{"data":[{"id":"meituan/longcat-2.0","canonical_slug":"meituan/longcat-2.0-20260720","hugging_face_id":"meituan-longcat/LongCat-2.0","name":"Meituan: LongCat 2.0","created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","context_length":1048756,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},"top_provider":{"context_length":1048756,"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","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meituan/longcat-2.0-20260720/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"thinkingmachines/inkling","canonical_slug":"thinkingmachines/inkling-20260715","hugging_face_id":"thinkingmachines/Inkling","name":"Thinking Machines: Inkling","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":1048576,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017"},"top_provider":{"context_length":524288,"max_completion_tokens":null,"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","seed","stop","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/thinkingmachines/inkling-20260715/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":40.7,"coding_index":52.1,"agentic_index":32.3}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"}},{"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->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000029","completion":"0.000015","input_cache_read":"0.00000029"},"top_provider":{"context_length":1048576,"max_completion_tokens":1048576,"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"},"benchmarks":{"design_arena":[{"arena":"agents","category":"godotgamedev","elo":1199,"win_rate":48.5,"rank":11},{"arena":"agents","category":"python-pptxslides","elo":1379,"win_rate":71,"rank":1},{"arena":"agents","category":"webapps","elo":1329,"win_rate":63,"rank":1},{"arena":"models","category":"3d","elo":1456,"win_rate":69.4,"rank":1},{"arena":"models","category":"codecategories","elo":1418,"win_rate":67.1,"rank":1},{"arena":"models","category":"dataviz","elo":1382,"win_rate":66.5,"rank":1},{"arena":"models","category":"uicomponent","elo":1413,"win_rate":67.7,"rank":1},{"arena":"models","category":"website","elo":1375,"win_rate":63.5,"rank":1}],"artificial_analysis":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"tencent/hy3","canonical_slug":"tencent/hy3-20260706","hugging_face_id":"tencent/Hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000058","input_cache_read":"0.000000035"},"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy3-20260706/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1232,"win_rate":43.8,"rank":37},{"arena":"models","category":"codecategories","elo":1207,"win_rate":41.2,"rank":45},{"arena":"models","category":"dataviz","elo":1154,"win_rate":36.1,"rank":68},{"arena":"models","category":"gamedev","elo":1190,"win_rate":38.6,"rank":56},{"arena":"models","category":"uicomponent","elo":1197,"win_rate":40.2,"rank":52},{"arena":"models","category":"website","elo":1207,"win_rate":41.4,"rank":52}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2-20260616","hugging_face_id":"zai-org/GLM-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000024","input_cache_read":"0.00000014"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.2-20260616/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1185,"win_rate":48.2,"rank":11},{"arena":"agents","category":"androidnative","elo":1231,"win_rate":54.9,"rank":9},{"arena":"agents","category":"fullstack","elo":1271,"win_rate":63.8,"rank":5},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":18},{"arena":"agents","category":"htmlslides","elo":1208,"win_rate":51.8,"rank":9},{"arena":"agents","category":"mobileapps","elo":1233,"win_rate":54.3,"rank":9},{"arena":"agents","category":"python-pptxslides","elo":1186,"win_rate":48,"rank":10},{"arena":"agents","category":"webapps","elo":1269,"win_rate":57.1,"rank":7},{"arena":"models","category":"3d","elo":1367,"win_rate":60,"rank":4},{"arena":"models","category":"asciiart","elo":1227,"win_rate":48.5,"rank":17},{"arena":"models","category":"codecategories","elo":1346,"win_rate":60.7,"rank":3},{"arena":"models","category":"dataviz","elo":1304,"win_rate":57.3,"rank":10},{"arena":"models","category":"gamedev","elo":1358,"win_rate":62,"rank":2},{"arena":"models","category":"svg","elo":1261,"win_rate":55.5,"rank":9},{"arena":"models","category":"uicomponent","elo":1333,"win_rate":59.8,"rank":5},{"arena":"models","category":"website","elo":1340,"win_rate":60.8,"rank":3}],"artificial_analysis":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"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":"0.00000072","completion":"0.0000035","input_cache_read":"0.00000015"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","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"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1138,"win_rate":42.8,"rank":16},{"arena":"agents","category":"androidnative","elo":1252,"win_rate":57.6,"rank":6},{"arena":"agents","category":"fullstack","elo":1216,"win_rate":54.5,"rank":11},{"arena":"agents","category":"godotgamedev","elo":1190,"win_rate":49.5,"rank":12},{"arena":"agents","category":"htmlslides","elo":1227,"win_rate":53.8,"rank":7},{"arena":"agents","category":"mobileapps","elo":1213,"win_rate":50.4,"rank":13},{"arena":"agents","category":"python-pptxslides","elo":1147,"win_rate":42.4,"rank":15},{"arena":"agents","category":"webapps","elo":1229,"win_rate":49.2,"rank":16},{"arena":"models","category":"3d","elo":1300,"win_rate":52.4,"rank":17},{"arena":"models","category":"asciiart","elo":1242,"win_rate":51.9,"rank":13},{"arena":"models","category":"codecategories","elo":1291,"win_rate":53.5,"rank":18},{"arena":"models","category":"dataviz","elo":1256,"win_rate":51.5,"rank":31},{"arena":"models","category":"gamedev","elo":1270,"win_rate":50.7,"rank":27},{"arena":"models","category":"svg","elo":1223,"win_rate":48.8,"rank":19},{"arena":"models","category":"uicomponent","elo":1297,"win_rate":54.5,"rank":18},{"arena":"models","category":"website","elo":1302,"win_rate":55.7,"rank":11}],"artificial_analysis":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6}},"reasoning":{"mandatory":true,"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":1000000,"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","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":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"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1189,"win_rate":41.6,"rank":50},{"arena":"models","category":"asciiart","elo":1113,"win_rate":37.5,"rank":51},{"arena":"models","category":"codecategories","elo":1155,"win_rate":36.1,"rank":69},{"arena":"models","category":"dataviz","elo":1153,"win_rate":37.6,"rank":70},{"arena":"models","category":"gamedev","elo":1183,"win_rate":38.8,"rank":60},{"arena":"models","category":"svg","elo":1129,"win_rate":37.7,"rank":48},{"arena":"models","category":"uicomponent","elo":1178,"win_rate":39.3,"rank":59},{"arena":"models","category":"website","elo":1128,"win_rate":32.5,"rank":82}],"artificial_analysis":{"intelligence_index":37.8,"coding_index":49.3,"agentic_index":27.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium"],"default_effort":"high"}},{"id":"minimax/minimax-m3","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":524288,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1200,"win_rate":52.6,"rank":8},{"arena":"agents","category":"androidnative","elo":1120,"win_rate":36.5,"rank":20},{"arena":"agents","category":"fullstack","elo":1250,"win_rate":53,"rank":8},{"arena":"agents","category":"htmlslides","elo":1203,"win_rate":50.6,"rank":12},{"arena":"agents","category":"mobileapps","elo":1254,"win_rate":56.9,"rank":5},{"arena":"agents","category":"webapps","elo":1247,"win_rate":51.6,"rank":14},{"arena":"models","category":"3d","elo":1279,"win_rate":54.4,"rank":24},{"arena":"models","category":"asciiart","elo":1195,"win_rate":47.5,"rank":23},{"arena":"models","category":"codecategories","elo":1285,"win_rate":54.4,"rank":22},{"arena":"models","category":"dataviz","elo":1268,"win_rate":53.8,"rank":23},{"arena":"models","category":"gamedev","elo":1274,"win_rate":50.5,"rank":26},{"arena":"models","category":"svg","elo":1223,"win_rate":50.2,"rank":21},{"arena":"models","category":"uicomponent","elo":1281,"win_rate":53.5,"rank":23},{"arena":"models","category":"website","elo":1285,"win_rate":54.6,"rank":20}],"artificial_analysis":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4}},"reasoning":{"mandatory":false}},{"id":"minimax/minimax-m3:batch","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3 (batch)","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.00000003"},"top_provider":{"context_length":524288,"max_completion_tokens":null,"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","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1200,"win_rate":52.6,"rank":8},{"arena":"agents","category":"androidnative","elo":1120,"win_rate":36.5,"rank":20},{"arena":"agents","category":"fullstack","elo":1250,"win_rate":53,"rank":8},{"arena":"agents","category":"htmlslides","elo":1203,"win_rate":50.6,"rank":12},{"arena":"agents","category":"mobileapps","elo":1254,"win_rate":56.9,"rank":5},{"arena":"agents","category":"webapps","elo":1247,"win_rate":51.6,"rank":14},{"arena":"models","category":"3d","elo":1279,"win_rate":54.4,"rank":24},{"arena":"models","category":"asciiart","elo":1195,"win_rate":47.5,"rank":23},{"arena":"models","category":"codecategories","elo":1285,"win_rate":54.4,"rank":22},{"arena":"models","category":"dataviz","elo":1268,"win_rate":53.8,"rank":23},{"arena":"models","category":"gamedev","elo":1274,"win_rate":50.5,"rank":26},{"arena":"models","category":"svg","elo":1223,"win_rate":50.2,"rank":21},{"arena":"models","category":"uicomponent","elo":1281,"win_rate":53.5,"rank":23},{"arena":"models","category":"website","elo":1285,"win_rate":54.6,"rank":20}],"artificial_analysis":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4}},"reasoning":{"mandatory":false}},{"id":"stepfun/step-3.7-flash","canonical_slug":"stepfun/step-3.7-flash-20260528","hugging_face_id":"stepfun-ai/Step-3.7-Flash","name":"StepFun: Step 3.7 Flash","created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","context_length":256000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"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/stepfun/step-3.7-flash-20260528/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1178,"win_rate":41.9,"rank":55},{"arena":"models","category":"asciiart","elo":1194,"win_rate":46.7,"rank":24},{"arena":"models","category":"codecategories","elo":1203,"win_rate":44.8,"rank":48},{"arena":"models","category":"dataviz","elo":1204,"win_rate":45.9,"rank":46},{"arena":"models","category":"gamedev","elo":1204,"win_rate":41.9,"rank":46},{"arena":"models","category":"svg","elo":1120,"win_rate":39,"rank":51},{"arena":"models","category":"uicomponent","elo":1201,"win_rate":43.6,"rank":48},{"arena":"models","category":"website","elo":1212,"win_rate":46.2,"rank":49}],"artificial_analysis":{"intelligence_index":30.3,"coding_index":39.6,"agentic_index":21.5}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"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":"0.00000095"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":20},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4}},"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":"0.000000289","completion":"0.0000024"},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27}},"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","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":"0.0000013","completion":"0.0000026","input_cache_read":"0.0000001"},"top_provider":{"context_length":1048576,"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":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":948,"win_rate":22.1,"rank":33},{"arena":"agents","category":"godotgamedev","elo":1059,"win_rate":34,"rank":27},{"arena":"agents","category":"webapps","elo":999,"win_rate":26.4,"rank":34},{"arena":"models","category":"3d","elo":1318,"win_rate":59.6,"rank":10},{"arena":"models","category":"asciiart","elo":1188,"win_rate":46.6,"rank":27},{"arena":"models","category":"codecategories","elo":1274,"win_rate":54.1,"rank":25},{"arena":"models","category":"dataviz","elo":1226,"win_rate":49.5,"rank":39},{"arena":"models","category":"gamedev","elo":1291,"win_rate":55.7,"rank":21},{"arena":"models","category":"svg","elo":1185,"win_rate":46.5,"rank":36},{"arena":"models","category":"uicomponent","elo":1260,"win_rate":51.9,"rank":31},{"arena":"models","category":"website","elo":1260,"win_rate":52.5,"rank":30}],"artificial_analysis":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek: DeepSeek V4 Flash","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000018"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1246,"win_rate":49.4,"rank":35},{"arena":"models","category":"asciiart","elo":1151,"win_rate":43.1,"rank":45},{"arena":"models","category":"codecategories","elo":1236,"win_rate":49.2,"rank":37},{"arena":"models","category":"dataviz","elo":1154,"win_rate":40.6,"rank":67},{"arena":"models","category":"gamedev","elo":1253,"win_rate":50.3,"rank":32},{"arena":"models","category":"svg","elo":1204,"win_rate":48.6,"rank":26},{"arena":"models","category":"uicomponent","elo":1200,"win_rate":45,"rank":50},{"arena":"models","category":"website","elo":1233,"win_rate":49.5,"rank":38}],"artificial_analysis":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"xiaomi/mimo-v2.5-pro","canonical_slug":"xiaomi/mimo-v2.5-pro-20260422","hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000003","input_cache_read":"0.0000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.5-pro-20260422/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1308,"win_rate":57.2,"rank":15},{"arena":"models","category":"asciiart","elo":1179,"win_rate":47.1,"rank":34},{"arena":"models","category":"codecategories","elo":1311,"win_rate":57.8,"rank":9},{"arena":"models","category":"dataviz","elo":1294,"win_rate":57.8,"rank":13},{"arena":"models","category":"gamedev","elo":1339,"win_rate":62,"rank":5},{"arena":"models","category":"svg","elo":1223,"win_rate":52,"rank":20},{"arena":"models","category":"uicomponent","elo":1297,"win_rate":56.4,"rank":19},{"arena":"models","category":"website","elo":1306,"win_rate":56.9,"rank":10}],"artificial_analysis":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1}},"reasoning":{"mandatory":false}},{"id":"xiaomi/mimo-v2.5","canonical_slug":"xiaomi/mimo-v2.5-20260422","hugging_face_id":"XiaomiMiMo/MiMo-V2.5","name":"Xiaomi: MiMo-V2.5","created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","context_length":1048576,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.00000005"},"top_provider":{"context_length":1048576,"max_completion_tokens":1048576,"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/xiaomi/mimo-v2.5-20260422/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1274,"win_rate":52.5,"rank":26},{"arena":"models","category":"asciiart","elo":1177,"win_rate":46.6,"rank":38},{"arena":"models","category":"codecategories","elo":1292,"win_rate":55.3,"rank":17},{"arena":"models","category":"dataviz","elo":1284,"win_rate":55.7,"rank":16},{"arena":"models","category":"gamedev","elo":1299,"win_rate":56.5,"rank":17},{"arena":"models","category":"svg","elo":1220,"win_rate":52.7,"rank":22},{"arena":"models","category":"uicomponent","elo":1295,"win_rate":55.8,"rank":20},{"arena":"models","category":"website","elo":1295,"win_rate":55.7,"rank":19}],"artificial_analysis":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7}},"reasoning":{"mandatory":false}},{"id":"openai/gpt-5.4-image-2","canonical_slug":"openai/gpt-5.4-image-2-20260421","hugging_face_id":"","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","context_length":272000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000008","completion":"0.000015","image_output":"0.00003","web_search":"0.01","input_cache_read":"0.000002"},"top_provider":{"context_length":272000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"moonshotai/kimi-k2.6","canonical_slug":"moonshotai/kimi-k2.6-20260420","hugging_face_id":"moonshotai/Kimi-K2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.00000341","input_cache_read":"0.0000002"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","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"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1152,"win_rate":48,"rank":15},{"arena":"agents","category":"agentichtmlslides","elo":1248,"win_rate":59,"rank":2},{"arena":"agents","category":"agenticslides","elo":1187,"win_rate":45.8,"rank":5},{"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":5},{"arena":"agents","category":"androidnative","elo":1280,"win_rate":62.3,"rank":4},{"arena":"agents","category":"fullstack","elo":1200,"win_rate":55.5,"rank":14},{"arena":"agents","category":"godotgamedev","elo":1165,"win_rate":48,"rank":14},{"arena":"agents","category":"htmlslides","elo":1227,"win_rate":54.6,"rank":6},{"arena":"agents","category":"mobileapps","elo":1243,"win_rate":56.9,"rank":7},{"arena":"agents","category":"pptxslides","elo":1181,"win_rate":44.3,"rank":5},{"arena":"agents","category":"python-pptxslides","elo":1180,"win_rate":42.1,"rank":11},{"arena":"agents","category":"webapps","elo":1268,"win_rate":59.3,"rank":8},{"arena":"models","category":"3d","elo":1332,"win_rate":60.6,"rank":7},{"arena":"models","category":"asciiart","elo":1188,"win_rate":46,"rank":29},{"arena":"models","category":"codecategories","elo":1308,"win_rate":57,"rank":12},{"arena":"models","category":"dataviz","elo":1289,"win_rate":56.3,"rank":15},{"arena":"models","category":"gamedev","elo":1304,"win_rate":56.1,"rank":15},{"arena":"models","category":"svg","elo":1229,"win_rate":51.7,"rank":17},{"arena":"models","category":"uicomponent","elo":1300,"win_rate":56.1,"rank":17},{"arena":"models","category":"website","elo":1301,"win_rate":55.8,"rank":13}],"artificial_analysis":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"z-ai/glm-5.1","canonical_slug":"z-ai/glm-5.1-20260406","hugging_face_id":"zai-org/GLM-5.1","name":"Z.ai: GLM 5.1","created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000001"},"top_provider":{"context_length":202752,"max_completion_tokens":65536,"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/z-ai/glm-5.1-20260406/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1336,"win_rate":62.6,"rank":5},{"arena":"models","category":"asciiart","elo":1187,"win_rate":47.8,"rank":30},{"arena":"models","category":"codecategories","elo":1308,"win_rate":57.9,"rank":11},{"arena":"models","category":"dataviz","elo":1366,"win_rate":67,"rank":3},{"arena":"models","category":"gamedev","elo":1326,"win_rate":61.2,"rank":9},{"arena":"models","category":"svg","elo":1270,"win_rate":59.4,"rank":7},{"arena":"models","category":"uicomponent","elo":1314,"win_rate":59.5,"rank":10},{"arena":"models","category":"website","elo":1298,"win_rate":55.7,"rank":16},{"arena":"agents","category":"agenticgamedev","elo":1176,"win_rate":50.6,"rank":13},{"arena":"agents","category":"agentichtmlslides","elo":1205,"win_rate":52,"rank":6},{"arena":"agents","category":"agenticslides","elo":1245,"win_rate":54.4,"rank":3},{"arena":"agents","category":"agenticslides(html)","elo":1204,"win_rate":51.8,"rank":6},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1240,"win_rate":53.3,"rank":4},{"arena":"agents","category":"androidnative","elo":1227,"win_rate":53.1,"rank":11},{"arena":"agents","category":"fullstack","elo":1205,"win_rate":55.7,"rank":13},{"arena":"agents","category":"godotgamedev","elo":1104,"win_rate":39.5,"rank":25},{"arena":"agents","category":"htmlslides","elo":1204,"win_rate":51.3,"rank":11},{"arena":"agents","category":"mobileapps","elo":1219,"win_rate":53.9,"rank":11},{"arena":"agents","category":"pptxslides","elo":1241,"win_rate":53.5,"rank":4},{"arena":"agents","category":"python-pptxslides","elo":1258,"win_rate":54.2,"rank":5},{"arena":"agents","category":"webapps","elo":1224,"win_rate":53.5,"rank":17}],"artificial_analysis":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"google/gemma-4-26b-a4b-it","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","hugging_face_id":"google/gemma-4-26B-A4B-it","name":"Google: Gemma 4 26B A4B ","created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.00000007","completion":"0.00000034"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11}},"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"google/gemma-4-31b-it","canonical_slug":"google/gemma-4-31b-it-20260402","hugging_face_id":"google/gemma-4-31B-it","name":"Google: Gemma 4 31B","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.00000009","completion":"0.00000034"},"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4}},"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"arcee-ai/trinity-large-thinking","canonical_slug":"arcee-ai/trinity-large-thinking","hugging_face_id":"arcee-ai/Trinity-Large-Thinking","name":"Arcee AI: Trinity Large Thinking","created":1775058318,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000022","completion":"0.00000085","input_cache_read":"0.00000006"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3,"top_p":0.8,"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/arcee-ai/trinity-large-thinking/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1139,"win_rate":41.3,"rank":69},{"arena":"models","category":"asciiart","elo":1079,"win_rate":37.1,"rank":53},{"arena":"models","category":"codecategories","elo":1148,"win_rate":40.2,"rank":72},{"arena":"models","category":"dataviz","elo":1127,"win_rate":39.3,"rank":78},{"arena":"models","category":"gamedev","elo":1135,"win_rate":38.4,"rank":74},{"arena":"models","category":"svg","elo":1066,"win_rate":35.2,"rank":62},{"arena":"models","category":"uicomponent","elo":1081,"win_rate":32.6,"rank":82},{"arena":"models","category":"website","elo":1161,"win_rate":41.3,"rank":68}],"artificial_analysis":{"intelligence_index":18.2,"coding_index":25.8,"agentic_index":3.7}},"reasoning":{"mandatory":true}},{"id":"kwaipilot/kat-coder-pro-v2","canonical_slug":"kwaipilot/kat-coder-pro-v2-20260327","hugging_face_id":"","name":"Kwaipilot: KAT-Coder-Pro V2","created":1774649310,"description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":262144,"max_completion_tokens":144000,"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":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/kwaipilot/kat-coder-pro-v2-20260327/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":33.7,"coding_index":59.5,"agentic_index":15.5}}},{"id":"minimax/minimax-m2.7","canonical_slug":"minimax/minimax-m2.7-20260318","hugging_face_id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax: MiniMax M2.7","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.00000005"},"top_provider":{"context_length":196608,"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","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.7-20260318/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1247,"win_rate":50.6,"rank":34},{"arena":"models","category":"asciiart","elo":1178,"win_rate":48,"rank":35},{"arena":"models","category":"codecategories","elo":1265,"win_rate":53,"rank":30},{"arena":"models","category":"dataviz","elo":1261,"win_rate":53.2,"rank":27},{"arena":"models","category":"gamedev","elo":1263,"win_rate":53.1,"rank":28},{"arena":"models","category":"svg","elo":1189,"win_rate":50.3,"rank":34},{"arena":"models","category":"uicomponent","elo":1247,"win_rate":50,"rank":34},{"arena":"models","category":"website","elo":1271,"win_rate":53.9,"rank":27}],"artificial_analysis":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6}},"reasoning":{"mandatory":true}},{"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":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000085","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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":25.4,"coding_index":37.7,"agentic_index":8.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["medium","low"],"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":256000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.00000015"},"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/qwen3.5-9b-20260310/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4}},"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":256000,"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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8}},"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":256000,"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"},"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":"0.00000029","completion":"0.0000024"},"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/qwen3.5-122b-a10b-20260224/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":32.3,"coding_index":45.7,"agentic_index":20.7}},"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":256000,"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"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1218,"win_rate":56.7,"rank":41},{"arena":"models","category":"codecategories","elo":1210,"win_rate":52.6,"rank":43},{"arena":"models","category":"dataviz","elo":1204,"win_rate":53.2,"rank":45},{"arena":"models","category":"gamedev","elo":1196,"win_rate":50.1,"rank":51},{"arena":"models","category":"svg","elo":1191,"win_rate":56.1,"rank":33},{"arena":"models","category":"uicomponent","elo":1199,"win_rate":51.4,"rank":51},{"arena":"models","category":"website","elo":1215,"win_rate":52.6,"rank":45}],"artificial_analysis":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8}},"reasoning":{"mandatory":false}},{"id":"minimax/minimax-m2.5","canonical_slug":"minimax/minimax-m2.5-20260211","hugging_face_id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax: MiniMax M2.5","created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000009","input_cache_read":"0.00000005"},"top_provider":{"context_length":196608,"max_completion_tokens":196608,"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":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.5-20260211/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1227,"win_rate":57.6,"rank":38},{"arena":"models","category":"codecategories","elo":1237,"win_rate":56.8,"rank":36},{"arena":"models","category":"dataviz","elo":1201,"win_rate":51.2,"rank":48},{"arena":"models","category":"gamedev","elo":1232,"win_rate":55.5,"rank":39},{"arena":"models","category":"svg","elo":1200,"win_rate":54.5,"rank":29},{"arena":"models","category":"uicomponent","elo":1209,"win_rate":53.4,"rank":44},{"arena":"models","category":"website","elo":1247,"win_rate":57.5,"rank":35}]},"reasoning":{"mandatory":true}},{"id":"z-ai/glm-5","canonical_slug":"z-ai/glm-5-20260211","hugging_face_id":"zai-org/GLM-5","name":"Z.ai: GLM 5","created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.00000208","input_cache_read":"0.00000012"},"top_provider":{"context_length":202752,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5-20260211/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1218,"win_rate":59.4,"rank":12},{"arena":"agents","category":"fullstack","elo":1160,"win_rate":51.6,"rank":17},{"arena":"agents","category":"godotgamedev","elo":1144,"win_rate":46.7,"rank":16},{"arena":"agents","category":"htmlslides","elo":1169,"win_rate":44.8,"rank":16},{"arena":"agents","category":"mobileapps","elo":1208,"win_rate":52.4,"rank":15},{"arena":"models","category":"3d","elo":1286,"win_rate":56.3,"rank":23},{"arena":"models","category":"asciiart","elo":1186,"win_rate":48,"rank":31},{"arena":"models","category":"codecategories","elo":1278,"win_rate":55.5,"rank":23},{"arena":"models","category":"dataviz","elo":1259,"win_rate":53,"rank":29},{"arena":"models","category":"gamedev","elo":1290,"win_rate":57.4,"rank":22},{"arena":"models","category":"svg","elo":1218,"win_rate":54.4,"rank":23},{"arena":"models","category":"uicomponent","elo":1267,"win_rate":53.6,"rank":29},{"arena":"models","category":"website","elo":1273,"win_rate":55,"rank":25}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"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":262144,"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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8}}},{"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":"0.00000045","completion":"0.00000225","input_cache_read":"0.00000007"},"top_provider":{"context_length":262144,"max_completion_tokens":64000,"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/moonshotai/kimi-k2.5-0127/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1106,"win_rate":57.9,"rank":22},{"arena":"agents","category":"fullstack","elo":1154,"win_rate":54.2,"rank":18},{"arena":"agents","category":"godotgamedev","elo":1219,"win_rate":59.8,"rank":9},{"arena":"agents","category":"mobileapps","elo":1175,"win_rate":49,"rank":21},{"arena":"agents","category":"webapps","elo":1177,"win_rate":50.3,"rank":21},{"arena":"models","category":"3d","elo":1263,"win_rate":53.2,"rank":29},{"arena":"models","category":"asciiart","elo":1205,"win_rate":46.7,"rank":19},{"arena":"models","category":"codecategories","elo":1268,"win_rate":54.2,"rank":29},{"arena":"models","category":"dataviz","elo":1251,"win_rate":51.6,"rank":33},{"arena":"models","category":"gamedev","elo":1262,"win_rate":53.4,"rank":29},{"arena":"models","category":"svg","elo":1196,"win_rate":48.1,"rank":31},{"arena":"models","category":"uicomponent","elo":1272,"win_rate":53.5,"rank":28},{"arena":"models","category":"website","elo":1275,"win_rate":55.4,"rank":24}],"artificial_analysis":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7}},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"openai/gpt-audio","canonical_slug":"openai/gpt-audio","hugging_face_id":"","name":"OpenAI: GPT Audio","created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","audio":"0.000032","audio_output":"0.000064"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","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/openai/gpt-audio/endpoints"}},{"id":"openai/gpt-audio-mini","canonical_slug":"openai/gpt-audio-mini","hugging_face_id":"","name":"OpenAI: GPT Audio Mini","created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000024","audio":"0.0000006","audio_output":"0.0000024"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","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/openai/gpt-audio-mini/endpoints"}},{"id":"z-ai/glm-4.7-flash","canonical_slug":"z-ai/glm-4.7-flash-20260119","hugging_face_id":"zai-org/GLM-4.7-Flash","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.0000004","input_cache_read":"0.00000001"},"top_provider":{"context_length":202752,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-flash-20260119/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1178,"win_rate":51.2,"rank":54},{"arena":"models","category":"codecategories","elo":1208,"win_rate":53.1,"rank":44},{"arena":"models","category":"dataviz","elo":1152,"win_rate":45.3,"rank":71},{"arena":"models","category":"gamedev","elo":1191,"win_rate":49.7,"rank":54},{"arena":"models","category":"svg","elo":1088,"win_rate":44.2,"rank":55},{"arena":"models","category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35},{"arena":"models","category":"website","elo":1219,"win_rate":54,"rank":42}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"z-ai/glm-4.7","canonical_slug":"z-ai/glm-4.7-20251222","hugging_face_id":"zai-org/GLM-4.7","name":"Z.ai: GLM 4.7","created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.00000175","input_cache_read":"0.00000008"},"top_provider":{"context_length":202752,"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","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-20251222/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1100,"win_rate":56,"rank":24},{"arena":"agents","category":"fullstack","elo":1089,"win_rate":44.9,"rank":24},{"arena":"agents","category":"godotgamedev","elo":1058,"win_rate":35.8,"rank":28},{"arena":"agents","category":"mobileapps","elo":1178,"win_rate":49.5,"rank":19},{"arena":"models","category":"3d","elo":1248,"win_rate":54.3,"rank":32},{"arena":"models","category":"asciiart","elo":1203,"win_rate":48.1,"rank":22},{"arena":"models","category":"codecategories","elo":1247,"win_rate":54.8,"rank":34},{"arena":"models","category":"dataviz","elo":1225,"win_rate":51.2,"rank":41},{"arena":"models","category":"gamedev","elo":1245,"win_rate":55.2,"rank":35},{"arena":"models","category":"svg","elo":1193,"win_rate":54.3,"rank":32},{"arena":"models","category":"uicomponent","elo":1235,"win_rate":51,"rank":37},{"arena":"models","category":"website","elo":1251,"win_rate":55.3,"rank":33}],"artificial_analysis":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4}},"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":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000002","input_cache_read":"0.000000025"},"top_provider":{"context_length":262144,"max_completion_tokens":228000,"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":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":14.2,"coding_index":14.4,"agentic_index":2}},"reasoning":{"mandatory":false}},{"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":131072,"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":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":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"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1190,"win_rate":49.5,"rank":49},{"arena":"models","category":"asciiart","elo":1120,"win_rate":40.5,"rank":50},{"arena":"models","category":"codecategories","elo":1194,"win_rate":49.3,"rank":57},{"arena":"models","category":"dataviz","elo":1187,"win_rate":48.1,"rank":56},{"arena":"models","category":"gamedev","elo":1188,"win_rate":46.6,"rank":57},{"arena":"models","category":"svg","elo":1082,"win_rate":40.8,"rank":57},{"arena":"models","category":"uicomponent","elo":1185,"win_rate":46.8,"rank":56},{"arena":"models","category":"website","elo":1199,"win_rate":50.2,"rank":55}],"artificial_analysis":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3}},"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"allenai/olmo-3-32b-think","canonical_slug":"allenai/olmo-3-32b-think-20251121","hugging_face_id":"allenai/Olmo-3-32B-Think","name":"AllenAI: Olmo 3 32B Think","created":1763758276,"description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005"},"top_provider":{"context_length":65536,"max_completion_tokens":65536,"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","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/allenai/olmo-3-32b-think-20251121/endpoints"},"reasoning":{"mandatory":true}},{"id":"deepcogito/cogito-v2.1-671b","canonical_slug":"deepcogito/cogito-v2.1-671b-20251118","hugging_face_id":"","name":"Deep Cogito: Cogito v2.1 671B","created":1763071233,"description":"Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":null,"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","stop","structured_outputs","temperature","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/deepcogito/cogito-v2.1-671b-20251118/endpoints"},"reasoning":{"mandatory":false}},{"id":"ibm-granite/granite-4.0-h-micro","canonical_slug":"ibm-granite/granite-4.0-h-micro","hugging_face_id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","created":1760927695,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000017","completion":"0.000000112"},"top_provider":{"context_length":131000,"max_completion_tokens":131000,"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","temperature","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/ibm-granite/granite-4.0-h-micro/endpoints"}},{"id":"openai/gpt-5-image-mini","canonical_slug":"openai/gpt-5-image-mini","hugging_face_id":"","name":"OpenAI: GPT-5 Image Mini","created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["file","image","text"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.000002","image_output":"0.000008","web_search":"0.01","input_cache_read":"0.00000025"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","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/openai/gpt-5-image-mini/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1193,"win_rate":48.1,"rank":9},{"arena":"models","category":"image","elo":1206,"win_rate":51.1,"rank":9},{"arena":"models","category":"logo","elo":1222,"win_rate":51.6,"rank":6}]},"reasoning":{"mandatory":true}},{"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":256000,"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":262144,"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"}},{"id":"openai/gpt-5-image","canonical_slug":"openai/gpt-5-image","hugging_face_id":"","name":"OpenAI: GPT-5 Image","created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00001","image_output":"0.00004","web_search":"0.01","input_cache_read":"0.00000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","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/openai/gpt-5-image/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1199,"win_rate":49.3,"rank":7},{"arena":"models","category":"image","elo":1214,"win_rate":54.1,"rank":7},{"arena":"models","category":"logo","elo":1215,"win_rate":53.1,"rank":7}]},"reasoning":{"mandatory":true}},{"id":"openai/o3-deep-research","canonical_slug":"openai/o3-deep-research-2025-06-26","hugging_face_id":"","name":"OpenAI: o3 Deep Research","created":1760129661,"description":"o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00004","web_search":"0.01","input_cache_read":"0.0000025"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","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/openai/o3-deep-research-2025-06-26/endpoints"},"reasoning":{"mandatory":false}},{"id":"openai/o4-mini-deep-research","canonical_slug":"openai/o4-mini-deep-research-2025-06-26","hugging_face_id":"","name":"OpenAI: o4 Mini Deep Research","created":1760129642,"description":"o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.01","input_cache_read":"0.0000005"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","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/openai/o4-mini-deep-research-2025-06-26/endpoints"},"reasoning":{"mandatory":false}},{"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"}},{"id":"z-ai/glm-4.6","canonical_slug":"z-ai/glm-4.6","hugging_face_id":"zai-org/GLM-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000002","input_cache_read":"0.0000001"},"top_provider":{"context_length":202752,"max_completion_tokens":131072,"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":0.6,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.6/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1070,"win_rate":52.6,"rank":26},{"arena":"agents","category":"fullstack","elo":1070,"win_rate":42.3,"rank":28},{"arena":"agents","category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":13},{"arena":"agents","category":"mobileapps","elo":1173,"win_rate":48.7,"rank":23},{"arena":"models","category":"3d","elo":1185,"win_rate":54,"rank":51},{"arena":"models","category":"codecategories","elo":1196,"win_rate":54.3,"rank":56},{"arena":"models","category":"dataviz","elo":1193,"win_rate":52.8,"rank":53},{"arena":"models","category":"gamedev","elo":1206,"win_rate":54.6,"rank":45},{"arena":"models","category":"svg","elo":1159,"win_rate":52.1,"rank":41},{"arena":"models","category":"uicomponent","elo":1195,"win_rate":54,"rank":54},{"arena":"models","category":"website","elo":1199,"win_rate":54.4,"rank":56}],"artificial_analysis":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7}},"reasoning":{"mandatory":false}},{"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":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.00000041","input_cache_read":"0.00000027"},"top_provider":{"context_length":163840,"max_completion_tokens":163840,"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,"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"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1205,"win_rate":56.4,"rank":44},{"arena":"models","category":"codecategories","elo":1201,"win_rate":54.2,"rank":51},{"arena":"models","category":"dataviz","elo":1181,"win_rate":50.6,"rank":58},{"arena":"models","category":"gamedev","elo":1201,"win_rate":53.1,"rank":48},{"arena":"models","category":"svg","elo":1082,"win_rate":42,"rank":58},{"arena":"models","category":"uicomponent","elo":1203,"win_rate":53.3,"rank":46},{"arena":"models","category":"website","elo":1203,"win_rate":54.2,"rank":53}]},"reasoning":{"mandatory":false}},{"id":"thedrummer/cydonia-24b-v4.1","canonical_slug":"thedrummer/cydonia-24b-v4.1","hugging_face_id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.00000015"},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"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":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints"}},{"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":131072,"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"}},{"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":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.00000095","input_cache_read":"0.00000013"},"top_provider":{"context_length":163840,"max_completion_tokens":32768,"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/deepseek/deepseek-v3.1-terminus/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1198,"win_rate":56,"rank":45},{"arena":"models","category":"codecategories","elo":1206,"win_rate":56,"rank":46},{"arena":"models","category":"dataviz","elo":1193,"win_rate":53,"rank":52},{"arena":"models","category":"gamedev","elo":1187,"win_rate":52.5,"rank":58},{"arena":"models","category":"svg","elo":1115,"win_rate":50.1,"rank":52},{"arena":"models","category":"uicomponent","elo":1218,"win_rate":59.3,"rank":41},{"arena":"models","category":"website","elo":1212,"win_rate":56.4,"rank":46}],"artificial_analysis":{"intelligence_index":30.4,"coding_index":43.5,"agentic_index":18.1}},"reasoning":{"mandatory":false}},{"id":"qwen/qwen3-next-80b-a3b-thinking","canonical_slug":"qwen/qwen3-next-80b-a3b-thinking-2509","hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","created":1757612284,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000012"},"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","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,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2025-09-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1}},"reasoning":{"mandatory":true}},{"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":262144,"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"}},{"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":131072,"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":32768,"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"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1135,"win_rate":48,"rank":71},{"arena":"models","category":"codecategories","elo":1142,"win_rate":47.9,"rank":75},{"arena":"models","category":"dataviz","elo":1128,"win_rate":46.8,"rank":75},{"arena":"models","category":"gamedev","elo":1141,"win_rate":47.2,"rank":71},{"arena":"models","category":"svg","elo":1017,"win_rate":38.2,"rank":73},{"arena":"models","category":"uicomponent","elo":1120,"win_rate":47.5,"rank":74},{"arena":"models","category":"website","elo":1147,"win_rate":48,"rank":74}]},"reasoning":{"mandatory":false}},{"id":"openai/gpt-oss-120b","canonical_slug":"openai/gpt-oss-120b","hugging_face_id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000000037","completion":"0.00000017"},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-120b/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":958,"win_rate":29.4,"rank":98},{"arena":"models","category":"codecategories","elo":994,"win_rate":33.4,"rank":104},{"arena":"models","category":"dataviz","elo":1029,"win_rate":45.1,"rank":94},{"arena":"models","category":"gamedev","elo":1049,"win_rate":40.6,"rank":92},{"arena":"models","category":"uicomponent","elo":960,"win_rate":35.5,"rank":99},{"arena":"models","category":"website","elo":993,"win_rate":32.5,"rank":107}],"artificial_analysis":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"openai/gpt-oss-20b","canonical_slug":"openai/gpt-oss-20b","hugging_face_id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000014"},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-20b/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":963,"win_rate":39.7,"rank":100},{"arena":"models","category":"website","elo":877,"win_rate":27.9,"rank":115}],"artificial_analysis":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"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":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000003"},"top_provider":{"context_length":262144,"max_completion_tokens":null,"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"}},{"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":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000023","completion":"0.0000023","input_cache_read":"0.0000002"},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"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","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/qwen3-235b-a22b-thinking-2507/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1056,"win_rate":40.7,"rank":88},{"arena":"models","category":"codecategories","elo":1063,"win_rate":40.9,"rank":92},{"arena":"models","category":"dataviz","elo":976,"win_rate":32.3,"rank":99},{"arena":"models","category":"gamedev","elo":1014,"win_rate":34.3,"rank":100},{"arena":"models","category":"uicomponent","elo":979,"win_rate":33.9,"rank":98},{"arena":"models","category":"website","elo":1077,"win_rate":42.1,"rank":92}],"artificial_analysis":{"intelligence_index":19.6,"coding_index":22.1,"agentic_index":3.8}},"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":1048576,"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","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-coder-480b-a35b-07-25/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1174,"win_rate":61.2,"rank":62},{"arena":"models","category":"dataviz","elo":1111,"win_rate":54.9,"rank":83},{"arena":"models","category":"gamedev","elo":1157,"win_rate":59,"rank":64},{"arena":"models","category":"uicomponent","elo":1151,"win_rate":61.5,"rank":64},{"arena":"models","category":"website","elo":1183,"win_rate":61.7,"rank":63}]}},{"id":"bytedance/ui-tars-1.5-7b","canonical_slug":"bytedance/ui-tars-1.5-7b","hugging_face_id":"ByteDance-Seed/UI-TARS-1.5-7B","name":"ByteDance: UI-TARS 7B ","created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.0000001"},"top_provider":{"context_length":128000,"max_completion_tokens":2048,"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":"2025-01-31","expiration_date":null,"links":{"details":"/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints"}},{"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":"0.00000009","completion":"0.00000055"},"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":{},"supported_voices":null,"knowledge_cutoff":"2025-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1051,"win_rate":41.1,"rank":89},{"arena":"models","category":"codecategories","elo":1069,"win_rate":42.7,"rank":89},{"arena":"models","category":"dataviz","elo":1087,"win_rate":47.7,"rank":85},{"arena":"models","category":"gamedev","elo":1008,"win_rate":35.2,"rank":101},{"arena":"models","category":"uicomponent","elo":1003,"win_rate":38.8,"rank":93},{"arena":"models","category":"website","elo":1083,"win_rate":43.7,"rank":91}]}},{"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":128000,"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"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":937,"win_rate":39.8,"rank":109},{"arena":"models","category":"dataviz","elo":957,"win_rate":43.3,"rank":101},{"arena":"models","category":"gamedev","elo":945,"win_rate":39.4,"rank":107},{"arena":"models","category":"uicomponent","elo":944,"win_rate":40.5,"rank":101},{"arena":"models","category":"website","elo":920,"win_rate":38.3,"rank":112}]}},{"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":"0.0000005","completion":"0.00000215","input_cache_read":"0.00000035"},"top_provider":{"context_length":163840,"max_completion_tokens":32768,"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"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1168,"win_rate":53.4,"rank":58},{"arena":"models","category":"codecategories","elo":1169,"win_rate":52.6,"rank":65},{"arena":"models","category":"dataviz","elo":1208,"win_rate":60.7,"rank":44},{"arena":"models","category":"gamedev","elo":1154,"win_rate":49.5,"rank":65},{"arena":"models","category":"svg","elo":1088,"win_rate":48.7,"rank":54},{"arena":"models","category":"uicomponent","elo":1141,"win_rate":55.1,"rank":66},{"arena":"models","category":"website","elo":1174,"win_rate":52.7,"rank":64}]},"reasoning":{"mandatory":true}},{"id":"google/gemma-3n-e4b-it","canonical_slug":"google/gemma-3n-e4b-it","hugging_face_id":"google/gemma-3n-E4B-it","name":"Google: Gemma 3n 4B","created":1747776824,"description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...","context_length":32000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000006","completion":"0.00000012"},"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-3n-e4b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":3.2,"agentic_index":null}}},{"id":"arcee-ai/virtuoso-large","canonical_slug":"arcee-ai/virtuoso-large","hugging_face_id":"","name":"Arcee AI: Virtuoso Large","created":1746478885,"description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000012"},"top_provider":{"context_length":131072,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-03-31","expiration_date":null,"links":{"details":"/api/v1/models/arcee-ai/virtuoso-large/endpoints"}},{"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","response_format","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"}},{"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":131072,"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","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"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":972,"win_rate":37.5,"rank":108},{"arena":"models","category":"dataviz","elo":997,"win_rate":39,"rank":97},{"arena":"models","category":"gamedev","elo":954,"win_rate":33.8,"rank":105},{"arena":"models","category":"uicomponent","elo":982,"win_rate":42.4,"rank":97},{"arena":"models","category":"website","elo":979,"win_rate":37.7,"rank":108}]},"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":131702,"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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":10.4,"coding_index":13.8,"agentic_index":1.8}},"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_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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":11.5,"coding_index":15.3,"agentic_index":1.8}},"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":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000008"},"top_provider":{"context_length":1048576,"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":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":957,"win_rate":40.2,"rank":99},{"arena":"models","category":"codecategories","elo":910,"win_rate":35.8,"rank":111},{"arena":"models","category":"dataviz","elo":912,"win_rate":38.4,"rank":108},{"arena":"models","category":"gamedev","elo":894,"win_rate":33.7,"rank":109},{"arena":"models","category":"uicomponent","elo":936,"win_rate":40.8,"rank":103},{"arena":"models","category":"website","elo":896,"win_rate":34.4,"rank":114}],"artificial_analysis":{"intelligence_index":14.3,"coding_index":16.3,"agentic_index":1.3}}},{"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":10000000,"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"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":820,"win_rate":26.6,"rank":114},{"arena":"models","category":"dataviz","elo":925,"win_rate":39.3,"rank":106},{"arena":"models","category":"gamedev","elo":829,"win_rate":27.4,"rank":111},{"arena":"models","category":"uicomponent","elo":805,"win_rate":25.5,"rank":108},{"arena":"models","category":"website","elo":775,"win_rate":22.7,"rank":120}],"artificial_analysis":{"intelligence_index":10,"coding_index":8.2,"agentic_index":1.1}}},{"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":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000024","completion":"0.0000009","input_cache_read":"0.000000135"},"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","response_format","seed","stop","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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":15.4,"coding_index":21.2,"agentic_index":1.5}}},{"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":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","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"}},{"id":"google/gemma-3-4b-it","canonical_slug":"google/gemma-3-4b-it","hugging_face_id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000005","completion":"0.0000001"},"top_provider":{"context_length":131072,"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":{},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-3-4b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":2.7,"agentic_index":null}}},{"id":"google/gemma-3-12b-it","canonical_slug":"google/gemma-3-12b-it","hugging_face_id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000005","completion":"0.00000015"},"top_provider":{"context_length":131072,"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/google/gemma-3-12b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":5.5,"coding_index":5.8,"agentic_index":0.3}}},{"id":"google/gemma-3-27b-it","canonical_slug":"google/gemma-3-27b-it","hugging_face_id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000008","completion":"0.00000045","input_cache_read":"0.00000004"},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"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":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-08-31","expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-3-27b-it/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3}}},{"id":"thedrummer/skyfall-36b-v2","canonical_slug":"thedrummer/skyfall-36b-v2","hugging_face_id":"TheDrummer/Skyfall-36B-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000055","completion":"0.0000008","input_cache_read":"0.00000025"},"top_provider":{"context_length":32768,"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","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/thedrummer/skyfall-36b-v2/endpoints"}},{"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":131072,"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":128000,"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"}},{"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"}},{"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":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":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/microsoft/phi-4/endpoints"}},{"id":"deepseek/deepseek-chat","canonical_slug":"deepseek/deepseek-chat-v3","hugging_face_id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek: DeepSeek V3","created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000032","completion":"0.00000089"},"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","response_format","seed","stop","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/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1144,"win_rate":50.7,"rank":64},{"arena":"models","category":"codecategories","elo":1139,"win_rate":48.5,"rank":78},{"arena":"models","category":"dataviz","elo":1127,"win_rate":51.4,"rank":77},{"arena":"models","category":"gamedev","elo":1110,"win_rate":43.9,"rank":80},{"arena":"models","category":"svg","elo":1026,"win_rate":38.8,"rank":72},{"arena":"models","category":"uicomponent","elo":1130,"win_rate":52.8,"rank":70},{"arena":"models","category":"website","elo":1145,"win_rate":48.5,"rank":76}]}},{"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":"0.0000001","completion":"0.00000032"},"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-3.3-70b-instruct/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3}}},{"id":"openai/gpt-4o-2024-11-20","canonical_slug":"openai/gpt-4o-2024-11-20","hugging_face_id":"","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-2024-11-20/endpoints"}},{"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":128000,"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":32768,"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":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints"}},{"id":"anthracite-org/magnum-v4-72b","canonical_slug":"anthracite-org/magnum-v4-72b","hugging_face_id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.000003","completion":"0.000005"},"top_provider":{"context_length":16384,"max_completion_tokens":2048,"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","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/anthracite-org/magnum-v4-72b/endpoints"}},{"id":"qwen/qwen-2.5-7b-instruct","canonical_slug":"qwen/qwen-2.5-7b-instruct","hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen: Qwen2.5 7B Instruct","created":1729036800,"description":"Qwen2.5 7B 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":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000003","completion":"0.0000003"},"top_provider":{"context_length":32768,"max_completion_tokens":2048,"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":{"temperature":null,"top_p":null,"frequency_penalty":null},"supported_voices":null,"knowledge_cutoff":"2024-06-30","expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-2.5-7b-instruct/endpoints"}},{"id":"thedrummer/rocinante-12b","canonical_slug":"thedrummer/rocinante-12b","hugging_face_id":"TheDrummer/Rocinante-12B-v1.1","name":"TheDrummer: Rocinante 12B","created":1727654400,"description":"Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000025","completion":"0.0000005"},"top_provider":{"context_length":65536,"max_completion_tokens":65536,"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":"2024-04-30","expiration_date":null,"links":{"details":"/api/v1/models/thedrummer/rocinante-12b/endpoints"}},{"id":"meta-llama/llama-3.2-1b-instruct","canonical_slug":"meta-llama/llama-3.2-1b-instruct","hugging_face_id":"meta-llama/Llama-3.2-1B-Instruct","name":"Meta: Llama 3.2 1B Instruct","created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.000000027","completion":"0.000000201"},"top_provider":{"context_length":60000,"max_completion_tokens":60000,"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":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints"}},{"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":131072,"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","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"}},{"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":131072,"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"}},{"id":"sao10k/l3.1-euryale-70b","canonical_slug":"sao10k/l3.1-euryale-70b","hugging_face_id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000085","completion":"0.00000085"},"top_provider":{"context_length":131072,"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":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/sao10k/l3.1-euryale-70b/endpoints"}},{"id":"nousresearch/hermes-3-llama-3.1-70b","canonical_slug":"nousresearch/hermes-3-llama-3.1-70b","hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-70B","name":"Nous: Hermes 3 70B Instruct","created":1723939200,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"chatml"},"pricing":{"prompt":"0.0000007","completion":"0.0000007"},"top_provider":{"context_length":131072,"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":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints"}},{"id":"nousresearch/hermes-3-llama-3.1-405b","canonical_slug":"nousresearch/hermes-3-llama-3.1-405b","hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-405B","name":"Nous: Hermes 3 405B Instruct","created":1723766400,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"chatml"},"pricing":{"prompt":"0.000001","completion":"0.000001"},"top_provider":{"context_length":131072,"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":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints"}},{"id":"sao10k/l3-lunaris-8b","canonical_slug":"sao10k/l3-lunaris-8b","hugging_face_id":"Sao10K/L3-8B-Lunaris-v1","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000004","completion":"0.00000005"},"top_provider":{"context_length":8192,"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":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/sao10k/l3-lunaris-8b/endpoints"}},{"id":"openai/gpt-4o-2024-08-06","canonical_slug":"openai/gpt-4o-2024-08-06","hugging_face_id":null,"name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-2024-08-06/endpoints"}},{"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":"0.0000004","completion":"0.0000004"},"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-3.1-70b-instruct/endpoints"}},{"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"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5}}},{"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":"mistral"},"pricing":{"prompt":"0.000000019","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"}},{"id":"openai/gpt-4o-mini","canonical_slug":"openai/gpt-4o-mini","hugging_face_id":null,"name":"OpenAI: GPT-4o-mini","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":11.4,"agentic_index":1}}},{"id":"openai/gpt-4o-mini-2024-07-18","canonical_slug":"openai/gpt-4o-mini-2024-07-18","hugging_face_id":null,"name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints"}},{"id":"openai/gpt-4o","canonical_slug":"openai/gpt-4o","hugging_face_id":null,"name":"OpenAI: GPT-4o","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":925,"win_rate":39.2,"rank":100},{"arena":"models","category":"codecategories","elo":891,"win_rate":34.8,"rank":112},{"arena":"models","category":"dataviz","elo":887,"win_rate":36,"rank":109},{"arena":"models","category":"gamedev","elo":962,"win_rate":42.3,"rank":104},{"arena":"models","category":"uicomponent","elo":922,"win_rate":38.1,"rank":104},{"arena":"models","category":"website","elo":856,"win_rate":31.5,"rank":117}]}},{"id":"openai/gpt-4o-2024-05-13","canonical_slug":"openai/gpt-4o-2024-05-13","hugging_face_id":null,"name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000015"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-10-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4o-2024-05-13/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":24.2,"agentic_index":null}}},{"id":"openai/gpt-4-turbo","canonical_slug":"openai/gpt-4-turbo","hugging_face_id":null,"name":"OpenAI: GPT-4 Turbo","created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00003"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4-turbo/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":21.5,"agentic_index":null}}},{"id":"openai/gpt-3.5-turbo-0613","canonical_slug":"openai/gpt-3.5-turbo-0613","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000002"},"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints"}},{"id":"openai/gpt-4-turbo-preview","canonical_slug":"openai/gpt-4-turbo-preview","hugging_face_id":null,"name":"OpenAI: GPT-4 Turbo Preview","created":1706140800,"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00003"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-12-31","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4-turbo-preview/endpoints"}},{"id":"openai/gpt-3.5-turbo-instruct","canonical_slug":"openai/gpt-3.5-turbo-instruct","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo Instruct","created":1695859200,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":"chatml"},"pricing":{"prompt":"0.0000015","completion":"0.000002"},"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints"}},{"id":"openai/gpt-3.5-turbo-16k","canonical_slug":"openai/gpt-3.5-turbo-16k","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000004"},"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints"}},{"id":"mancer/weaver","canonical_slug":"mancer/weaver","hugging_face_id":null,"name":"Mancer: Weaver (alpha)","created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","context_length":8000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.0000005","completion":"0.00000075"},"top_provider":{"context_length":8000,"max_completion_tokens":2000,"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","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-06-30","expiration_date":null,"links":{"details":"/api/v1/models/mancer/weaver/endpoints"}},{"id":"undi95/remm-slerp-l2-13b","canonical_slug":"undi95/remm-slerp-l2-13b","hugging_face_id":"Undi95/ReMM-SLERP-L2-13B","name":"ReMM SLERP 13B","created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.00000045","completion":"0.00000065"},"top_provider":{"context_length":6144,"max_completion_tokens":2048,"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","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-06-30","expiration_date":null,"links":{"details":"/api/v1/models/undi95/remm-slerp-l2-13b/endpoints"}},{"id":"gryphe/mythomax-l2-13b","canonical_slug":"gryphe/mythomax-l2-13b","hugging_face_id":"Gryphe/MythoMax-L2-13b","name":"MythoMax 13B","created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.00000008","completion":"0.00000011"},"top_provider":{"context_length":4096,"max_completion_tokens":4096,"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","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2023-06-30","expiration_date":null,"links":{"details":"/api/v1/models/gryphe/mythomax-l2-13b/endpoints"}},{"id":"openai/gpt-3.5-turbo","canonical_slug":"openai/gpt-3.5-turbo","hugging_face_id":null,"name":"OpenAI: GPT-3.5 Turbo","created":1685232000,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.0000015"},"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-3.5-turbo/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":10.7,"agentic_index":null}}},{"id":"openai/gpt-4","canonical_slug":"openai/gpt-4","hugging_face_id":null,"name":"OpenAI: GPT-4","created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","context_length":8191,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0.00006"},"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2021-09-30","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-4/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":13.1,"agentic_index":null}}}],"total_count":115,"links":{"next":null}}