"arena":"models","category":"codecategories","elo":1228,"win_rate":46.4,"rank":53},{"arena":"models","category":"dataviz","elo":1180,"win_rate":41.1,"rank":66},{"arena":"models","category":"gamedev","elo":1206,"win_rate":44.6,"rank":54},{"arena":"models","category":"svg","elo":1180,"win_rate":45.1,"rank":35},{"arena":"models","category":"uicomponent","elo":1230,"win_rate":46.8,"rank":50},{"arena":"models","category":"website","elo":1236,"win_rate":46.7,"rank":51}],"artificial_analysis":{"intelligence_index":34.3,"coding_index":69.1,"agentic_index":41}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"tencent/hy4-preview","canonical_slug":"tencent/hy4-preview-20260827","hugging_face_id":"tencent/Hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000007506","completion":"0.0000022509","input_cache_read":"0.0000000378","overrides":[{"utc_start":0,"utc_end":1600,"prompt":"0.000000834","completion":"0.000002501","input_cache_read":"0.000000042"},{"utc_start":1600,"utc_end":0,"prompt":"0.0000007506","completion":"0.0000022509","input_cache_read":"0.0000000378"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy4-preview-20260827/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"anthropic/claude-sonnet-5.5","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","hugging_face_id":null,"name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","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":"0.0000001","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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5.5-20260928/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"blender3d","elo":1305,"win_rate":64.1,"rank":3},{"arena":"agents","category":"mobileapps","elo":1283,"win_rate":60,"rank":3},{"arena":"agents","category":"spreadsheet","elo":1291,"win_rate":53.3,"rank":4},{"arena":"agents","category":"webapps","elo":1305,"win_rate":60.3,"rank":3},{"arena":"models","category":"3d","elo":1401,"win_rate":51.4,"rank":5},{"arena":"models","category":"codecategories","elo":1354,"win_rate":56.3,"rank":5},{"arena":"models","category":"dataviz","elo":1387,"win_rate":67.7,"rank":2},{"arena":"models","category":"gamedev","elo":1413,"win_rate":62.1,"rank":2},{"arena":"models","category":"uicomponent","elo":1374,"win_rate":63.4,"rank":4},{"arena":"models","category":"website","elo":1322,"win_rate":54.5,"rank":6}],"artificial_analysis":{"intelligence_index":56,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"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":{},"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":1140,"win_rate":52.2,"rank":16},{"arena":"agents","category":"androidnative","elo":1198,"win_rate":62.1,"rank":13},{"arena":"agents","category":"fullstack","elo":1213,"win_rate":64.3,"rank":14},{"arena":"agents","category":"godotgamedev","elo":1226,"win_rate":60.6,"rank":12},{"arena":"agents","category":"mobileapps","elo":1212,"win_rate":63.6,"rank":15},{"arena":"agents","category":"webapps","elo":1190,"win_rate":57,"rank":27},{"arena":"models","category":"3d","elo":1231,"win_rate":57.5,"rank":40},{"arena":"models","category":"asciiart","elo":1233,"win_rate":60.1,"rank":19},{"arena":"models","category":"codecategories","elo":1275,"win_rate":59.4,"rank":26},{"arena":"models","category":"dataviz","elo":1278,"win_rate":58.3,"rank":23},{"arena":"models","category":"gamedev","elo":1259,"win_rate":58.8,"rank":37},{"arena":"models","category":"svg","elo":1193,"win_rate":58.7,"rank":28},{"arena":"models","category":"uicomponent","elo":1266,"win_rate":58.3,"rank":33},{"arena":"models","category":"website","elo":1283,"win_rate":60,"rank":23}],"artificial_analysis":{"intelligence_index":30.1,"coding_index":63,"agentic_index":31.8}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"}},{"id":"google/gemini-3.8-flash","canonical_slug":"google/gemini-3.8-flash-20260902","hugging_face_id":null,"name":"Google: Gemini 3.8 Flash","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","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":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667"},"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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.8-flash-20260902/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1084,"win_rate":33.4,"rank":31},{"arena":"agents","category":"blender3d","elo":1232,"win_rate":54.3,"rank":5},{"arena":"agents","category":"fullstack","elo":1244,"win_rate":48.1,"rank":11},{"arena":"agents","category":"godotgamedev","elo":1273,"win_rate":53,"rank":5},{"arena":"agents","category":"mobileapps","elo":1236,"win_rate":54.6,"rank":7},{"arena":"agents","category":"python-pptxslides","elo":1137,"win_rate":40.1,"rank":21},{"arena":"agents","category":"spreadsheet","elo":1055,"win_rate":40.5,"rank":22},{"arena":"agents","category":"webapps","elo":1239,"win_rate":46.9,"rank":14},{"arena":"models","category":"3d","elo":1293,"win_rate":49.9,"rank":21},{"arena":"models","category":"asciiart","elo":1267,"win_rate":52.1,"rank":13},{"arena":"models","category":"codecategories","elo":1302,"win_rate":50.4,"rank":15},{"arena":"models","category":"dataviz","elo":1271,"win_rate":51.2,"rank":27},{"arena":"models","category":"gamedev","elo":1303,"win_rate":51,"rank":18},{"arena":"models","category":"svg","elo":1291,"win_rate":54.8,"rank":9},{"arena":"models","category":"uicomponent","elo":1313,"win_rate":53.9,"rank":15},{"arena":"models","category":"website","elo":1299,"win_rate":50.1,"rank":17}],"artificial_analysis":{"intelligence_index":40.9,"coding_index":76.3,"agentic_index":40.2}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}}],"total_count":16,"links":{"next":null}}