{"data":[{"id":"google/gemini-4-neon","canonical_slug":"google/gemini-4-neon-20261118","hugging_face_id":null,"name":"Google: Gemini 4 Neon","created":1795006977,"description":"Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","image":"0.000003","audio":"0.000003","input_audio_cache":"0.00000015","web_search":"0.014","internal_reasoning":"0.000015","input_cache_read":"0.00000015","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"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-4-neon-20261118/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1047,"win_rate":33.3,"rank":45},{"arena":"models","category":"3d","elo":1491,"win_rate":76.2,"rank":1},{"arena":"models","category":"codecategories","elo":1390,"win_rate":65.4,"rank":2},{"arena":"models","category":"gamedev","elo":1394,"win_rate":64.7,"rank":5},{"arena":"models","category":"uicomponent","elo":1347,"win_rate":58.1,"rank":7},{"arena":"models","category":"website","elo":1343,"win_rate":60,"rank":4}],"artificial_analysis":{"intelligence_index":61.4,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":65.1,"strategy_and_ops_index":63.8,"legal_index":63.8,"healthcare_and_medical_index":60.1,"engineering_index":66.8,"economics_index":61.9,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-6.2-astra-pro","canonical_slug":"openai/gpt-6.2-astra-pro-20261117","hugging_face_id":null,"name":"OpenAI: GPT-6.2 Astra Pro","created":1794938432,"description":"GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000008","completion":"0.00004","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.00001","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000016","completion":"0.00006","input_cache_read":"0.0000008","input_cache_write":"0.00002"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"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-6.2-astra-pro-20261117/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-6.2-astra","canonical_slug":"openai/gpt-6.2-astra-20261117","hugging_face_id":null,"name":"OpenAI: GPT-6.2 Astra","created":1794938423,"description":"GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects. It is suited for real-world engineering, professional work and scientific research, with stronger...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000008","completion":"0.00004","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.00001","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000016","completion":"0.00006","input_cache_read":"0.0000008","input_cache_write":"0.00002"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"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-6.2-astra-20261117/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":62.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":60.9,"strategy_and_ops_index":63.3,"legal_index":58.7,"healthcare_and_medical_index":57,"engineering_index":66.6,"economics_index":61.1,"cyber_index":40.8,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-6.2-sol-pro","canonical_slug":"openai/gpt-6.2-sol-pro-20261117","hugging_face_id":null,"name":"OpenAI: GPT-6.2 Sol Pro","created":1794938409,"description":"GPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","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":false},"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-6.2-sol-pro-20261117/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-6.2-sol","canonical_slug":"openai/gpt-6.2-sol-20261117","hugging_face_id":null,"name":"OpenAI: GPT-6.2 Sol","created":1794938371,"description":"GPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series. It is an efficient, versatile model for everyday work, suited...","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-6.2-sol-20261117/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":57.3,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":57.2,"strategy_and_ops_index":59.4,"legal_index":55,"healthcare_and_medical_index":53.3,"engineering_index":61.2,"economics_index":57.4,"cyber_index":37.7,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"google/gemini-4-hydrogen","canonical_slug":"google/gemini-4-hydrogen-20261112","hugging_face_id":null,"name":"Google: Gemini 4 Hydrogen","created":1794506460,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","image":"0.0000015","audio":"0.0000015","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.0000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000833333333333333"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"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-4-hydrogen-20261112/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"codetovideo","elo":1335,"win_rate":69.5,"rank":3},{"arena":"agents","category":"mobileapps","elo":1295,"win_rate":60,"rank":5},{"arena":"agents","category":"pdf","elo":1209,"win_rate":54.3,"rank":14},{"arena":"models","category":"3d","elo":1396,"win_rate":66.1,"rank":8},{"arena":"models","category":"asciiart","elo":1456,"win_rate":73.1,"rank":1},{"arena":"models","category":"codecategories","elo":1330,"win_rate":56.3,"rank":12},{"arena":"models","category":"dataviz","elo":1288,"win_rate":54.8,"rank":17},{"arena":"models","category":"gamedev","elo":1338,"win_rate":52.3,"rank":12},{"arena":"models","category":"uicomponent","elo":1337,"win_rate":54,"rank":11},{"arena":"models","category":"website","elo":1326,"win_rate":58.7,"rank":6}],"artificial_analysis":{"intelligence_index":53.9,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":58.1,"strategy_and_ops_index":57.7,"legal_index":56.7,"healthcare_and_medical_index":53.3,"engineering_index":60.1,"economics_index":55,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"google/gemini-4-carbon","canonical_slug":"google/gemini-4-carbon-20261110","hugging_face_id":null,"name":"Google: Gemini 4 Carbon","created":1794326871,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"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-4-carbon-20261110/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"codetovideo","elo":1275,"win_rate":62.8,"rank":5},{"arena":"agents","category":"mobileapps","elo":1297,"win_rate":62,"rank":3},{"arena":"agents","category":"pdf","elo":1326,"win_rate":69.4,"rank":3},{"arena":"agents","category":"spreadsheet","elo":1222,"win_rate":49.1,"rank":13},{"arena":"models","category":"3d","elo":1413,"win_rate":68.4,"rank":7},{"arena":"models","category":"codecategories","elo":1350,"win_rate":60.8,"rank":7},{"arena":"models","category":"dataviz","elo":1343,"win_rate":62,"rank":5},{"arena":"models","category":"gamedev","elo":1410,"win_rate":67.8,"rank":4},{"arena":"models","category":"svg","elo":1393,"win_rate":68.9,"rank":1},{"arena":"models","category":"uicomponent","elo":1345,"win_rate":59.8,"rank":8},{"arena":"models","category":"website","elo":1304,"win_rate":55,"rank":14}],"artificial_analysis":{"intelligence_index":60,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":62.6,"strategy_and_ops_index":60.9,"legal_index":62,"healthcare_and_medical_index":56.8,"engineering_index":65.3,"economics_index":59.6,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-6.1-terra-pro","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","hugging_face_id":null,"name":"OpenAI: GPT-6.1 Terra Pro","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.00000005","input_cache_write":"0.00000125","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.0000075","input_cache_read":"0.0000001","input_cache_write":"0.0000025"}]},"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-6.1-terra-pro-20261026/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-6.1-terra","canonical_slug":"openai/gpt-6.1-terra-20261026","hugging_face_id":null,"name":"OpenAI: GPT-6.1 Terra","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","web_search":"0.01","input_cache_read":"0.00000005","input_cache_write":"0.00000125","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000002","completion":"0.0000075","input_cache_read":"0.0000001","input_cache_write":"0.0000025"}]},"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-terra-20261026/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":51.3,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":49,"strategy_and_ops_index":50,"legal_index":46.4,"healthcare_and_medical_index":44.7,"engineering_index":54.7,"economics_index":48.5,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1174,"win_rate":51.6,"rank":26},{"arena":"models","category":"3d","elo":1307,"win_rate":54.9,"rank":18},{"arena":"models","category":"asciiart","elo":1213,"win_rate":48.8,"rank":25},{"arena":"models","category":"codecategories","elo":1273,"win_rate":50.3,"rank":25},{"arena":"models","category":"dataviz","elo":1276,"win_rate":50.6,"rank":23},{"arena":"models","category":"gamedev","elo":1313,"win_rate":52.7,"rank":16},{"arena":"models","category":"svg","elo":1200,"win_rate":44.9,"rank":29},{"arena":"models","category":"uicomponent","elo":1257,"win_rate":49.1,"rank":40},{"arena":"models","category":"website","elo":1248,"win_rate":48.1,"rank":44}],"artificial_analysis":{"intelligence_index":36.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":43.6,"strategy_and_ops_index":39.1,"legal_index":38.7,"healthcare_and_medical_index":37.5,"engineering_index":42.5,"economics_index":42.7,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":76.5}},"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"mistralai/mistral-large-4-0","canonical_slug":"mistralai/mistral-large-4-0-20261006","hugging_face_id":"mistralai/Mistral-Large-4-1T-A52B","name":"Mistral: Mistral Large 4","created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000007","completion":"0.0000021","input_cache_read":"0.00000007"},"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-4-0-20261006/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1225,"win_rate":45.7,"rank":36},{"arena":"models","category":"asciiart","elo":1196,"win_rate":43.5,"rank":26},{"arena":"models","category":"codecategories","elo":1247,"win_rate":46.9,"rank":43},{"arena":"models","category":"dataviz","elo":1271,"win_rate":51.3,"rank":29},{"arena":"models","category":"gamedev","elo":1190,"win_rate":40.4,"rank":56},{"arena":"models","category":"svg","elo":1216,"win_rate":44.9,"rank":26},{"arena":"models","category":"uicomponent","elo":1272,"win_rate":49,"rank":32},{"arena":"models","category":"website","elo":1253,"win_rate":48,"rank":41}],"artificial_analysis":{"intelligence_index":26.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":39.1,"strategy_and_ops_index":43.4,"legal_index":34.6,"healthcare_and_medical_index":36.7,"engineering_index":33.4,"economics_index":35.6,"cyber_index":50.9,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"openai/gpt-6.1-sol-pro","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","hugging_face_id":null,"name":"OpenAI: GPT-6.1 Sol Pro","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","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":{"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-6.1-sol-pro-20260929/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1191,"win_rate":48.1,"rank":15},{"arena":"agents","category":"blender3d","elo":1238,"win_rate":59.9,"rank":2},{"arena":"agents","category":"codetovideo","elo":1185,"win_rate":54,"rank":17},{"arena":"agents","category":"fullstack","elo":1225,"win_rate":47.2,"rank":14},{"arena":"agents","category":"mobileapps","elo":1227,"win_rate":52.6,"rank":15},{"arena":"agents","category":"pdf","elo":1123,"win_rate":42.4,"rank":39},{"arena":"agents","category":"spreadsheet","elo":1207,"win_rate":41.2,"rank":14},{"arena":"agents","category":"webapps","elo":1268,"win_rate":56.6,"rank":9},{"arena":"models","category":"3d","elo":1414,"win_rate":59.3,"rank":6},{"arena":"models","category":"codecategories","elo":1353,"win_rate":56.4,"rank":6},{"arena":"models","category":"dataviz","elo":1282,"win_rate":52.8,"rank":19},{"arena":"models","category":"gamedev","elo":1385,"win_rate":58.1,"rank":7},{"arena":"models","category":"svg","elo":1333,"win_rate":59.9,"rank":3},{"arena":"models","category":"uicomponent","elo":1356,"win_rate":58.5,"rank":6},{"arena":"models","category":"website","elo":1312,"win_rate":54.1,"rank":11}],"artificial_analysis":{"intelligence_index":54.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":56.2,"strategy_and_ops_index":57.6,"legal_index":53.7,"healthcare_and_medical_index":52,"engineering_index":59.4,"economics_index":56.3,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1264,"win_rate":58.1,"rank":6},{"arena":"agents","category":"blender3d","elo":1232,"win_rate":59.2,"rank":3},{"arena":"agents","category":"codetovideo","elo":1326,"win_rate":70.6,"rank":4},{"arena":"agents","category":"fullstack","elo":1349,"win_rate":62.8,"rank":3},{"arena":"agents","category":"mobileapps","elo":1258,"win_rate":57.2,"rank":7},{"arena":"agents","category":"pdf","elo":1241,"win_rate":58.5,"rank":11},{"arena":"agents","category":"spreadsheet","elo":1250,"win_rate":46,"rank":10},{"arena":"agents","category":"webapps","elo":1286,"win_rate":58.9,"rank":4},{"arena":"models","category":"3d","elo":1393,"win_rate":56,"rank":9},{"arena":"models","category":"asciiart","elo":1399,"win_rate":70.9,"rank":2},{"arena":"models","category":"codecategories","elo":1353,"win_rate":57.6,"rank":5},{"arena":"models","category":"dataviz","elo":1355,"win_rate":63.5,"rank":3},{"arena":"models","category":"gamedev","elo":1426,"win_rate":64.9,"rank":3},{"arena":"models","category":"svg","elo":1289,"win_rate":55.1,"rank":9},{"arena":"models","category":"uicomponent","elo":1376,"win_rate":62.1,"rank":2},{"arena":"models","category":"website","elo":1303,"win_rate":53.2,"rank":15}],"artificial_analysis":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":55.8,"strategy_and_ops_index":58.1,"legal_index":52.2,"healthcare_and_medical_index":54.2,"engineering_index":58.5,"economics_index":54.1,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"openai/gpt-6-luna-pro","canonical_slug":"openai/gpt-6-luna-pro-20260922","hugging_face_id":null,"name":"OpenAI: GPT-6 Luna Pro","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","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-pro-20260922/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":33.9,"strategy_and_ops_index":43.2,"legal_index":32.2,"healthcare_and_medical_index":34.8,"engineering_index":33.3,"economics_index":34.5,"cyber_index":52.7,"openness_index":null,"multilingual_index":null,"decision_index":75.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"openai/gpt-6-sol-pro","canonical_slug":"openai/gpt-6-sol-pro-20260922","hugging_face_id":null,"name":"OpenAI: GPT-6 Sol Pro","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","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":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","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":{"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-sol-pro-20260922/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"openai/gpt-6-sol","canonical_slug":"openai/gpt-6-sol-20260922","hugging_face_id":null,"name":"OpenAI: GPT-6 Sol","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding 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":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","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":{"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-sol-20260922/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":44.2,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":47.5,"strategy_and_ops_index":52.1,"legal_index":46.3,"healthcare_and_medical_index":45.1,"engineering_index":48.9,"economics_index":47.7,"cyber_index":36.8,"openness_index":null,"multilingual_index":null,"decision_index":null}},"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1401,"win_rate":75.2,"rank":1},{"arena":"agents","category":"blender3d","elo":1221,"win_rate":57,"rank":4},{"arena":"agents","category":"codetovideo","elo":1339,"win_rate":72.8,"rank":2},{"arena":"agents","category":"fullstack","elo":1386,"win_rate":70,"rank":2},{"arena":"agents","category":"mobileapps","elo":1296,"win_rate":61.8,"rank":4},{"arena":"agents","category":"pdf","elo":1312,"win_rate":68.5,"rank":4},{"arena":"agents","category":"spreadsheet","elo":1289,"win_rate":53.1,"rank":6},{"arena":"agents","category":"webapps","elo":1308,"win_rate":62.7,"rank":1},{"arena":"models","category":"3d","elo":1449,"win_rate":65.2,"rank":3},{"arena":"models","category":"asciiart","elo":1343,"win_rate":63.8,"rank":4},{"arena":"models","category":"codecategories","elo":1381,"win_rate":61.4,"rank":4},{"arena":"models","category":"dataviz","elo":1383,"win_rate":63.7,"rank":1},{"arena":"models","category":"gamedev","elo":1435,"win_rate":66.4,"rank":2},{"arena":"models","category":"svg","elo":1315,"win_rate":54.1,"rank":5},{"arena":"models","category":"uicomponent","elo":1367,"win_rate":62.5,"rank":4},{"arena":"models","category":"website","elo":1321,"win_rate":55.5,"rank":8}],"artificial_analysis":{"intelligence_index":59.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":59.4,"strategy_and_ops_index":61.4,"legal_index":58,"healthcare_and_medical_index":57.9,"engineering_index":65.3,"economics_index":60.3,"cyber_index":28.7,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"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":"0.0000000399","completion":"0.0000000784","input_cache_read":"0.00000003"},"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},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1199,"win_rate":50,"rank":21},{"arena":"models","category":"3d","elo":1281,"win_rate":55,"rank":22},{"arena":"models","category":"asciiart","elo":1261,"win_rate":54.2,"rank":13},{"arena":"models","category":"codecategories","elo":1260,"win_rate":48.3,"rank":31},{"arena":"models","category":"dataviz","elo":1253,"win_rate":49.9,"rank":36},{"arena":"models","category":"gamedev","elo":1253,"win_rate":46.7,"rank":29},{"arena":"models","category":"svg","elo":1265,"win_rate":54.8,"rank":17},{"arena":"models","category":"uicomponent","elo":1289,"win_rate":52,"rank":23},{"arena":"models","category":"website","elo":1252,"win_rate":47.2,"rank":42}],"artificial_analysis":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":38.8,"strategy_and_ops_index":44.5,"legal_index":34.8,"healthcare_and_medical_index":36.6,"engineering_index":34.5,"economics_index":35.3,"cyber_index":49.9,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3-20260816","hugging_face_id":"zai-org/GLM-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"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...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000000699","completion":"0.0000014","input_cache_read":"0.0000000689"},"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_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-5.3-20260816/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1332,"win_rate":70,"rank":1},{"arena":"models","category":"3d","elo":1277,"win_rate":55,"rank":23},{"arena":"models","category":"asciiart","elo":1182,"win_rate":45,"rank":32},{"arena":"models","category":"codecategories","elo":1275,"win_rate":52,"rank":24},{"arena":"models","category":"dataviz","elo":1245,"win_rate":50,"rank":38},{"arena":"models","category":"gamedev","elo":1271,"win_rate":50.4,"rank":24},{"arena":"models","category":"svg","elo":1237,"win_rate":50.9,"rank":21},{"arena":"models","category":"uicomponent","elo":1277,"win_rate":52.9,"rank":27},{"arena":"models","category":"website","elo":1273,"win_rate":52.3,"rank":26},{"arena":"agents","category":"htmlslides","elo":1189,"win_rate":39.1,"rank":2},{"arena":"agents","category":"mobileapps","elo":1184,"win_rate":52.2,"rank":27},{"arena":"agents","category":"python-pptxslides","elo":1217,"win_rate":47.6,"rank":10},{"arena":"agents","category":"webapps","elo":1270,"win_rate":54.2,"rank":7}],"artificial_analysis":{"intelligence_index":31.7,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":42.1,"strategy_and_ops_index":47.4,"legal_index":35.8,"healthcare_and_medical_index":39.3,"engineering_index":37.6,"economics_index":37.3,"cyber_index":36.4,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"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":"0.0000000443","completion":"0.0000003","input_cache_read":"0.000000035"},"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":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1175,"win_rate":48.8,"rank":58},{"arena":"models","category":"asciiart","elo":1082,"win_rate":34,"rank":67},{"arena":"models","category":"codecategories","elo":1211,"win_rate":46.5,"rank":62},{"arena":"models","category":"dataviz","elo":1167,"win_rate":40,"rank":74},{"arena":"models","category":"gamedev","elo":1181,"win_rate":44.9,"rank":61},{"arena":"models","category":"svg","elo":1164,"win_rate":44.7,"rank":45},{"arena":"models","category":"uicomponent","elo":1220,"win_rate":47.1,"rank":55},{"arena":"models","category":"website","elo":1225,"win_rate":46.8,"rank":60}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"anthropic/claude-opus-5","canonical_slug":"anthropic/claude-opus-5-20260723","hugging_face_id":null,"name":"Anthropic: Claude Opus 5","created":1784912544,"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...","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","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1203,"win_rate":53.3,"rank":3},{"arena":"agents","category":"androidnative","elo":1243,"win_rate":55.7,"rank":8},{"arena":"agents","category":"blender3d","elo":1201,"win_rate":63.1,"rank":5},{"arena":"agents","category":"codetovideo","elo":1247,"win_rate":62.5,"rank":8},{"arena":"agents","category":"fullstack","elo":1285,"win_rate":57.5,"rank":8},{"arena":"agents","category":"godotgamedev","elo":1249,"win_rate":54.6,"rank":3},{"arena":"agents","category":"mobileapps","elo":1348,"win_rate":67.1,"rank":1},{"arena":"agents","category":"pdf","elo":1243,"win_rate":58,"rank":9},{"arena":"agents","category":"python-pptxslides","elo":1225,"win_rate":50.9,"rank":8},{"arena":"agents","category":"spreadsheet","elo":1241,"win_rate":43.8,"rank":11},{"arena":"agents","category":"webapps","elo":1235,"win_rate":53.2,"rank":13},{"arena":"models","category":"3d","elo":1309,"win_rate":59.7,"rank":17},{"arena":"models","category":"asciiart","elo":1338,"win_rate":67.6,"rank":5},{"arena":"models","category":"codecategories","elo":1310,"win_rate":57.4,"rank":15},{"arena":"models","category":"dataviz","elo":1324,"win_rate":58.4,"rank":10},{"arena":"models","category":"gamedev","elo":1316,"win_rate":58,"rank":14},{"arena":"models","category":"svg","elo":1298,"win_rate":58.1,"rank":7},{"arena":"models","category":"uicomponent","elo":1335,"win_rate":60.8,"rank":12},{"arena":"models","category":"website","elo":1299,"win_rate":56.1,"rank":18}],"artificial_analysis":{"intelligence_index":44.2,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":49.7,"strategy_and_ops_index":53.7,"legal_index":50.9,"healthcare_and_medical_index":47.1,"engineering_index":51.3,"economics_index":50.4,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"google/gemini-3.5-flash-lite","canonical_slug":"google/gemini-3.5-flash-lite-20260721","hugging_face_id":null,"name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"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.","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":"0.0000003","completion":"0.0000025","image":"0.0000003","audio":"0.0000003","input_audio_cache":"0.00000003","web_search":"0.014","internal_reasoning":"0.0000025","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333"},"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-3.5-flash-lite-20260721/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":11.7,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":23.3,"strategy_and_ops_index":20.7,"legal_index":23.9,"healthcare_and_medical_index":20.5,"engineering_index":21.2,"economics_index":21.9,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"}},{"id":"openai/gpt-5.6-luna-pro","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"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. **Cost note:** pro mode spends far more...","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-pro-20260709/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":23.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":31.8,"strategy_and_ops_index":40.7,"legal_index":27.7,"healthcare_and_medical_index":32.4,"engineering_index":29.4,"economics_index":32.8,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"openai/gpt-5.6-terra-pro","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"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. **Cost note:** pro mode spends far more...","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":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","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":{"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-pro-20260709/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"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":"0.000002","completion":"0.000012","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","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":{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":32.3,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":34.6,"strategy_and_ops_index":45.1,"legal_index":32,"healthcare_and_medical_index":37,"engineering_index":36.6,"economics_index":35.7,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"openai/gpt-5.6-sol-pro","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"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. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.000005","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000008","completion":"0.00003","input_cache_read":"0.0000008","input_cache_write":"0.00001"}]},"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-sol-pro-20260709/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Sol","created":1783590850,"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...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000004","input_cache_write":"0.000005","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000008","completion":"0.00003","input_cache_read":"0.0000008","input_cache_write":"0.00001"}]},"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-sol-20260709/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1170,"win_rate":51.6,"rank":8},{"arena":"agents","category":"androidnative","elo":1208,"win_rate":52.7,"rank":12},{"arena":"agents","category":"blender3d","elo":959,"win_rate":31.4,"rank":22},{"arena":"agents","category":"codetovideo","elo":1109,"win_rate":42.6,"rank":24},{"arena":"agents","category":"fullstack","elo":1226,"win_rate":53.1,"rank":13},{"arena":"agents","category":"godotgamedev","elo":1190,"win_rate":53.5,"rank":14},{"arena":"agents","category":"htmlslides","elo":1119,"win_rate":53.7,"rank":9},{"arena":"agents","category":"mobileapps","elo":1202,"win_rate":49.9,"rank":23},{"arena":"agents","category":"pdf","elo":1203,"win_rate":53.2,"rank":18},{"arena":"agents","category":"python-pptxslides","elo":1179,"win_rate":48.2,"rank":15},{"arena":"agents","category":"spreadsheet","elo":1032,"win_rate":25.6,"rank":22},{"arena":"agents","category":"webapps","elo":1209,"win_rate":51.8,"rank":16},{"arena":"models","category":"3d","elo":1224,"win_rate":52.6,"rank":37},{"arena":"models","category":"asciiart","elo":1189,"win_rate":50.6,"rank":29},{"arena":"models","category":"codecategories","elo":1260,"win_rate":52.5,"rank":30},{"arena":"models","category":"dataviz","elo":1246,"win_rate":52.9,"rank":37},{"arena":"models","category":"gamedev","elo":1256,"win_rate":51.4,"rank":27},{"arena":"models","category":"svg","elo":1178,"win_rate":48.8,"rank":39},{"arena":"models","category":"uicomponent","elo":1260,"win_rate":53.3,"rank":37},{"arena":"models","category":"website","elo":1264,"win_rate":52.5,"rank":31}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"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":"0.00000062","completion":"0.00000242","input_cache_read":"0.00000014"},"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","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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1156,"win_rate":49.7,"rank":9},{"arena":"agents","category":"androidnative","elo":1168,"win_rate":52.7,"rank":23},{"arena":"agents","category":"blender3d","elo":983,"win_rate":36.1,"rank":20},{"arena":"agents","category":"fullstack","elo":1218,"win_rate":60,"rank":17},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":19},{"arena":"agents","category":"htmlslides","elo":1077,"win_rate":49.5,"rank":15},{"arena":"agents","category":"mobileapps","elo":1155,"win_rate":47.4,"rank":33},{"arena":"agents","category":"pdf","elo":1243,"win_rate":59.4,"rank":10},{"arena":"agents","category":"python-pptxslides","elo":1160,"win_rate":48.3,"rank":18},{"arena":"agents","category":"spreadsheet","elo":1027,"win_rate":42.9,"rank":23},{"arena":"agents","category":"webapps","elo":1191,"win_rate":55.6,"rank":20},{"arena":"models","category":"3d","elo":1253,"win_rate":52.7,"rank":27},{"arena":"models","category":"asciiart","elo":1174,"win_rate":46.1,"rank":35},{"arena":"models","category":"codecategories","elo":1268,"win_rate":50.5,"rank":29},{"arena":"models","category":"dataviz","elo":1279,"win_rate":51.7,"rank":20},{"arena":"models","category":"gamedev","elo":1239,"win_rate":48.9,"rank":36},{"arena":"models","category":"svg","elo":1189,"win_rate":47.2,"rank":33},{"arena":"models","category":"uicomponent","elo":1279,"win_rate":55.1,"rank":26},{"arena":"models","category":"website","elo":1272,"win_rate":49.8,"rank":28}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":32.1,"strategy_and_ops_index":30,"legal_index":28.5,"healthcare_and_medical_index":28.7,"engineering_index":null,"economics_index":32.1,"cyber_index":null,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"moonshotai/kimi-k2.7-code","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","hugging_face_id":"moonshotai/Kimi-K2.7-Code","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"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...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.000003","input_cache_read":"0.00000012"},"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_tokens","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","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/moonshotai/kimi-k2.7-code-20260612/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1077,"win_rate":42.8,"rank":22},{"arena":"agents","category":"androidnative","elo":1127,"win_rate":46,"rank":31},{"arena":"agents","category":"fullstack","elo":1153,"win_rate":50.9,"rank":27},{"arena":"agents","category":"godotgamedev","elo":1115,"win_rate":49.2,"rank":27},{"arena":"agents","category":"htmlslides","elo":1105,"win_rate":53.9,"rank":10},{"arena":"agents","category":"mobileapps","elo":1135,"win_rate":46.1,"rank":39},{"arena":"agents","category":"python-pptxslides","elo":1119,"win_rate":44.6,"rank":24},{"arena":"agents","category":"webapps","elo":1144,"win_rate":46.9,"rank":32},{"arena":"models","category":"3d","elo":1207,"win_rate":49.6,"rank":46},{"arena":"models","category":"asciiart","elo":1175,"win_rate":47.6,"rank":34},{"arena":"models","category":"codecategories","elo":1235,"win_rate":49.6,"rank":48},{"arena":"models","category":"dataviz","elo":1216,"win_rate":48,"rank":55},{"arena":"models","category":"gamedev","elo":1193,"win_rate":46.2,"rank":55},{"arena":"models","category":"svg","elo":1157,"win_rate":43.3,"rank":47},{"arena":"models","category":"uicomponent","elo":1245,"win_rate":50.9,"rank":46},{"arena":"models","category":"website","elo":1253,"win_rate":51.3,"rank":40}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":27.8,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true}},{"id":"anthropic/claude-fable-5","canonical_slug":"anthropic/claude-5-fable-20260609","hugging_face_id":null,"name":"Anthropic: Claude Fable 5","created":1781007515,"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...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00005","web_search":"0.01","input_cache_read":"0.000001","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002"},"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-5-fable-20260609/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1231,"win_rate":62,"rank":2},{"arena":"agents","category":"agentichtmlslides","elo":1254,"win_rate":59.4,"rank":1},{"arena":"agents","category":"agenticslides(html)","elo":1252,"win_rate":59.5,"rank":1},{"arena":"agents","category":"androidnative","elo":1274,"win_rate":65.3,"rank":4},{"arena":"agents","category":"fullstack","elo":1258,"win_rate":58.2,"rank":10},{"arena":"agents","category":"godotgamedev","elo":1261,"win_rate":64.3,"rank":2},{"arena":"agents","category":"htmlslides","elo":1180,"win_rate":63.2,"rank":3},{"arena":"agents","category":"mobileapps","elo":1256,"win_rate":60.4,"rank":8},{"arena":"agents","category":"python-pptxslides","elo":1269,"win_rate":61.2,"rank":4},{"arena":"agents","category":"webapps","elo":1229,"win_rate":56.3,"rank":14},{"arena":"models","category":"3d","elo":1284,"win_rate":61.6,"rank":21},{"arena":"models","category":"asciiart","elo":1311,"win_rate":67.9,"rank":7},{"arena":"models","category":"codecategories","elo":1293,"win_rate":57.9,"rank":18},{"arena":"models","category":"dataviz","elo":1300,"win_rate":57.8,"rank":14},{"arena":"models","category":"gamedev","elo":1308,"win_rate":60.8,"rank":17},{"arena":"models","category":"svg","elo":1287,"win_rate":62.8,"rank":10},{"arena":"models","category":"uicomponent","elo":1303,"win_rate":58.2,"rank":18},{"arena":"models","category":"website","elo":1284,"win_rate":56.3,"rank":24}]},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"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","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1183,"win_rate":55.3,"rank":5},{"arena":"agents","category":"agentichtmlslides","elo":1227,"win_rate":55.6,"rank":3},{"arena":"agents","category":"agenticslides","elo":1294,"win_rate":64.8,"rank":1},{"arena":"agents","category":"agenticslides(html)","elo":1230,"win_rate":56,"rank":3},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1},{"arena":"agents","category":"androidnative","elo":1220,"win_rate":55.6,"rank":11},{"arena":"agents","category":"blender3d","elo":1096,"win_rate":48.2,"rank":13},{"arena":"agents","category":"codetovideo","elo":1186,"win_rate":53.3,"rank":16},{"arena":"agents","category":"fullstack","elo":1227,"win_rate":55,"rank":12},{"arena":"agents","category":"godotgamedev","elo":1201,"win_rate":55.8,"rank":11},{"arena":"agents","category":"htmlslides","elo":1124,"win_rate":58.1,"rank":8},{"arena":"agents","category":"mobileapps","elo":1209,"win_rate":53.5,"rank":20},{"arena":"agents","category":"pdf","elo":1165,"win_rate":49.3,"rank":28},{"arena":"agents","category":"pptxslides","elo":1306,"win_rate":67.9,"rank":1},{"arena":"agents","category":"python-pptxslides","elo":1298,"win_rate":65.9,"rank":2},{"arena":"agents","category":"spreadsheet","elo":1034,"win_rate":23.1,"rank":21},{"arena":"agents","category":"webapps","elo":1200,"win_rate":50.3,"rank":18},{"arena":"models","category":"3d","elo":1189,"win_rate":50.8,"rank":53},{"arena":"models","category":"asciiart","elo":1261,"win_rate":60.7,"rank":12},{"arena":"models","category":"codecategories","elo":1236,"win_rate":52,"rank":47},{"arena":"models","category":"dataviz","elo":1232,"win_rate":52.4,"rank":45},{"arena":"models","category":"gamedev","elo":1233,"win_rate":51.5,"rank":40},{"arena":"models","category":"svg","elo":1175,"win_rate":50.2,"rank":40},{"arena":"models","category":"uicomponent","elo":1241,"win_rate":52.7,"rank":49},{"arena":"models","category":"website","elo":1246,"win_rate":52.8,"rank":46}]},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"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":"0.0000000833333333333333"},"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"}},{"id":"mistralai/mistral-medium-3-5","canonical_slug":"mistralai/mistral-medium-3.5-20260430","hugging_face_id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral: Mistral Medium 3.5","created":1777570439,"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...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","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":"2027-01-31","links":{"details":"/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":4.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":11.1,"strategy_and_ops_index":9.4,"legal_index":9.7,"healthcare_and_medical_index":10.7,"engineering_index":12.2,"economics_index":11.6,"cyber_index":null,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"openai/gpt-5.5","canonical_slug":"openai/gpt-5.5-20260423","hugging_face_id":"","name":"OpenAI: GPT-5.5","created":1777051893,"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_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","web_search":"0.01","input_cache_read":"0.0000005","overrides":[{"min_prompt_tokens":272000,"prompt":"0.00001","completion":"0.000045","input_cache_read":"0.000001"}]},"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":"2025-12-01","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.5-20260423/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1125,"win_rate":52.2,"rank":15},{"arena":"agents","category":"agentichtmlslides","elo":1084,"win_rate":34.2,"rank":8},{"arena":"agents","category":"agenticslides","elo":1150,"win_rate":43.5,"rank":6},{"arena":"agents","category":"agenticslides(html)","elo":1077,"win_rate":33.2,"rank":8},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1155,"win_rate":45.2,"rank":6},{"arena":"agents","category":"androidnative","elo":1152,"win_rate":50.8,"rank":27},{"arena":"agents","category":"fullstack","elo":1067,"win_rate":43,"rank":36},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":52.3,"rank":22},{"arena":"agents","category":"htmlslides","elo":970,"win_rate":35.6,"rank":24},{"arena":"agents","category":"mobileapps","elo":1135,"win_rate":50.4,"rank":38},{"arena":"agents","category":"pptxslides","elo":1157,"win_rate":45.3,"rank":6},{"arena":"agents","category":"python-pptxslides","elo":1152,"win_rate":43.3,"rank":20},{"arena":"agents","category":"webapps","elo":1084,"win_rate":42.6,"rank":39},{"arena":"models","category":"3d","elo":1163,"win_rate":48.7,"rank":63},{"arena":"models","category":"asciiart","elo":1236,"win_rate":57,"rank":22},{"arena":"models","category":"codecategories","elo":1242,"win_rate":52.8,"rank":46},{"arena":"models","category":"dataviz","elo":1257,"win_rate":55.3,"rank":34},{"arena":"models","category":"gamedev","elo":1265,"win_rate":56,"rank":25},{"arena":"models","category":"svg","elo":1219,"win_rate":54.6,"rank":23},{"arena":"models","category":"uicomponent","elo":1244,"win_rate":53.2,"rank":47},{"arena":"models","category":"website","elo":1244,"win_rate":52.2,"rank":47}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"moonshotai/kimi-k2.6","canonical_slug":"moonshotai/kimi-k2.6-20260420","hugging_face_id":"moonshotai/Kimi-K2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"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...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000065","completion":"0.00000341","input_cache_read":"0.00000015"},"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_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","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/moonshotai/kimi-k2.6-20260420/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1088,"win_rate":47.5,"rank":21},{"arena":"agents","category":"agentichtmlslides","elo":1248,"win_rate":59,"rank":2},{"arena":"agents","category":"agenticslides","elo":1187,"win_rate":45.8,"rank":4},{"arena":"agents","category":"agenticslides(html)","elo":1252,"win_rate":59.2,"rank":2},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1186,"win_rate":45.5,"rank":4},{"arena":"agents","category":"androidnative","elo":1150,"win_rate":49.2,"rank":28},{"arena":"agents","category":"fullstack","elo":1133,"win_rate":49.4,"rank":30},{"arena":"agents","category":"godotgamedev","elo":1090,"win_rate":46.8,"rank":28},{"arena":"agents","category":"htmlslides","elo":1087,"win_rate":52.3,"rank":13},{"arena":"agents","category":"mobileapps","elo":1148,"win_rate":47.6,"rank":36},{"arena":"agents","category":"pptxslides","elo":1181,"win_rate":44.3,"rank":4},{"arena":"agents","category":"python-pptxslides","elo":1180,"win_rate":42.1,"rank":14},{"arena":"agents","category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},{"arena":"agents","category":"webapps","elo":1268,"win_rate":59.3,"rank":10},{"arena":"models","category":"3d","elo":1235,"win_rate":57.6,"rank":33},{"arena":"models","category":"asciiart","elo":1142,"win_rate":46.1,"rank":45},{"arena":"models","category":"codecategories","elo":1254,"win_rate":55,"rank":38},{"arena":"models","category":"dataviz","elo":1244,"win_rate":52.1,"rank":40},{"arena":"models","category":"gamedev","elo":1222,"win_rate":54.8,"rank":45},{"arena":"models","category":"svg","elo":1165,"win_rate":51.2,"rank":44},{"arena":"models","category":"uicomponent","elo":1251,"win_rate":55.8,"rank":43},{"arena":"models","category":"website","elo":1259,"win_rate":54.6,"rank":35}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"anthropic/claude-opus-4.7","canonical_slug":"anthropic/claude-4.7-opus-20260416","hugging_face_id":null,"name":"Anthropic: Claude Opus 4.7","created":1776351100,"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...","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","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"mistralai/mistral-small-2603","canonical_slug":"mistralai/mistral-small-2603","hugging_face_id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral: Mistral Small 4","created":1773695685,"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...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","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/mistralai/mistral-small-2603/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":4.3,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":11.6,"strategy_and_ops_index":6.8,"legal_index":11.6,"healthcare_and_medical_index":8.8,"engineering_index":13.3,"economics_index":11.7,"cyber_index":null,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"openai/gpt-5.4","canonical_slug":"openai/gpt-5.4-20260305","hugging_face_id":"","name":"OpenAI: GPT-5.4","created":1772734352,"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...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.000015","web_search":"0.01","input_cache_read":"0.00000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000005","completion":"0.0000225","input_cache_read":"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":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-20260305/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1068,"win_rate":42.3,"rank":100},{"arena":"models","category":"asciiart","elo":1184,"win_rate":55.4,"rank":30},{"arena":"models","category":"codecategories","elo":1194,"win_rate":52.5,"rank":67},{"arena":"models","category":"dataviz","elo":1229,"win_rate":56.6,"rank":46},{"arena":"models","category":"gamedev","elo":1211,"win_rate":57.6,"rank":47},{"arena":"models","category":"svg","elo":1179,"win_rate":57.8,"rank":38},{"arena":"models","category":"uicomponent","elo":1223,"win_rate":57.4,"rank":52},{"arena":"models","category":"website","elo":1207,"win_rate":52.5,"rank":69},{"arena":"agents","category":"androidnative","elo":1020,"win_rate":47.7,"rank":42},{"arena":"agents","category":"fullstack","elo":995,"win_rate":40.9,"rank":44},{"arena":"agents","category":"godotgamedev","elo":1135,"win_rate":46.9,"rank":23},{"arena":"agents","category":"mobileapps","elo":1079,"win_rate":46.1,"rank":51},{"arena":"agents","category":"webapps","elo":1027,"win_rate":40.3,"rank":44}]},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1118,"win_rate":51.1,"rank":17},{"arena":"agents","category":"androidnative","elo":1181,"win_rate":61.8,"rank":17},{"arena":"agents","category":"fullstack","elo":1190,"win_rate":64.3,"rank":19},{"arena":"agents","category":"godotgamedev","elo":1226,"win_rate":60.6,"rank":7},{"arena":"agents","category":"mobileapps","elo":1204,"win_rate":63.6,"rank":22},{"arena":"agents","category":"webapps","elo":1157,"win_rate":56.9,"rank":30},{"arena":"models","category":"3d","elo":1201,"win_rate":57.5,"rank":49},{"arena":"models","category":"asciiart","elo":1221,"win_rate":60.1,"rank":23},{"arena":"models","category":"codecategories","elo":1258,"win_rate":59.4,"rank":33},{"arena":"models","category":"dataviz","elo":1272,"win_rate":58.3,"rank":26},{"arena":"models","category":"gamedev","elo":1231,"win_rate":58.8,"rank":43},{"arena":"models","category":"svg","elo":1180,"win_rate":58.7,"rank":35},{"arena":"models","category":"uicomponent","elo":1255,"win_rate":58.3,"rank":42},{"arena":"models","category":"website","elo":1272,"win_rate":60,"rank":27}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":null,"multilingual_index":0.905,"decision_index":null}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"}},{"id":"anthropic/claude-opus-4.6","canonical_slug":"anthropic/claude-4.6-opus-20260205","hugging_face_id":"","name":"Anthropic: Claude Opus 4.6","created":1770219050,"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...","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","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-opus-20260205/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1144,"win_rate":45.5,"rank":11},{"arena":"agents","category":"androidnative","elo":1179,"win_rate":61.1,"rank":18},{"arena":"agents","category":"blender3d","elo":937,"win_rate":32.9,"rank":23},{"arena":"agents","category":"codetovideo","elo":1116,"win_rate":43.1,"rank":22},{"arena":"agents","category":"fullstack","elo":1197,"win_rate":59,"rank":18},{"arena":"agents","category":"mobileapps","elo":1198,"win_rate":56.9,"rank":24},{"arena":"agents","category":"pdf","elo":1191,"win_rate":52.5,"rank":23},{"arena":"agents","category":"spreadsheet","elo":983,"win_rate":22.1,"rank":30},{"arena":"agents","category":"webapps","elo":1173,"win_rate":55.5,"rank":26},{"arena":"models","category":"3d","elo":1241,"win_rate":62.5,"rank":28},{"arena":"models","category":"asciiart","elo":1240,"win_rate":61.9,"rank":19},{"arena":"models","category":"codecategories","elo":1271,"win_rate":61.2,"rank":28},{"arena":"models","category":"dataviz","elo":1274,"win_rate":58.7,"rank":24},{"arena":"models","category":"gamedev","elo":1250,"win_rate":61,"rank":30},{"arena":"models","category":"svg","elo":1211,"win_rate":60.9,"rank":27},{"arena":"models","category":"uicomponent","elo":1267,"win_rate":59.8,"rank":33},{"arena":"models","category":"website","elo":1278,"win_rate":61.1,"rank":25}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":null,"multilingual_index":0.922,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":false,"supports_max_tokens":true,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high"}},{"id":"mistralai/devstral-2512","canonical_slug":"mistralai/devstral-2512","hugging_face_id":"mistralai/Devstral-2-123B-Instruct-2512","name":"Mistral: Devstral 2 2512","created":1765285419,"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. Devstral 2 supports exploring...","context_length":262144,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/devstral-2512/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":27.8,"multilingual_index":0.775,"decision_index":null}}},{"id":"amazon/nova-2-lite-v1","canonical_slug":"amazon/nova-2-lite-v1","hugging_face_id":"","name":"Amazon: Nova 2 Lite","created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","context_length":1000000,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/amazon/nova-2-lite-v1/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false}},{"id":"mistralai/ministral-14b-2512","canonical_slug":"mistralai/ministral-14b-2512","hugging_face_id":"mistralai/Ministral-3-14B-Instruct-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"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...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-14b-2512/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":957,"win_rate":39.6,"rank":126},{"arena":"models","category":"codecategories","elo":1047,"win_rate":44,"rank":125},{"arena":"models","category":"gamedev","elo":1010,"win_rate":43.6,"rank":126},{"arena":"models","category":"website","elo":1068,"win_rate":44.8,"rank":123}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":38.9,"multilingual_index":0.683,"decision_index":null}}},{"id":"mistralai/ministral-8b-2512","canonical_slug":"mistralai/ministral-8b-2512","hugging_face_id":"mistralai/Ministral-3-8B-Instruct-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-8b-2512/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":999,"win_rate":46.2,"rank":121},{"arena":"models","category":"codecategories","elo":1035,"win_rate":42.9,"rank":126},{"arena":"models","category":"gamedev","elo":962,"win_rate":38.7,"rank":132},{"arena":"models","category":"website","elo":1052,"win_rate":42.9,"rank":127}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":38.9,"multilingual_index":0.663,"decision_index":null}}},{"id":"mistralai/ministral-3b-2512","canonical_slug":"mistralai/ministral-3b-2512","hugging_face_id":"mistralai/Ministral-3-3B-Instruct-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/ministral-3b-2512/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":930,"win_rate":35.9,"rank":131},{"arena":"models","category":"codecategories","elo":992,"win_rate":37.3,"rank":133},{"arena":"models","category":"gamedev","elo":920,"win_rate":33,"rank":141},{"arena":"models","category":"website","elo":1015,"win_rate":38.2,"rank":136}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":38.9,"multilingual_index":0.567,"decision_index":null}}},{"id":"mistralai/mistral-large-2512","canonical_slug":"mistralai/mistral-large-2512","hugging_face_id":"mistralai/Mistral-Large-3-675B-Instruct-2512","name":"Mistral: Mistral Large 3 2512","created":1764624472,"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.","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.0645,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-2512/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1066,"win_rate":46.9,"rank":101},{"arena":"models","category":"asciiart","elo":1054,"win_rate":40.3,"rank":73},{"arena":"models","category":"codecategories","elo":1124,"win_rate":47.6,"rank":100},{"arena":"models","category":"dataviz","elo":1131,"win_rate":45.7,"rank":91},{"arena":"models","category":"gamedev","elo":1052,"win_rate":41.5,"rank":114},{"arena":"models","category":"svg","elo":977,"win_rate":38,"rank":96},{"arena":"models","category":"uicomponent","elo":1085,"win_rate":43,"rank":106},{"arena":"models","category":"website","elo":1150,"win_rate":49.5,"rank":97}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":38.9,"multilingual_index":0.803,"decision_index":null}}},{"id":"anthropic/claude-opus-4.5","canonical_slug":"anthropic/claude-4.5-opus-20251124","hugging_face_id":"","name":"Anthropic: Claude Opus 4.5","created":1764010580,"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...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"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":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","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1181,"win_rate":58.5,"rank":55},{"arena":"models","category":"asciiart","elo":1175,"win_rate":54.8,"rank":33},{"arena":"models","category":"codecategories","elo":1224,"win_rate":59.5,"rank":54},{"arena":"models","category":"dataviz","elo":1237,"win_rate":58.5,"rank":41},{"arena":"models","category":"gamedev","elo":1201,"win_rate":59.3,"rank":52},{"arena":"models","category":"svg","elo":1165,"win_rate":58.7,"rank":43},{"arena":"models","category":"uicomponent","elo":1222,"win_rate":58.1,"rank":53},{"arena":"models","category":"website","elo":1234,"win_rate":59.7,"rank":54},{"arena":"agents","category":"androidnative","elo":1160,"win_rate":65.5,"rank":25},{"arena":"agents","category":"fullstack","elo":1134,"win_rate":60.1,"rank":29},{"arena":"agents","category":"mobileapps","elo":1181,"win_rate":60.7,"rank":28},{"arena":"agents","category":"webapps","elo":1127,"win_rate":55.1,"rank":33}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":11.1,"multilingual_index":0.913,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"openai/gpt-5.1","canonical_slug":"openai/gpt-5.1-20251113","hugging_face_id":"","name":"OpenAI: GPT-5.1","created":1763060305,"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...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125"},"top_provider":{"context_length":400000,"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-5.1-20251113/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1028,"win_rate":43.7,"rank":117},{"arena":"models","category":"asciiart","elo":1104,"win_rate":48.6,"rank":62},{"arena":"models","category":"codecategories","elo":1152,"win_rate":53,"rank":84},{"arena":"models","category":"dataviz","elo":1199,"win_rate":58,"rank":62},{"arena":"models","category":"gamedev","elo":1150,"win_rate":55.8,"rank":72},{"arena":"models","category":"svg","elo":1133,"win_rate":57.4,"rank":57},{"arena":"models","category":"uicomponent","elo":1150,"win_rate":52.9,"rank":82},{"arena":"models","category":"website","elo":1174,"win_rate":54,"rank":82}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":5.6,"multilingual_index":0.906,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"mistralai/voxtral-small-24b-2507","canonical_slug":"mistralai/voxtral-small-24b-2507","hugging_face_id":"mistralai/Voxtral-Small-24B-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"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...","context_length":32768,"architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000003","audio":"0.0001","input_cache_read":"0.00000001"},"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.2,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1039,"win_rate":41,"rank":114},{"arena":"models","category":"asciiart","elo":1125,"win_rate":49.3,"rank":56},{"arena":"models","category":"codecategories","elo":1096,"win_rate":44.9,"rank":111},{"arena":"models","category":"dataviz","elo":1119,"win_rate":45.7,"rank":98},{"arena":"models","category":"gamedev","elo":1069,"win_rate":44.7,"rank":105},{"arena":"models","category":"svg","elo":1009,"win_rate":39.1,"rank":91},{"arena":"models","category":"uicomponent","elo":1083,"win_rate":42.6,"rank":107},{"arena":"models","category":"website","elo":1110,"win_rate":45.1,"rank":110}],"artificial_analysis":{"intelligence_index":7.4,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":19.4,"strategy_and_ops_index":11.2,"legal_index":18,"healthcare_and_medical_index":12.1,"engineering_index":17,"economics_index":19.1,"cyber_index":null,"openness_index":11.1,"multilingual_index":0.834,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"anthropic/claude-sonnet-4.5","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","hugging_face_id":"","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"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...","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","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"}]},"top_provider":{"context_length":1000000,"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":1,"top_p":1,"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/anthropic/claude-4.5-sonnet-20250929/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1124,"win_rate":51,"rank":81},{"arena":"models","category":"asciiart","elo":1190,"win_rate":56.1,"rank":28},{"arena":"models","category":"codecategories","elo":1164,"win_rate":51.5,"rank":74},{"arena":"models","category":"dataviz","elo":1161,"win_rate":47.4,"rank":77},{"arena":"models","category":"gamedev","elo":1138,"win_rate":51.1,"rank":78},{"arena":"models","category":"svg","elo":1099,"win_rate":52.2,"rank":67},{"arena":"models","category":"uicomponent","elo":1156,"win_rate":49.4,"rank":79},{"arena":"models","category":"website","elo":1177,"win_rate":51.8,"rank":78},{"arena":"agents","category":"fullstack","elo":1028,"win_rate":43.7,"rank":40},{"arena":"agents","category":"mobileapps","elo":1130,"win_rate":53,"rank":40},{"arena":"agents","category":"webapps","elo":1027,"win_rate":43.2,"rank":43}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":11.1,"multilingual_index":0.893,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"mistralai/mistral-medium-3.1","canonical_slug":"mistralai/mistral-medium-3.1","hugging_face_id":"","name":"Mistral: Mistral Medium 3.1","created":1755095639,"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...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3.1/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1048,"win_rate":44.6,"rank":109},{"arena":"models","category":"asciiart","elo":983,"win_rate":30.8,"rank":76},{"arena":"models","category":"codecategories","elo":1102,"win_rate":45.1,"rank":108},{"arena":"models","category":"dataviz","elo":1138,"win_rate":47.2,"rank":88},{"arena":"models","category":"gamedev","elo":1046,"win_rate":40.8,"rank":118},{"arena":"models","category":"svg","elo":976,"win_rate":38.2,"rank":97},{"arena":"models","category":"uicomponent","elo":1083,"win_rate":43.6,"rank":108},{"arena":"models","category":"website","elo":1120,"win_rate":46,"rank":108}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":11.1,"multilingual_index":null,"decision_index":null}}},{"id":"openai/gpt-5","canonical_slug":"openai/gpt-5-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5","created":1754587413,"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...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","web_search":"0.01","input_cache_read":"0.000000125"},"top_provider":{"context_length":400000,"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":"2024-09-30","expiration_date":"2026-12-11","links":{"details":"/api/v1/models/openai/gpt-5-2025-08-07/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1023,"win_rate":41.3,"rank":118},{"arena":"models","category":"asciiart","elo":1126,"win_rate":49,"rank":55},{"arena":"models","category":"codecategories","elo":1150,"win_rate":54.5,"rank":86},{"arena":"models","category":"dataviz","elo":1216,"win_rate":60.5,"rank":54},{"arena":"models","category":"gamedev","elo":1157,"win_rate":59.3,"rank":70},{"arena":"models","category":"svg","elo":1172,"win_rate":64.1,"rank":42},{"arena":"models","category":"uicomponent","elo":1163,"win_rate":57.4,"rank":76},{"arena":"models","category":"website","elo":1172,"win_rate":53.7,"rank":83}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":5.6,"multilingual_index":0.907,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"openai/gpt-5-mini","canonical_slug":"openai/gpt-5-mini-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5 Mini","created":1754587407,"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....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000002","web_search":"0.01","input_cache_read":"0.000000025"},"top_provider":{"context_length":400000,"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":"2024-05-31","expiration_date":"2026-12-11","links":{"details":"/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1004,"win_rate":36.9,"rank":120},{"arena":"models","category":"asciiart","elo":1110,"win_rate":44.8,"rank":60},{"arena":"models","category":"codecategories","elo":1097,"win_rate":43.5,"rank":110},{"arena":"models","category":"dataviz","elo":1125,"win_rate":43.7,"rank":95},{"arena":"models","category":"gamedev","elo":1101,"win_rate":46.5,"rank":97},{"arena":"models","category":"svg","elo":1075,"win_rate":45.8,"rank":75},{"arena":"models","category":"uicomponent","elo":1089,"win_rate":41.9,"rank":104},{"arena":"models","category":"website","elo":1112,"win_rate":44.3,"rank":109}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":5.6,"multilingual_index":0.874,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"openai/gpt-5-nano","canonical_slug":"openai/gpt-5-nano-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5 Nano","created":1754587402,"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...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.000000005"},"top_provider":{"context_length":400000,"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":"2024-05-31","expiration_date":"2026-12-11","links":{"details":"/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":933,"win_rate":36.3,"rank":130},{"arena":"models","category":"codecategories","elo":1066,"win_rate":48,"rank":118},{"arena":"models","category":"dataviz","elo":1050,"win_rate":46.2,"rank":115},{"arena":"models","category":"gamedev","elo":1017,"win_rate":46.5,"rank":124},{"arena":"models","category":"uicomponent","elo":1050,"win_rate":51.9,"rank":116},{"arena":"models","category":"website","elo":1089,"win_rate":48.9,"rank":119}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":5.6,"multilingual_index":0.812,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"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":"0.00000009","completion":"0.00000036"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":869,"win_rate":29.4,"rank":133},{"arena":"models","category":"codecategories","elo":945,"win_rate":33.4,"rank":141},{"arena":"models","category":"dataviz","elo":982,"win_rate":43.6,"rank":125},{"arena":"models","category":"gamedev","elo":964,"win_rate":40.5,"rank":131},{"arena":"models","category":"uicomponent","elo":910,"win_rate":35.7,"rank":137},{"arena":"models","category":"website","elo":955,"win_rate":32.5,"rank":144}],"artificial_analysis":{"intelligence_index":3.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":7.8,"strategy_and_ops_index":5.5,"legal_index":8.1,"healthcare_and_medical_index":5.8,"engineering_index":11.2,"economics_index":9,"cyber_index":null,"openness_index":38.9,"multilingual_index":0.828,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-oss-20b","canonical_slug":"openai/gpt-oss-20b","hugging_face_id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"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...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.00000003"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"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":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-20b/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":933,"win_rate":39.7,"rank":130},{"arena":"models","category":"website","elo":840,"win_rate":27.9,"rank":151}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":38.9,"multilingual_index":0.752,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"mistralai/codestral-2508","canonical_slug":"mistralai/codestral-2508","hugging_face_id":"","name":"Mistral: Codestral 2508","created":1754079630,"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)","context_length":256000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003"},"top_provider":{"context_length":256000,"max_completion_tokens":204800,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/codestral-2508/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":989,"win_rate":38.5,"rank":134},{"arena":"models","category":"dataviz","elo":1012,"win_rate":41.1,"rank":120},{"arena":"models","category":"gamedev","elo":939,"win_rate":36.3,"rank":137},{"arena":"models","category":"uicomponent","elo":1001,"win_rate":46.7,"rank":125},{"arena":"models","category":"website","elo":1000,"win_rate":37.8,"rank":138},{"arena":"models","category":"3d","elo":987,"win_rate":45.4,"rank":122}]}},{"id":"mistralai/mistral-medium-3","canonical_slug":"mistralai/mistral-medium-3","hugging_face_id":"","name":"Mistral: Mistral Medium 3","created":1746627341,"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...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000044","completion":"0.0000022","input_cache_read":"0.000000044"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1051,"win_rate":54.7,"rank":107},{"arena":"models","category":"codecategories","elo":1051,"win_rate":48.1,"rank":123},{"arena":"models","category":"dataviz","elo":1029,"win_rate":46,"rank":118},{"arena":"models","category":"gamedev","elo":990,"win_rate":45.2,"rank":129},{"arena":"models","category":"uicomponent","elo":1008,"win_rate":49.6,"rank":124},{"arena":"models","category":"website","elo":1066,"win_rate":47.6,"rank":124}]}},{"id":"openai/gpt-4.1","canonical_slug":"openai/gpt-4.1-2025-04-14","hugging_face_id":"","name":"OpenAI: GPT-4.1","created":1744651385,"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...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":817,"win_rate":30.9,"rank":138},{"arena":"models","category":"codecategories","elo":1007,"win_rate":50.9,"rank":131},{"arena":"models","category":"dataviz","elo":1104,"win_rate":59.5,"rank":102},{"arena":"models","category":"gamedev","elo":1051,"win_rate":59.1,"rank":115},{"arena":"models","category":"uicomponent","elo":984,"win_rate":49.7,"rank":127},{"arena":"models","category":"website","elo":1026,"win_rate":52.3,"rank":132}]}},{"id":"openai/gpt-4.1-mini","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","hugging_face_id":"","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"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...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.0000016","web_search":"0.01","input_cache_read":"0.0000001"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":804,"win_rate":30.5,"rank":139},{"arena":"models","category":"codecategories","elo":975,"win_rate":47.5,"rank":139},{"arena":"models","category":"dataviz","elo":1034,"win_rate":49.2,"rank":117},{"arena":"models","category":"gamedev","elo":1043,"win_rate":58.5,"rank":119},{"arena":"models","category":"uicomponent","elo":945,"win_rate":45.4,"rank":131},{"arena":"models","category":"website","elo":985,"win_rate":47.8,"rank":139}]}},{"id":"openai/gpt-4.1-nano","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","hugging_face_id":"","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"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...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","web_search":"0.01","input_cache_read":"0.00000003"},"top_provider":{"context_length":1047576,"max_completion_tokens":942818,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":892,"win_rate":46,"rank":132},{"arena":"models","category":"codecategories","elo":944,"win_rate":47.3,"rank":142},{"arena":"models","category":"dataviz","elo":885,"win_rate":41.1,"rank":135},{"arena":"models","category":"gamedev","elo":942,"win_rate":49.6,"rank":136},{"arena":"models","category":"uicomponent","elo":899,"win_rate":43.9,"rank":138},{"arena":"models","category":"website","elo":960,"win_rate":48.1,"rank":143}]}},{"id":"mistralai/mistral-saba","canonical_slug":"mistralai/mistral-saba-2502","hugging_face_id":"","name":"Mistral: Saba","created":1739803239,"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...","context_length":32768,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000006","input_cache_read":"0.00000002"},"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-09-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-saba-2502/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"amazon/nova-lite-v1","canonical_slug":"amazon/nova-lite-v1","hugging_face_id":"","name":"Amazon: Nova Lite 1.0","created":1733437363,"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...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.00000024"},"top_provider":{"context_length":300000,"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-lite-v1/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":11.1,"multilingual_index":null,"decision_index":null}}},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":11.1,"multilingual_index":null,"decision_index":null}}},{"id":"amazon/nova-pro-v1","canonical_slug":"amazon/nova-pro-v1","hugging_face_id":"","name":"Amazon: Nova Pro 1.0","created":1733436303,"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...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":"0.0000008","completion":"0.0000032"},"top_provider":{"context_length":300000,"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-pro-v1/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":11.1,"multilingual_index":null,"decision_index":null}}},{"id":"mistralai/mistral-large-2407","canonical_slug":"mistralai/mistral-large-2407","hugging_face_id":"mistralai/Mistral-Large-Instruct-2407","name":"Mistral Large 2407","created":1731978415,"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/)....","context_length":131072,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002"},"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-03-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-2407/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"mistralai/mistral-nemo","canonical_slug":"mistralai/mistral-nemo","hugging_face_id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral: Mistral Nemo","created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000000029","completion":"0.00000003"},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-nemo/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"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"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"mistralai/mixtral-8x22b-instruct","canonical_slug":"mistralai/mixtral-8x22b-instruct","hugging_face_id":"mistralai/Mixtral-8x22B-Instruct-v0.1","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"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: - strong math, coding,...","context_length":65536,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002"},"top_provider":{"context_length":65536,"max_completion_tokens":52428,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-01-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"mistralai/mistral-large","canonical_slug":"mistralai/mistral-large","hugging_face_id":null,"name":"Mistral Large","created":1708905600,"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/)....","context_length":128000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002"},"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2024-11-30","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-large/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]}],"total_count":75,"links":{"next":null}}