{"data":[{"id":"mistralai/pixtral-large-2502","canonical_slug":"mistralai/pixtral-large-2502","hugging_face_id":null,"name":"Mistral: Pixtral Large 2502","created":1795135865,"description":"Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following [Pixtral Large 2411](https://openrouter.ai/mistralai/pixtral-large-2411). It accepts text and image input, including documents, charts, and natural images,...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/pixtral-large-2502/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"qwen/qwen4-max","canonical_slug":"qwen/qwen4-max-20261115","hugging_face_id":null,"name":"Qwen: Qwen4 Max","created":1794795526,"description":"Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000001425","completion":"0.000004275","input_cache_read":"0.00000007125","input_cache_write":"0.00000178125"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"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_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen4-max-20261115/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":42.9,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":54.1,"strategy_and_ops_index":56.9,"legal_index":49.6,"healthcare_and_medical_index":48.2,"engineering_index":50.1,"economics_index":51.3,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","low","none"],"default_effort":"high"}},{"id":"moonshotai/kimi-k3.1-pro","canonical_slug":"moonshotai/kimi-k3.1-pro-20261023","hugging_face_id":"moonshotai/Kimi-K3.1-Pro","name":"MoonshotAI: Kimi K3.1 Pro","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000002403","completion":"0.0000084023","input_cache_read":"0.0000002"},"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":{"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3.1-pro-20261023/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1165,"win_rate":45.1,"rank":24},{"arena":"agents","category":"codetovideo","elo":1242,"win_rate":59.6,"rank":10},{"arena":"agents","category":"fullstack","elo":1323,"win_rate":61.5,"rank":4},{"arena":"agents","category":"mobileapps","elo":1269,"win_rate":59.5,"rank":6},{"arena":"agents","category":"pdf","elo":1229,"win_rate":57.4,"rank":13},{"arena":"agents","category":"python-pptxslides","elo":1287,"win_rate":60.5,"rank":3},{"arena":"agents","category":"spreadsheet","elo":1315,"win_rate":62.9,"rank":5},{"arena":"agents","category":"webapps","elo":1293,"win_rate":60.3,"rank":3},{"arena":"models","category":"3d","elo":1422,"win_rate":68.6,"rank":4},{"arena":"models","category":"asciiart","elo":1302,"win_rate":57.9,"rank":9},{"arena":"models","category":"codecategories","elo":1341,"win_rate":59.7,"rank":10},{"arena":"models","category":"dataviz","elo":1298,"win_rate":55.8,"rank":15},{"arena":"models","category":"gamedev","elo":1380,"win_rate":62.6,"rank":8},{"arena":"models","category":"svg","elo":1318,"win_rate":61.6,"rank":4},{"arena":"models","category":"uicomponent","elo":1374,"win_rate":63.7,"rank":3},{"arena":"models","category":"website","elo":1314,"win_rate":57.3,"rank":9}],"artificial_analysis":{"intelligence_index":46.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":53.3,"strategy_and_ops_index":57.6,"legal_index":49.2,"healthcare_and_medical_index":51.6,"engineering_index":50.9,"economics_index":49.9,"cyber_index":64.1,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"moonshotai/kimi-k3.1-pro:batch","canonical_slug":"moonshotai/kimi-k3.1-pro-20261023","hugging_face_id":"moonshotai/Kimi-K3.1-Pro","name":"MoonshotAI: Kimi K3.1 Pro (batch)","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000372","completion":"0.000005583","input_cache_read":"0.0000001"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3.1-pro-20261023/endpoints"},"endpoints":["/api/v1/batches"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1165,"win_rate":45.1,"rank":24},{"arena":"agents","category":"codetovideo","elo":1242,"win_rate":59.6,"rank":10},{"arena":"agents","category":"fullstack","elo":1323,"win_rate":61.5,"rank":4},{"arena":"agents","category":"mobileapps","elo":1269,"win_rate":59.5,"rank":6},{"arena":"agents","category":"pdf","elo":1229,"win_rate":57.4,"rank":13},{"arena":"agents","category":"python-pptxslides","elo":1287,"win_rate":60.5,"rank":3},{"arena":"agents","category":"spreadsheet","elo":1315,"win_rate":62.9,"rank":5},{"arena":"agents","category":"webapps","elo":1293,"win_rate":60.3,"rank":3},{"arena":"models","category":"3d","elo":1422,"win_rate":68.6,"rank":4},{"arena":"models","category":"asciiart","elo":1302,"win_rate":57.9,"rank":9},{"arena":"models","category":"codecategories","elo":1341,"win_rate":59.7,"rank":10},{"arena":"models","category":"dataviz","elo":1298,"win_rate":55.8,"rank":15},{"arena":"models","category":"gamedev","elo":1380,"win_rate":62.6,"rank":8},{"arena":"models","category":"svg","elo":1318,"win_rate":61.6,"rank":4},{"arena":"models","category":"uicomponent","elo":1374,"win_rate":63.7,"rank":3},{"arena":"models","category":"website","elo":1314,"win_rate":57.3,"rank":9}],"artificial_analysis":{"intelligence_index":46.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":53.3,"strategy_and_ops_index":57.6,"legal_index":49.2,"healthcare_and_medical_index":51.6,"engineering_index":50.9,"economics_index":49.9,"cyber_index":64.1,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"deepseek/deepseek-v4.1-flash-1017","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003","overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":0,"utc_end":100,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":100,"utc_end":400,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":400,"utc_end":600,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":600,"utc_end":1000,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":1000,"utc_end":0,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"spreadsheet","elo":1263,"win_rate":47.8,"rank":9},{"arena":"models","category":"3d","elo":1331,"win_rate":47.9,"rank":16},{"arena":"models","category":"asciiart","elo":1221,"win_rate":48,"rank":24},{"arena":"models","category":"codecategories","elo":1281,"win_rate":48.5,"rank":22},{"arena":"models","category":"dataviz","elo":1273,"win_rate":52.2,"rank":25},{"arena":"models","category":"gamedev","elo":1239,"win_rate":43.4,"rank":35},{"arena":"models","category":"svg","elo":1236,"win_rate":50.8,"rank":22},{"arena":"models","category":"uicomponent","elo":1272,"win_rate":47.8,"rank":31},{"arena":"models","category":"website","elo":1289,"win_rate":51.6,"rank":21}],"artificial_analysis":{"intelligence_index":32.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":42.2,"strategy_and_ops_index":49.2,"legal_index":37.7,"healthcare_and_medical_index":41.3,"engineering_index":37.6,"economics_index":38.5,"cyber_index":56.8,"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":"deepseek/deepseek-v4.1-flash-1017:batch","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017 (batch)","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000035","completion":"0.000000149","input_cache_read":"0.0000000029"},"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":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints"},"endpoints":["/api/v1/batches"],"benchmarks":{"design_arena":[{"arena":"agents","category":"spreadsheet","elo":1263,"win_rate":47.8,"rank":9},{"arena":"models","category":"3d","elo":1331,"win_rate":47.9,"rank":16},{"arena":"models","category":"asciiart","elo":1221,"win_rate":48,"rank":24},{"arena":"models","category":"codecategories","elo":1281,"win_rate":48.5,"rank":22},{"arena":"models","category":"dataviz","elo":1273,"win_rate":52.2,"rank":25},{"arena":"models","category":"gamedev","elo":1239,"win_rate":43.4,"rank":35},{"arena":"models","category":"svg","elo":1236,"win_rate":50.8,"rank":22},{"arena":"models","category":"uicomponent","elo":1272,"win_rate":47.8,"rank":31},{"arena":"models","category":"website","elo":1289,"win_rate":51.6,"rank":21}],"artificial_analysis":{"intelligence_index":32.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":42.2,"strategy_and_ops_index":49.2,"legal_index":37.7,"healthcare_and_medical_index":41.3,"engineering_index":37.6,"economics_index":38.5,"cyber_index":56.8,"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":"nvidia/nemotron-3.5-super-vl","canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","name":"NVIDIA: Nemotron 3.5 Super VL","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.00000002"},"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","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-super-vl-20261015/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1048,"win_rate":31.4,"rank":44},{"arena":"models","category":"3d","elo":1101,"win_rate":29.2,"rank":89},{"arena":"models","category":"codecategories","elo":1131,"win_rate":32,"rank":97},{"arena":"models","category":"dataviz","elo":1088,"win_rate":26.9,"rank":108},{"arena":"models","category":"gamedev","elo":1066,"win_rate":27.2,"rank":110},{"arena":"models","category":"uicomponent","elo":1146,"win_rate":32,"rank":87},{"arena":"models","category":"website","elo":1152,"win_rate":34.4,"rank":95}],"artificial_analysis":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":26.7,"strategy_and_ops_index":21.8,"legal_index":25.3,"healthcare_and_medical_index":21,"engineering_index":23.5,"economics_index":26.1,"cyber_index":null,"openness_index":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"nvidia/nemotron-3.5-super-vl:free","canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","name":"NVIDIA: Nemotron 3.5 Super VL (free)","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-super-vl-20261015/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1048,"win_rate":31.4,"rank":44},{"arena":"models","category":"3d","elo":1101,"win_rate":29.2,"rank":89},{"arena":"models","category":"codecategories","elo":1131,"win_rate":32,"rank":97},{"arena":"models","category":"dataviz","elo":1088,"win_rate":26.9,"rank":108},{"arena":"models","category":"gamedev","elo":1066,"win_rate":27.2,"rank":110},{"arena":"models","category":"uicomponent","elo":1146,"win_rate":32,"rank":87},{"arena":"models","category":"website","elo":1152,"win_rate":34.4,"rank":95}],"artificial_analysis":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":26.7,"strategy_and_ops_index":21.8,"legal_index":25.3,"healthcare_and_medical_index":21,"engineering_index":23.5,"economics_index":26.1,"cyber_index":null,"openness_index":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false}},{"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":"qwen/qwen3.8-max-prime","canonical_slug":"qwen/qwen3.8-max-prime-20260923","hugging_face_id":null,"name":"Qwen: Qwen3.8 Max Prime","created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.0000005"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"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_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-max-prime-20260923/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"}},{"id":"qwen/qwen3.8-omni-flash","canonical_slug":"qwen/qwen3.8-omni-flash-20260918","hugging_face_id":null,"name":"Qwen: Qwen3.8 Omni Flash","created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","audio","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-omni-flash-20260918/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"~deepseek/deepseek-pro-latest","canonical_slug":"~deepseek/deepseek-pro-latest","alias_target":{"name":"DeepSeek: DeepSeek V4 Pro 0813","slug":"deepseek/deepseek-v4-pro-0813"},"hugging_face_id":null,"name":"DeepSeek: DeepSeek Pro Latest","created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.0000000999","completion":"0.000005","input_cache_read":"0.0000000999"},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~deepseek/deepseek-pro-latest/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"~deepseek/deepseek-flash-latest","canonical_slug":"~deepseek/deepseek-flash-latest","alias_target":{"name":"DeepSeek: DeepSeek V4.1 Flash 1017","slug":"deepseek/deepseek-v4.1-flash-1017"},"hugging_face_id":null,"name":"DeepSeek: DeepSeek Flash Latest","created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000000036","completion":"0.0000005","input_cache_read":"0.00000001"},"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_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~deepseek/deepseek-flash-latest/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.0000000498","completion":"0.0000001992","input_cache_read":"0.000000000996"},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints"},"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":40.8,"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":"deepseek/deepseek-v4.1-flash:batch","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.00000015","input_cache_read":"0.000000004"},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints"},"endpoints":["/api/v1/batches"],"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":40.8,"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":"qwen/qwen3.8-max-0902","canonical_slug":"qwen/qwen3.8-max-20260902","hugging_face_id":null,"name":"Qwen: Qwen3.8 Max (0902)","created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"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_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-max-20260902/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":33.7,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":45,"strategy_and_ops_index":47.3,"legal_index":41,"healthcare_and_medical_index":40.8,"engineering_index":39.3,"economics_index":42.5,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"}},{"id":"qwen/qwen3.8-max-0902:batch","canonical_slug":"qwen/qwen3.8-max-20260902","hugging_face_id":null,"name":"Qwen: Qwen3.8 Max (0902) (batch)","created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000115","completion":"0.00000345"},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"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_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-max-20260902/endpoints"},"endpoints":["/api/v1/batches"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":33.7,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":45,"strategy_and_ops_index":47.3,"legal_index":41,"healthcare_and_medical_index":40.8,"engineering_index":39.3,"economics_index":42.5,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"}},{"id":"qwen/qwen3.8-flash","canonical_slug":"qwen/qwen3.8-flash-20260826","hugging_face_id":"Qwen/Qwen3.8-Flash-Next","name":"Qwen: Qwen3.8 Flash","created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-flash-20260826/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":28.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":39,"strategy_and_ops_index":44.5,"legal_index":35.1,"healthcare_and_medical_index":36.4,"engineering_index":33,"economics_index":36.1,"cyber_index":null,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"deepseek/deepseek-v4-flash-vision-exp","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-20260821","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.0000002156","completion":"0.0000006468","input_cache_read":"0.00000000686"},"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-vision-exp-20260821/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"qwen/qwen3.8-27b","canonical_slug":"qwen/qwen3.8-27b-20260814","hugging_face_id":"Qwen/Qwen3.8-27B","name":"Qwen: Qwen3.8 27B","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","context_length":1024000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000000035","completion":"0.0000015","input_cache_read":"0.0000000175"},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-27b-20260814/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":20.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":35.5,"strategy_and_ops_index":39,"legal_index":33.2,"healthcare_and_medical_index":34.6,"engineering_index":28.1,"economics_index":33.7,"cyber_index":12.7,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","low","none"],"default_effort":"xhigh"}},{"id":"qwen/qwen3.8-27b:batch","canonical_slug":"qwen/qwen3.8-27b-20260814","hugging_face_id":"Qwen/Qwen3.8-27B","name":"Qwen: Qwen3.8 27B (batch)","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000016","completion":"0.000002","input_cache_read":"0.00000004"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-27b-20260814/endpoints"},"endpoints":["/api/v1/batches"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":20.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":35.5,"strategy_and_ops_index":39,"legal_index":33.2,"healthcare_and_medical_index":34.6,"engineering_index":28.1,"economics_index":33.7,"cyber_index":12.7,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","low","none"],"default_effort":"xhigh"}},{"id":"qwen/qwen3.8-2.4t-a95b","canonical_slug":"qwen/qwen3.8-2.4t-a95b-20260812","hugging_face_id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","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":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-2.4t-a95b-20260812/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":41.3,"strategy_and_ops_index":44.4,"legal_index":37,"healthcare_and_medical_index":39,"engineering_index":null,"economics_index":37.3,"cyber_index":12.6,"openness_index":27.8,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh"}},{"id":"deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek/deepseek-v4-pro-20260813","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044"},"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":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260813/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":23.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":30.4,"strategy_and_ops_index":41.1,"legal_index":27.5,"healthcare_and_medical_index":null,"engineering_index":29.8,"economics_index":29.3,"cyber_index":null,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"nvidia/nemotron-3.5-lightning","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.0000002","input_cache_read":"0.00000004"},"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","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":5.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":14.9,"strategy_and_ops_index":7.1,"legal_index":14.2,"healthcare_and_medical_index":9,"engineering_index":15.5,"economics_index":14.8,"cyber_index":null,"openness_index":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"nvidia/nemotron-3.5-lightning:free","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"NVIDIA: Nemotron 3.5 Lightning (free)","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":5.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":14.9,"strategy_and_ops_index":7.1,"legal_index":14.2,"healthcare_and_medical_index":9,"engineering_index":15.5,"economics_index":14.8,"cyber_index":null,"openness_index":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"~deepseek/deepseek-v4-flash-latest","canonical_slug":"~deepseek/deepseek-v4-flash-latest","alias_target":{"name":"DeepSeek: DeepSeek V4 Flash 0731","slug":"deepseek/deepseek-v4-flash-0731"},"hugging_face_id":null,"name":"DeepSeek: DeepSeek V4 Flash Latest","created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.000000044","completion":"0.000000132","input_cache_read":"0.0000000014"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/~deepseek/deepseek-v4-flash-latest/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"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":"deepseek/deepseek-v4-flash-0731:batch","canonical_slug":"deepseek/deepseek-v4-flash-20260731","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731 (batch)","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":"0.000000048","completion":"0.000000144","input_cache_read":"0.000000012"},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"endpoints":["/api/v1/batches"],"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":"qwen/qwen3.7-flash","canonical_slug":"qwen/qwen3.7-flash-20260727","hugging_face_id":null,"name":"Qwen: Qwen3.7 Flash","created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.000000006","input_cache_write":"0.000000038","overrides":[{"min_prompt_tokens":32000,"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000002","input_cache_write":"0.000000125"},{"min_prompt_tokens":256000,"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000004","input_cache_write":"0.00000025"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","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/qwen/qwen3.7-flash-20260727/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3-20260715","hugging_face_id":"moonshotai/Kimi-K3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000192","completion":"0.000016","input_cache_read":"0.000000182"},"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":null,"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/moonshotai/kimi-k3-20260715/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1202,"win_rate":54,"rank":4},{"arena":"agents","category":"androidnative","elo":1253,"win_rate":56.9,"rank":7},{"arena":"agents","category":"blender3d","elo":1123,"win_rate":40.4,"rank":9},{"arena":"agents","category":"codetovideo","elo":1273,"win_rate":63,"rank":6},{"arena":"agents","category":"fullstack","elo":1290,"win_rate":60.9,"rank":7},{"arena":"agents","category":"godotgamedev","elo":1193,"win_rate":48.6,"rank":13},{"arena":"agents","category":"htmlslides","elo":1158,"win_rate":55.6,"rank":5},{"arena":"agents","category":"mobileapps","elo":1255,"win_rate":56.5,"rank":9},{"arena":"agents","category":"pdf","elo":1269,"win_rate":65,"rank":6},{"arena":"agents","category":"python-pptxslides","elo":1223,"win_rate":53.9,"rank":9},{"arena":"agents","category":"spreadsheet","elo":1051,"win_rate":27.8,"rank":19},{"arena":"agents","category":"webapps","elo":1264,"win_rate":58,"rank":11},{"arena":"models","category":"3d","elo":1352,"win_rate":63.6,"rank":13},{"arena":"models","category":"asciiart","elo":1352,"win_rate":68.3,"rank":3},{"arena":"models","category":"codecategories","elo":1345,"win_rate":60.4,"rank":8},{"arena":"models","category":"dataviz","elo":1348,"win_rate":63.6,"rank":4},{"arena":"models","category":"gamedev","elo":1340,"win_rate":55.2,"rank":11},{"arena":"models","category":"svg","elo":1291,"win_rate":59.6,"rank":8},{"arena":"models","category":"uicomponent","elo":1339,"win_rate":61.1,"rank":10},{"arena":"models","category":"website","elo":1334,"win_rate":59.6,"rank":5}],"artificial_analysis":{"intelligence_index":17.4,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":28.3,"strategy_and_ops_index":37,"legal_index":27.7,"healthcare_and_medical_index":29.2,"engineering_index":22.8,"economics_index":27.7,"cyber_index":41.3,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"moonshotai/kimi-k3:batch","canonical_slug":"moonshotai/kimi-k3-20260715","hugging_face_id":"moonshotai/Kimi-K3","name":"MoonshotAI: Kimi K3 (batch)","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000228","completion":"0.0000114","input_cache_read":"0.000000228"},"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"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/moonshotai/kimi-k3-20260715/endpoints"},"endpoints":["/api/v1/batches"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1202,"win_rate":54,"rank":4},{"arena":"agents","category":"androidnative","elo":1253,"win_rate":56.9,"rank":7},{"arena":"agents","category":"blender3d","elo":1123,"win_rate":40.4,"rank":9},{"arena":"agents","category":"codetovideo","elo":1273,"win_rate":63,"rank":6},{"arena":"agents","category":"fullstack","elo":1290,"win_rate":60.9,"rank":7},{"arena":"agents","category":"godotgamedev","elo":1193,"win_rate":48.6,"rank":13},{"arena":"agents","category":"htmlslides","elo":1158,"win_rate":55.6,"rank":5},{"arena":"agents","category":"mobileapps","elo":1255,"win_rate":56.5,"rank":9},{"arena":"agents","category":"pdf","elo":1269,"win_rate":65,"rank":6},{"arena":"agents","category":"python-pptxslides","elo":1223,"win_rate":53.9,"rank":9},{"arena":"agents","category":"spreadsheet","elo":1051,"win_rate":27.8,"rank":19},{"arena":"agents","category":"webapps","elo":1264,"win_rate":58,"rank":11},{"arena":"models","category":"3d","elo":1352,"win_rate":63.6,"rank":13},{"arena":"models","category":"asciiart","elo":1352,"win_rate":68.3,"rank":3},{"arena":"models","category":"codecategories","elo":1345,"win_rate":60.4,"rank":8},{"arena":"models","category":"dataviz","elo":1348,"win_rate":63.6,"rank":4},{"arena":"models","category":"gamedev","elo":1340,"win_rate":55.2,"rank":11},{"arena":"models","category":"svg","elo":1291,"win_rate":59.6,"rank":8},{"arena":"models","category":"uicomponent","elo":1339,"win_rate":61.1,"rank":10},{"arena":"models","category":"website","elo":1334,"win_rate":59.6,"rank":5}],"artificial_analysis":{"intelligence_index":17.4,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":28.3,"strategy_and_ops_index":37,"legal_index":27.7,"healthcare_and_medical_index":29.2,"engineering_index":22.8,"economics_index":27.7,"cyber_index":41.3,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"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":"nvidia/nemotron-3.5-content-safety","canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","hugging_face_id":"nvidia/Nemotron-3.5-Content-Safety","name":"NVIDIA: Nemotron 3.5 Content Safety","created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000002"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","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/nvidia/nemotron-3.5-content-safety-20260604/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000022","input_cache_read":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","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/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1060,"win_rate":30.2,"rank":43},{"arena":"models","category":"3d","elo":1096,"win_rate":37.8,"rank":92},{"arena":"models","category":"asciiart","elo":1082,"win_rate":36.3,"rank":68},{"arena":"models","category":"codecategories","elo":1124,"win_rate":35.3,"rank":101},{"arena":"models","category":"dataviz","elo":1134,"win_rate":37.1,"rank":90},{"arena":"models","category":"gamedev","elo":1108,"win_rate":35.3,"rank":92},{"arena":"models","category":"svg","elo":1056,"win_rate":32,"rank":80},{"arena":"models","category":"uicomponent","elo":1120,"win_rate":35.1,"rank":98},{"arena":"models","category":"website","elo":1125,"win_rate":34.3,"rank":106}],"artificial_analysis":{"intelligence_index":11.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":24.2,"strategy_and_ops_index":15.3,"legal_index":22.6,"healthcare_and_medical_index":18,"engineering_index":22.8,"economics_index":24.1,"cyber_index":13.1,"openness_index":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium","none"],"default_effort":"high"}},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra (free)","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","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/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1060,"win_rate":30.2,"rank":43},{"arena":"models","category":"3d","elo":1096,"win_rate":37.8,"rank":92},{"arena":"models","category":"asciiart","elo":1082,"win_rate":36.3,"rank":68},{"arena":"models","category":"codecategories","elo":1124,"win_rate":35.3,"rank":101},{"arena":"models","category":"dataviz","elo":1134,"win_rate":37.1,"rank":90},{"arena":"models","category":"gamedev","elo":1108,"win_rate":35.3,"rank":92},{"arena":"models","category":"svg","elo":1056,"win_rate":32,"rank":80},{"arena":"models","category":"uicomponent","elo":1120,"win_rate":35.1,"rank":98},{"arena":"models","category":"website","elo":1125,"win_rate":34.3,"rank":106}],"artificial_analysis":{"intelligence_index":11.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":24.2,"strategy_and_ops_index":15.3,"legal_index":22.6,"healthcare_and_medical_index":18,"engineering_index":22.8,"economics_index":24.1,"cyber_index":13.1,"openness_index":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium","none"],"default_effort":"high"}},{"id":"qwen/qwen3.7-plus","canonical_slug":"qwen/qwen3.7-plus-20260602","hugging_face_id":null,"name":"Qwen: Qwen3.7 Plus","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000032","completion":"0.00000128","input_cache_read":"0.000000064","input_cache_write":"0.0000004","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000096","completion":"0.00000384","input_cache_read":"0.000000192","input_cache_write":"0.0000012"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1140,"win_rate":43.6,"rank":35},{"arena":"models","category":"3d","elo":1205,"win_rate":47.7,"rank":48},{"arena":"models","category":"asciiart","elo":1134,"win_rate":41.2,"rank":50},{"arena":"models","category":"codecategories","elo":1251,"win_rate":49.8,"rank":40},{"arena":"models","category":"dataviz","elo":1272,"win_rate":51.2,"rank":27},{"arena":"models","category":"gamedev","elo":1232,"win_rate":48.3,"rank":42},{"arena":"models","category":"svg","elo":1193,"win_rate":46.6,"rank":32},{"arena":"models","category":"uicomponent","elo":1247,"win_rate":48.7,"rank":45},{"arena":"models","category":"website","elo":1257,"win_rate":50.3,"rank":37}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen/qwen3.7-plus:batch","canonical_slug":"qwen/qwen3.7-plus-20260602","hugging_face_id":null,"name":"Qwen: Qwen3.7 Plus (batch)","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000023","completion":"0.00000092"},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints"},"endpoints":["/api/v1/batches"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1140,"win_rate":43.6,"rank":35},{"arena":"models","category":"3d","elo":1205,"win_rate":47.7,"rank":48},{"arena":"models","category":"asciiart","elo":1134,"win_rate":41.2,"rank":50},{"arena":"models","category":"codecategories","elo":1251,"win_rate":49.8,"rank":40},{"arena":"models","category":"dataviz","elo":1272,"win_rate":51.2,"rank":27},{"arena":"models","category":"gamedev","elo":1232,"win_rate":48.3,"rank":42},{"arena":"models","category":"svg","elo":1193,"win_rate":46.6,"rank":32},{"arena":"models","category":"uicomponent","elo":1247,"win_rate":48.7,"rank":45},{"arena":"models","category":"website","elo":1257,"win_rate":50.3,"rank":37}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen/qwen3.7-max","canonical_slug":"qwen/qwen3.7-max-20260520","hugging_face_id":null,"name":"Qwen: Qwen3.7 Max","created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.000001475","completion":"0.000004425","input_cache_read":"0.000000295","input_cache_write":"0.00000184375"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","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/qwen/qwen3.7-max-20260520/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1105,"win_rate":45.6,"rank":20},{"arena":"agents","category":"androidnative","elo":1146,"win_rate":47.5,"rank":29},{"arena":"agents","category":"blender3d","elo":980,"win_rate":32.9,"rank":21},{"arena":"agents","category":"fullstack","elo":1171,"win_rate":47.4,"rank":25},{"arena":"agents","category":"godotgamedev","elo":1156,"win_rate":55.5,"rank":17},{"arena":"agents","category":"htmlslides","elo":1059,"win_rate":43.3,"rank":17},{"arena":"agents","category":"mobileapps","elo":1151,"win_rate":44.5,"rank":35},{"arena":"agents","category":"pdf","elo":1158,"win_rate":48.2,"rank":30},{"arena":"agents","category":"python-pptxslides","elo":1151,"win_rate":46.1,"rank":21},{"arena":"agents","category":"spreadsheet","elo":986,"win_rate":35.6,"rank":29},{"arena":"agents","category":"webapps","elo":1176,"win_rate":48.2,"rank":24},{"arena":"models","category":"3d","elo":1231,"win_rate":53.5,"rank":34},{"arena":"models","category":"asciiart","elo":1195,"win_rate":53,"rank":27},{"arena":"models","category":"codecategories","elo":1257,"win_rate":53.7,"rank":35},{"arena":"models","category":"dataviz","elo":1271,"win_rate":53.1,"rank":30},{"arena":"models","category":"gamedev","elo":1235,"win_rate":51.8,"rank":39},{"arena":"models","category":"svg","elo":1200,"win_rate":54.6,"rank":30},{"arena":"models","category":"uicomponent","elo":1257,"win_rate":53.5,"rank":41},{"arena":"models","category":"website","elo":1263,"win_rate":54.6,"rank":33}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"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":"mistralai/mistral-medium-3-5:batch","canonical_slug":"mistralai/mistral-medium-3.5-20260430","hugging_face_id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral: Mistral Medium 3.5 (batch)","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":"0.00000075","completion":"0.00000375"},"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-medium-3.5-20260430/endpoints"},"endpoints":["/api/v1/batches"],"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":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","canonical_slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","hugging_face_id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","name":"NVIDIA: Nemotron 3 Nano Omni (free)","created":1777393095,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...","context_length":256000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.6,"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/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/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":55.6,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"~moonshotai/kimi-latest","canonical_slug":"~moonshotai/kimi-latest","alias_target":{"name":"MoonshotAI: Kimi K3","slug":"moonshotai/kimi-k3"},"hugging_face_id":null,"name":"MoonshotAI: Kimi Latest","created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"0.0000001824","completion":"0.0000110055","input_cache_read":"0.00000018"},"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":null,"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/~moonshotai/kimi-latest/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"qwen/qwen3.5-plus-20260420","canonical_slug":"qwen/qwen3.5-plus-20260420","hugging_face_id":null,"name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000018","input_cache_write":"0.000000375","overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000375","completion":"0.00000225","input_cache_write":"0.00000046875"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.6-flash","canonical_slug":"qwen/qwen3.6-flash","hugging_face_id":null,"name":"Qwen: Qwen3.6 Flash","created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001875","completion":"0.000001125","input_cache_write":"0.000000234375","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000075","completion":"0.000003","input_cache_write":"0.0000009375"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-flash/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.6-35b-a3b","canonical_slug":"qwen/qwen3.6-35b-a3b-20260415","hugging_face_id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000009","input_cache_read":"0.000000025"},"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","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/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":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen/qwen3.6-27b","canonical_slug":"qwen/qwen3.6-27b-20260422","hugging_face_id":"Qwen/Qwen3.6-27B","name":"Qwen: Qwen3.6 27B","created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000032","completion":"0.0000032"},"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":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/qwen/qwen3.6-27b-20260422/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":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.0000009","completion":"0.0000015","input_cache_read":"0.0000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":948,"win_rate":22.1,"rank":48},{"arena":"agents","category":"godotgamedev","elo":1059,"win_rate":34,"rank":32},{"arena":"agents","category":"webapps","elo":1000,"win_rate":26.4,"rank":46},{"arena":"models","category":"3d","elo":1220,"win_rate":56.8,"rank":41},{"arena":"models","category":"asciiart","elo":1134,"win_rate":46.4,"rank":49},{"arena":"models","category":"codecategories","elo":1223,"win_rate":52.2,"rank":55},{"arena":"models","category":"dataviz","elo":1197,"win_rate":48.8,"rank":64},{"arena":"models","category":"gamedev","elo":1204,"win_rate":53,"rank":49},{"arena":"models","category":"svg","elo":1123,"win_rate":45.5,"rank":60},{"arena":"models","category":"uicomponent","elo":1205,"win_rate":50.6,"rank":62},{"arena":"models","category":"website","elo":1222,"win_rate":50.9,"rank":61}],"artificial_analysis":{"intelligence_index":20.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":28,"strategy_and_ops_index":36.6,"legal_index":26.3,"healthcare_and_medical_index":null,"engineering_index":28.7,"economics_index":28.5,"cyber_index":null,"openness_index":50,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000018"},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1156,"win_rate":49.3,"rank":67},{"arena":"models","category":"asciiart","elo":1094,"win_rate":42.7,"rank":64},{"arena":"models","category":"codecategories","elo":1187,"win_rate":49,"rank":69},{"arena":"models","category":"dataviz","elo":1122,"win_rate":40.7,"rank":97},{"arena":"models","category":"gamedev","elo":1169,"win_rate":50.3,"rank":66},{"arena":"models","category":"svg","elo":1139,"win_rate":48.4,"rank":53},{"arena":"models","category":"uicomponent","elo":1148,"win_rate":44.7,"rank":84},{"arena":"models","category":"website","elo":1195,"win_rate":49.1,"rank":70}],"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":50,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"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":"qwen/qwen3.6-plus","canonical_slug":"qwen/qwen3.6-plus-04-02","hugging_face_id":"","name":"Qwen: Qwen3.6 Plus","created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000325","completion":"0.00000195","input_cache_write":"0.00000040625","overrides":[{"min_prompt_tokens":256000,"prompt":"0.0000013","completion":"0.0000039","input_cache_write":"0.000001625"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","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/qwen/qwen3.6-plus-04-02/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1204,"win_rate":52.5,"rank":17},{"arena":"models","category":"3d","elo":1170,"win_rate":50.3,"rank":61},{"arena":"models","category":"asciiart","elo":1098,"win_rate":40.6,"rank":63},{"arena":"models","category":"codecategories","elo":1218,"win_rate":50,"rank":57},{"arena":"models","category":"dataviz","elo":1221,"win_rate":50.6,"rank":50},{"arena":"models","category":"gamedev","elo":1184,"win_rate":48,"rank":59},{"arena":"models","category":"svg","elo":1147,"win_rate":50,"rank":50},{"arena":"models","category":"uicomponent","elo":1215,"win_rate":50.3,"rank":58},{"arena":"models","category":"website","elo":1230,"win_rate":50,"rank":57}]},"reasoning":{"mandatory":false}},{"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":"nvidia/nemotron-3-super-120b-a12b","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.0000004"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","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/nvidia/nemotron-3-super-120b-a12b-20230311/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":83.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["medium","low","none"],"default_effort":"medium"}},{"id":"qwen/qwen3.5-9b","canonical_slug":"qwen/qwen3.5-9b-20260310","hugging_face_id":"Qwen/Qwen3.5-9B","name":"Qwen: Qwen3.5-9B","created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000017","completion":"0.00000025"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":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/qwen/qwen3.5-9b-20260310/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":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.5-35b-a3b","canonical_slug":"qwen/qwen3.5-35b-a3b-20260224","hugging_face_id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen: Qwen3.5-35B-A3B","created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.000001","input_cache_read":"0.00000005"},"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/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":38.9,"multilingual_index":0.864,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.5-27b","canonical_slug":"qwen/qwen3.5-27b-20260224","hugging_face_id":"Qwen/Qwen3.5-27B","name":"Qwen: Qwen3.5-27B","created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.0000026"},"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-27b-20260224/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":38.9,"multilingual_index":0.868,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.5-122b-a10b","canonical_slug":"qwen/qwen3.5-122b-a10b-20260224","hugging_face_id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000208"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/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":38.9,"multilingual_index":0.891,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.5-flash-02-23","canonical_slug":"qwen/qwen3.5-flash-20260224","hugging_face_id":null,"name":"Qwen: Qwen3.5-Flash","created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000065","completion":"0.00000026"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","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/qwen/qwen3.5-flash-20260224/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.5-plus-02-15","canonical_slug":"qwen/qwen3.5-plus-20260216","hugging_face_id":"","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000156","overrides":[{"min_prompt_tokens":256000,"prompt":"0.000000325","completion":"0.00000195"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","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":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1086,"win_rate":47.7,"rank":97},{"arena":"models","category":"asciiart","elo":1079,"win_rate":43.2,"rank":70},{"arena":"models","category":"codecategories","elo":1149,"win_rate":48.4,"rank":88},{"arena":"models","category":"dataviz","elo":1129,"win_rate":44.8,"rank":93},{"arena":"models","category":"gamedev","elo":1078,"win_rate":42.7,"rank":102},{"arena":"models","category":"svg","elo":1092,"win_rate":48.9,"rank":70},{"arena":"models","category":"uicomponent","elo":1161,"win_rate":52.2,"rank":77},{"arena":"models","category":"website","elo":1175,"win_rate":50,"rank":80}]},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3.5-397b-a17b","canonical_slug":"qwen/qwen3.5-397b-a17b-20260216","hugging_face_id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000045","completion":"0.000003","input_cache_read":"0.00000022"},"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1128,"win_rate":56.7,"rank":78},{"arena":"models","category":"codecategories","elo":1162,"win_rate":52.7,"rank":75},{"arena":"models","category":"dataviz","elo":1169,"win_rate":53.2,"rank":72},{"arena":"models","category":"gamedev","elo":1112,"win_rate":50.2,"rank":88},{"arena":"models","category":"svg","elo":1123,"win_rate":56.1,"rank":62},{"arena":"models","category":"uicomponent","elo":1147,"win_rate":51.4,"rank":86},{"arena":"models","category":"website","elo":1178,"win_rate":52.6,"rank":77}],"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":0.9,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3-coder-next","canonical_slug":"qwen/qwen3-coder-next-2025-02-03","hugging_face_id":"Qwen/Qwen3-Coder-Next","name":"Qwen: Qwen3 Coder Next","created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000012","completion":"0.0000008","input_cache_read":"0.00000007"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","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,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-next-2025-02-03/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":41.7,"multilingual_index":0.794,"decision_index":null}}},{"id":"moonshotai/kimi-k2.5","canonical_slug":"moonshotai/kimi-k2.5-0127","hugging_face_id":"moonshotai/Kimi-K2.5","name":"MoonshotAI: Kimi K2.5","created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000025","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","logprobs","max_tokens","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-k2.5-0127/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1103,"win_rate":57.8,"rank":33},{"arena":"agents","category":"fullstack","elo":1091,"win_rate":54.4,"rank":33},{"arena":"agents","category":"godotgamedev","elo":1219,"win_rate":59.8,"rank":8},{"arena":"agents","category":"mobileapps","elo":1140,"win_rate":54.7,"rank":37},{"arena":"agents","category":"webapps","elo":1103,"win_rate":51.6,"rank":35},{"arena":"models","category":"3d","elo":1172,"win_rate":53.1,"rank":60},{"arena":"models","category":"asciiart","elo":1151,"win_rate":46.5,"rank":41},{"arena":"models","category":"codecategories","elo":1218,"win_rate":54.1,"rank":56},{"arena":"models","category":"dataviz","elo":1213,"win_rate":51.3,"rank":56},{"arena":"models","category":"gamedev","elo":1178,"win_rate":53.4,"rank":63},{"arena":"models","category":"svg","elo":1133,"win_rate":48.4,"rank":58},{"arena":"models","category":"uicomponent","elo":1220,"win_rate":53.6,"rank":56},{"arena":"models","category":"website","elo":1236,"win_rate":55.2,"rank":52}],"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":0.84,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"nvidia/nemotron-3-nano-30b-a3b","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.00000024","input_cache_read":"0.000000012"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","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/nvidia/nemotron-3-nano-30b-a3b/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":83.3,"multilingual_index":0.612,"decision_index":null}},"reasoning":{"mandatory":false}},{"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":"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":"deepseek/deepseek-v3.2","canonical_slug":"deepseek/deepseek-v3.2-20251201","hugging_face_id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek: DeepSeek V3.2","created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000038","input_cache_read":"0.00000013"},"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1100,"win_rate":49.4,"rank":90},{"arena":"models","category":"asciiart","elo":1068,"win_rate":40.5,"rank":71},{"arena":"models","category":"codecategories","elo":1146,"win_rate":49.3,"rank":92},{"arena":"models","category":"dataviz","elo":1153,"win_rate":48.2,"rank":82},{"arena":"models","category":"gamedev","elo":1103,"win_rate":46.5,"rank":96},{"arena":"models","category":"svg","elo":1016,"win_rate":40.8,"rank":89},{"arena":"models","category":"uicomponent","elo":1132,"win_rate":46.8,"rank":90},{"arena":"models","category":"website","elo":1162,"win_rate":50.2,"rank":87}],"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":0.865,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"moonshotai/kimi-k2-thinking","canonical_slug":"moonshotai/kimi-k2-thinking-20251106","hugging_face_id":"moonshotai/Kimi-K2-Thinking","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000025","input_cache_read":"0.00000015"},"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","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/moonshotai/kimi-k2-thinking-20251106/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":1100,"win_rate":48.8,"rank":116}],"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":88.9,"multilingual_index":0.735,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true}},{"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":"qwen/qwen3-vl-8b-instruct","canonical_slug":"qwen/qwen3-vl-8b-instruct","hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen: Qwen3 VL 8B Instruct","created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.00000075","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","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.8,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-8b-instruct/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":50,"multilingual_index":null,"decision_index":null}}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","canonical_slug":"qwen/qwen3-vl-30b-a3b-instruct","hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":262144,"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":0.7,"top_p":0.8,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":1},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/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":50,"multilingual_index":null,"decision_index":null}}},{"id":"deepseek/deepseek-v3.2-exp","canonical_slug":"deepseek/deepseek-v3.2-exp","hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.00000041"},"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1115,"win_rate":56.4,"rank":84},{"arena":"models","category":"codecategories","elo":1152,"win_rate":54.2,"rank":83},{"arena":"models","category":"dataviz","elo":1146,"win_rate":50.6,"rank":85},{"arena":"models","category":"gamedev","elo":1116,"win_rate":52.9,"rank":87},{"arena":"models","category":"svg","elo":1016,"win_rate":42,"rank":90},{"arena":"models","category":"uicomponent","elo":1150,"win_rate":53.3,"rank":81},{"arena":"models","category":"website","elo":1166,"win_rate":54.3,"rank":85}],"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":0.867,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000021","completion":"0.0000019","input_cache_read":"0.0000001"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"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":0.7,"top_p":0.8,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/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":50,"multilingual_index":null,"decision_index":null}}},{"id":"deepseek/deepseek-v3.1-terminus","canonical_slug":"deepseek/deepseek-v3.1-terminus","hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.000001"},"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1108,"win_rate":56,"rank":86},{"arena":"models","category":"codecategories","elo":1157,"win_rate":56,"rank":80},{"arena":"models","category":"dataviz","elo":1162,"win_rate":53.4,"rank":76},{"arena":"models","category":"gamedev","elo":1103,"win_rate":52.5,"rank":95},{"arena":"models","category":"svg","elo":1049,"win_rate":50.1,"rank":82},{"arena":"models","category":"uicomponent","elo":1166,"win_rate":59.5,"rank":75},{"arena":"models","category":"website","elo":1174,"win_rate":56.4,"rank":81}],"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":0.827,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3-coder-flash","canonical_slug":"qwen/qwen3-coder-flash","hugging_face_id":"","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.000000195","completion":"0.000000975","input_cache_read":"0.000000039","input_cache_write":"0.00000024375","overrides":[{"min_prompt_tokens":32000,"prompt":"0.000000325","completion":"0.000001625","input_cache_read":"0.000000065","input_cache_write":"0.00000040625"},{"min_prompt_tokens":128000,"prompt":"0.00000052","completion":"0.0000026","input_cache_read":"0.000000104","input_cache_write":"0.00000065"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","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":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-flash/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"qwen/qwen3-next-80b-a3b-instruct","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct-2509","hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000011","input_cache_read":"0.00000007"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"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":{},"supported_voices":null,"knowledge_cutoff":"2025-09-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/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":44.4,"multilingual_index":null,"decision_index":null}}},{"id":"moonshotai/kimi-k2-0905","canonical_slug":"moonshotai/kimi-k2-0905","hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000025"},"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2-0905/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1080,"win_rate":48.5,"rank":116},{"arena":"models","category":"website","elo":1095,"win_rate":48.3,"rank":118}],"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":0.808,"decision_index":null}}},{"id":"deepseek/deepseek-chat-v3.1","canonical_slug":"deepseek/deepseek-chat-v3.1","hugging_face_id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000025","completion":"0.00000095","input_cache_read":"0.00000013"},"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1044,"win_rate":47.9,"rank":112},{"arena":"models","category":"codecategories","elo":1094,"win_rate":47.8,"rank":112},{"arena":"models","category":"dataviz","elo":1090,"win_rate":46.2,"rank":107},{"arena":"models","category":"gamedev","elo":1056,"win_rate":47.1,"rank":112},{"arena":"models","category":"svg","elo":951,"win_rate":38.2,"rank":100},{"arena":"models","category":"uicomponent","elo":1069,"win_rate":47.1,"rank":112},{"arena":"models","category":"website","elo":1110,"win_rate":48,"rank":111}]},"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":"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":"qwen/qwen3-coder-30b-a3b-instruct","canonical_slug":"qwen/qwen3-coder-30b-a3b-instruct","hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000028"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":1085,"win_rate":54.7,"rank":109},{"arena":"models","category":"uicomponent","elo":1030,"win_rate":54.1,"rank":120},{"arena":"models","category":"website","elo":1075,"win_rate":57.1,"rank":121}],"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}}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000003","input_cache_read":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/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":44.4,"multilingual_index":0.72,"decision_index":null}}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","canonical_slug":"qwen/qwen3-235b-a22b-thinking-2507","hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000045","completion":"0.0000035"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","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":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":965,"win_rate":40.4,"rank":124},{"arena":"models","category":"codecategories","elo":1015,"win_rate":40.8,"rank":130},{"arena":"models","category":"dataviz","elo":950,"win_rate":32.6,"rank":127},{"arena":"models","category":"gamedev","elo":929,"win_rate":34.2,"rank":139},{"arena":"models","category":"uicomponent","elo":929,"win_rate":34,"rank":134},{"arena":"models","category":"website","elo":1040,"win_rate":42,"rank":129}],"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":0.853,"decision_index":null}},"reasoning":{"mandatory":true}},{"id":"qwen/qwen3-coder","canonical_slug":"qwen/qwen3-coder-480b-a35b-07-25","hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.000001","input_cache_read":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1125,"win_rate":61.2,"rank":99},{"arena":"models","category":"dataviz","elo":1084,"win_rate":54.9,"rank":110},{"arena":"models","category":"gamedev","elo":1071,"win_rate":58.7,"rank":103},{"arena":"models","category":"uicomponent","elo":1096,"win_rate":61.4,"rank":102},{"arena":"models","category":"website","elo":1146,"win_rate":61.7,"rank":100}],"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}}},{"id":"qwen/qwen3-235b-a22b-2507","canonical_slug":"qwen/qwen3-235b-a22b-07-25","hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.0000008","input_cache_read":"0.00000005"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"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":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":961,"win_rate":41.1,"rank":125},{"arena":"models","category":"codecategories","elo":1020,"win_rate":42.6,"rank":128},{"arena":"models","category":"dataviz","elo":1064,"win_rate":49,"rank":114},{"arena":"models","category":"gamedev","elo":923,"win_rate":35,"rank":140},{"arena":"models","category":"uicomponent","elo":949,"win_rate":38.4,"rank":130},{"arena":"models","category":"website","elo":1045,"win_rate":43.6,"rank":128}],"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}}},{"id":"moonshotai/kimi-k2","canonical_slug":"moonshotai/kimi-k2","hugging_face_id":"moonshotai/Kimi-K2-Instruct","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000057","completion":"0.0000023"},"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-12-31","expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1015,"win_rate":51.7,"rank":129},{"arena":"models","category":"dataviz","elo":1018,"win_rate":49.4,"rank":119},{"arena":"models","category":"gamedev","elo":946,"win_rate":46.4,"rank":134},{"arena":"models","category":"uicomponent","elo":1014,"win_rate":55.1,"rank":122},{"arena":"models","category":"website","elo":1037,"win_rate":53.1,"rank":131}],"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":88.9,"multilingual_index":0.786,"decision_index":null}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","hugging_face_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.0000002"},"top_provider":{"context_length":128000,"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":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":889,"win_rate":39.8,"rank":145},{"arena":"models","category":"dataviz","elo":929,"win_rate":43.3,"rank":131},{"arena":"models","category":"gamedev","elo":860,"win_rate":39.4,"rank":145},{"arena":"models","category":"uicomponent","elo":890,"win_rate":40.5,"rank":140},{"arena":"models","category":"website","elo":883,"win_rate":38.3,"rank":148}]}},{"id":"deepseek/deepseek-r1-0528","canonical_slug":"deepseek/deepseek-r1-0528","hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek: R1 0528","created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.000000571","completion":"0.000002286"},"top_provider":{"context_length":128000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-r1-0528/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1078,"win_rate":53.3,"rank":99},{"arena":"models","category":"codecategories","elo":1120,"win_rate":52.6,"rank":103},{"arena":"models","category":"dataviz","elo":1177,"win_rate":60.9,"rank":69},{"arena":"models","category":"gamedev","elo":1069,"win_rate":49.3,"rank":106},{"arena":"models","category":"svg","elo":1022,"win_rate":48.7,"rank":87},{"arena":"models","category":"uicomponent","elo":1086,"win_rate":54.9,"rank":105},{"arena":"models","category":"website","elo":1137,"win_rate":52.7,"rank":101}],"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":50,"multilingual_index":0.86,"decision_index":null}},"reasoning":{"mandatory":true}},{"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":"meta-llama/llama-guard-4-12b","canonical_slug":"meta-llama/llama-guard-4-12b","hugging_face_id":"meta-llama/Llama-Guard-4-12B","name":"Meta: Llama Guard 4 12B","created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","context_length":163840,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000018","completion":"0.00000018"},"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-guard-4-12b/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"qwen/qwen3-30b-a3b","canonical_slug":"qwen/qwen3-30b-a3b-04-28","hugging_face_id":"Qwen/Qwen3-30B-A3B","name":"Qwen: Qwen3 30B A3B","created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000012","completion":"0.0000005"},"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":924,"win_rate":37.5,"rank":143},{"arena":"models","category":"dataviz","elo":967,"win_rate":39,"rank":126},{"arena":"models","category":"gamedev","elo":870,"win_rate":33.9,"rank":144},{"arena":"models","category":"uicomponent","elo":929,"win_rate":42.4,"rank":135},{"arena":"models","category":"website","elo":942,"win_rate":37.7,"rank":145}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen/qwen3-14b","canonical_slug":"qwen/qwen3-14b-04-28","hugging_face_id":"Qwen/Qwen3-14B","name":"Qwen: Qwen3 14B","created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000012","completion":"0.00000024"},"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-14b-04-28/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false}},{"id":"qwen/qwen3-32b","canonical_slug":"qwen/qwen3-32b-04-28","hugging_face_id":"Qwen/Qwen3-32B","name":"Qwen: Qwen3 32B","created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000008","completion":"0.00000028"},"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-32b-04-28/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":false}},{"id":"meta-llama/llama-4-maverick","canonical_slug":"meta-llama/llama-4-maverick-17b-128e-instruct","hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","name":"Meta: Llama 4 Maverick","created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","context_length":524288,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":"0.00000035","completion":"0.000001","input_cache_read":"0.00000017"},"top_provider":{"context_length":524288,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":868,"win_rate":40.2,"rank":134},{"arena":"models","category":"codecategories","elo":861,"win_rate":35.8,"rank":146},{"arena":"models","category":"dataviz","elo":882,"win_rate":38.4,"rank":136},{"arena":"models","category":"gamedev","elo":810,"win_rate":33.7,"rank":147},{"arena":"models","category":"uicomponent","elo":883,"win_rate":40.8,"rank":141},{"arena":"models","category":"website","elo":858,"win_rate":34.4,"rank":149}],"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":0.825,"decision_index":null}}},{"id":"meta-llama/llama-4-scout","canonical_slug":"meta-llama/llama-4-scout-17b-16e-instruct","hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","name":"Meta: Llama 4 Scout","created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","context_length":1310720,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000003"},"top_provider":{"context_length":327680,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":771,"win_rate":26.6,"rank":149},{"arena":"models","category":"dataviz","elo":896,"win_rate":39.3,"rank":134},{"arena":"models","category":"gamedev","elo":745,"win_rate":27.4,"rank":148},{"arena":"models","category":"uicomponent","elo":751,"win_rate":25.5,"rank":144},{"arena":"models","category":"website","elo":738,"win_rate":22.7,"rank":153}],"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":0.741,"decision_index":null}}},{"id":"deepseek/deepseek-chat-v3-0324","canonical_slug":"deepseek/deepseek-chat-v3-0324","hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000001"},"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-07-31","expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"mistralai/mistral-small-3.1-24b-instruct","canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","hugging_face_id":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000000351","completion":"0.000000555"},"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"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":"qwen/qwen2.5-vl-72b-instruct","canonical_slug":"qwen/qwen2.5-vl-72b-instruct","hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.0000008","completion":"0.000001","input_cache_read":"0.0000004"},"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"qwen/qwen-plus","canonical_slug":"qwen/qwen-plus-2025-01-25","hugging_face_id":"","name":"Qwen: Qwen-Plus","created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":"0.00000026","completion":"0.00000078","input_cache_read":"0.000000052","input_cache_write":"0.000000325","overrides":[{"min_prompt_tokens":256000,"prompt":"0.00000078","completion":"0.00000234","input_cache_read":"0.000000156","input_cache_write":"0.000000975"}]},"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"mistralai/mistral-small-24b-instruct-2501","canonical_slug":"mistralai/mistral-small-24b-instruct-2501","hugging_face_id":"mistralai/Mistral-Small-24B-Instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.00000008"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{"temperature":0.3,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"microsoft/phi-4","canonical_slug":"microsoft/phi-4","hugging_face_id":"microsoft/phi-4","name":"Microsoft: Phi 4","created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000014"},"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/microsoft/phi-4/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":50,"multilingual_index":null,"decision_index":null}}},{"id":"meta-llama/llama-3.3-70b-instruct","canonical_slug":"meta-llama/llama-3.3-70b-instruct","hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","name":"Meta: Llama 3.3 70B Instruct","created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000071","completion":"0.00000071","input_cache_read":"0.00000071"},"top_provider":{"context_length":128000,"max_completion_tokens":115200,"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":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.3-70b-instruct/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":38.9,"multilingual_index":0.764,"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":"qwen/qwen-2.5-coder-32b-instruct","canonical_slug":"qwen/qwen-2.5-coder-32b-instruct","hugging_face_id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000066","completion":"0.000001"},"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"meta-llama/llama-3.2-3b-instruct","canonical_slug":"meta-llama/llama-3.2-3b-instruct","hugging_face_id":"meta-llama/Llama-3.2-3B-Instruct","name":"Meta: Llama 3.2 3B Instruct","created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000005","completion":"0.00000033"},"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"qwen/qwen-2.5-72b-instruct","canonical_slug":"qwen/qwen-2.5-72b-instruct","hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000036","completion":"0.0000004"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-72b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"meta-llama/llama-3.1-70b-instruct","canonical_slug":"meta-llama/llama-3.1-70b-instruct","hugging_face_id":"meta-llama/Meta-Llama-3.1-70B-Instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000072","completion":"0.00000072"},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]},{"id":"meta-llama/llama-3.1-8b-instruct","canonical_slug":"meta-llama/llama-3.1-8b-instruct","hugging_face_id":"meta-llama/Meta-Llama-3.1-8B-Instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000002","completion":"0.00000004"},"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":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.1-8b-instruct/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":null,"multilingual_index":0.351,"decision_index":null}}},{"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":"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"]},{"id":"nvidia/switchyard","canonical_slug":"nvidia/switchyard","hugging_face_id":null,"name":"NVIDIA: Switchyard","created":1790025947,"description":"Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/switchyard/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"]}],"total_count":114,"links":{"next":null}}