{"data":[{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash-20260826","hugging_face_id":"zai-org/GLM-5.3-Flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1310720,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003"},"top_provider":{"context_length":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","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2098-12-31","links":{"details":"/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1368,"win_rate":63.5,"rank":5},{"arena":"models","category":"asciiart","elo":1296,"win_rate":57.6,"rank":7},{"arena":"models","category":"codecategories","elo":1305,"win_rate":51.9,"rank":14},{"arena":"models","category":"dataviz","elo":1273,"win_rate":50.8,"rank":22},{"arena":"models","category":"gamedev","elo":1329,"win_rate":51.8,"rank":9},{"arena":"models","category":"svg","elo":1312,"win_rate":57.8,"rank":7},{"arena":"models","category":"uicomponent","elo":1338,"win_rate":57.5,"rank":7},{"arena":"models","category":"website","elo":1291,"win_rate":50.2,"rank":17}],"artificial_analysis":{"intelligence_index":41.9,"coding_index":71.5,"agentic_index":51.2}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"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":1050000,"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":"0.0000000028"},"top_provider":{"context_length":1048576,"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":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":1241,"win_rate":51.1,"rank":34},{"arena":"models","category":"asciiart","elo":1164,"win_rate":46.5,"rank":38},{"arena":"models","category":"codecategories","elo":1275,"win_rate":54.2,"rank":27},{"arena":"models","category":"dataviz","elo":1268,"win_rate":54.8,"rank":23},{"arena":"models","category":"gamedev","elo":1268,"win_rate":54.2,"rank":29},{"arena":"models","category":"svg","elo":1200,"win_rate":51.3,"rank":31},{"arena":"models","category":"uicomponent","elo":1273,"win_rate":54.7,"rank":28},{"arena":"models","category":"website","elo":1279,"win_rate":54.3,"rank":26}],"artificial_analysis":{"intelligence_index":22.3,"coding_index":56.8,"agentic_index":17.4}},"reasoning":{"mandatory":false}},{"id":"openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Luna","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000012","web_search":"0.01","input_cache_read":"0.00000002","input_cache_write":"0.00000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000004","completion":"0.0000018","input_cache_read":"0.00000004","input_cache_write":"0.0000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.5,"coding_index":71.4,"agentic_index":42.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-20260731","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","context_length":1310720,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000065","completion":"0.00000018","input_cache_read":"0.000000016"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":[],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1238,"win_rate":49,"rank":36},{"arena":"models","category":"asciiart","elo":1116,"win_rate":34,"rank":56},{"arena":"models","category":"codecategories","elo":1245,"win_rate":46.6,"rank":40},{"arena":"models","category":"dataviz","elo":1197,"win_rate":41.2,"rank":55},{"arena":"models","category":"gamedev","elo":1234,"win_rate":44.9,"rank":38},{"arena":"models","category":"svg","elo":1214,"win_rate":45.3,"rank":24},{"arena":"models","category":"uicomponent","elo":1251,"win_rate":46.8,"rank":36},{"arena":"models","category":"website","elo":1251,"win_rate":46.9,"rank":38}],"artificial_analysis":{"intelligence_index":34.5,"coding_index":69.1,"agentic_index":41.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"high"}},{"id":"tencent/hy4-preview","canonical_slug":"tencent/hy4-preview-20260827","hugging_face_id":"tencent/Hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000834","completion":"0.000002501","input_cache_read":"0.000000042"},"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy4-preview-20260827/endpoints"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"google/gemini-3.8-flash","canonical_slug":"google/gemini-3.8-flash-20260902","hugging_face_id":null,"name":"Google: Gemini 3.8 Flash","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.8-flash-20260902/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"python-pptxslides","elo":1173,"win_rate":39,"rank":19},{"arena":"models","category":"3d","elo":1322,"win_rate":55.1,"rank":13},{"arena":"models","category":"codecategories","elo":1322,"win_rate":55.6,"rank":8},{"arena":"models","category":"dataviz","elo":1262,"win_rate":49.8,"rank":26},{"arena":"models","category":"gamedev","elo":1341,"win_rate":57.5,"rank":8},{"arena":"models","category":"uicomponent","elo":1340,"win_rate":57.2,"rank":6},{"arena":"models","category":"website","elo":1315,"win_rate":55.1,"rank":8}],"artificial_analysis":{"intelligence_index":41.2,"coding_index":76.3,"agentic_index":41.1}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"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":"0.000000966","completion":"0.000003036","input_cache_read":"0.0000001932"},"top_provider":{"context_length":1000000,"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":1209,"win_rate":49.4,"rank":10},{"arena":"agents","category":"androidnative","elo":1193,"win_rate":53,"rank":17},{"arena":"agents","category":"fullstack","elo":1248,"win_rate":61.2,"rank":11},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":16},{"arena":"agents","category":"htmlslides","elo":1178,"win_rate":49.6,"rank":13},{"arena":"agents","category":"mobileapps","elo":1191,"win_rate":51.3,"rank":19},{"arena":"agents","category":"python-pptxslides","elo":1195,"win_rate":48.8,"rank":16},{"arena":"agents","category":"webapps","elo":1240,"win_rate":56.4,"rank":12},{"arena":"models","category":"3d","elo":1326,"win_rate":55.8,"rank":11},{"arena":"models","category":"asciiart","elo":1235,"win_rate":50.6,"rank":17},{"arena":"models","category":"codecategories","elo":1312,"win_rate":54.7,"rank":10},{"arena":"models","category":"dataviz","elo":1313,"win_rate":54.3,"rank":9},{"arena":"models","category":"gamedev","elo":1303,"win_rate":52.3,"rank":15},{"arena":"models","category":"svg","elo":1247,"win_rate":52.7,"rank":15},{"arena":"models","category":"uicomponent","elo":1308,"win_rate":55.6,"rank":14},{"arena":"models","category":"website","elo":1307,"win_rate":55,"rank":11}],"artificial_analysis":{"intelligence_index":null,"coding_index":68.8,"agentic_index":39.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"meta/muse-spark-1.3-contributor","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","hugging_face_id":null,"name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","web_search":"0.0025","input_cache_read":"0.000000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3-20260715","hugging_face_id":"moonshotai/Kimi-K3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000234","completion":"0.0000117","input_cache_read":"0.000000261"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3-20260715/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1250,"win_rate":54.4,"rank":3},{"arena":"agents","category":"androidnative","elo":1257,"win_rate":54.4,"rank":6},{"arena":"agents","category":"fullstack","elo":1331,"win_rate":63.4,"rank":3},{"arena":"agents","category":"godotgamedev","elo":1199,"win_rate":48.5,"rank":10},{"arena":"agents","category":"htmlslides","elo":1259,"win_rate":59.6,"rank":2},{"arena":"agents","category":"mobileapps","elo":1277,"win_rate":57.7,"rank":3},{"arena":"agents","category":"python-pptxslides","elo":1273,"win_rate":59.1,"rank":4},{"arena":"agents","category":"webapps","elo":1317,"win_rate":61.1,"rank":2},{"arena":"models","category":"3d","elo":1426,"win_rate":69,"rank":1},{"arena":"models","category":"codecategories","elo":1389,"win_rate":64.9,"rank":1},{"arena":"models","category":"dataviz","elo":1365,"win_rate":64.1,"rank":2},{"arena":"models","category":"gamedev","elo":1402,"win_rate":62.8,"rank":2},{"arena":"models","category":"svg","elo":1337,"win_rate":63.3,"rank":3},{"arena":"models","category":"uicomponent","elo":1369,"win_rate":62.9,"rank":2},{"arena":"models","category":"website","elo":1354,"win_rate":61.2,"rank":2}],"artificial_analysis":{"intelligence_index":43.8,"coding_index":76.2,"agentic_index":50.6}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3-20260816","hugging_face_id":"zai-org/GLM-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1310720,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-20260816/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1394,"win_rate":68.1,"rank":4},{"arena":"models","category":"codecategories","elo":1332,"win_rate":58.3,"rank":5},{"arena":"models","category":"dataviz","elo":1262,"win_rate":51.2,"rank":25},{"arena":"models","category":"gamedev","elo":1379,"win_rate":64.6,"rank":3},{"arena":"models","category":"svg","elo":1324,"win_rate":60.8,"rank":6},{"arena":"models","category":"uicomponent","elo":1344,"win_rate":59.7,"rank":5},{"arena":"models","category":"website","elo":1319,"win_rate":56.4,"rank":6},{"arena":"agents","category":"htmlslides","elo":1189,"win_rate":39.1,"rank":9},{"arena":"agents","category":"mobileapps","elo":1231,"win_rate":54.4,"rank":13},{"arena":"agents","category":"python-pptxslides","elo":1256,"win_rate":51.2,"rank":7}],"artificial_analysis":{"intelligence_index":44.9,"coding_index":74.8,"agentic_index":53.4}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"upstage/solar-pro4","canonical_slug":"upstage/solar-pro4-20260810","hugging_face_id":null,"name":"Upstage: Solar Pro 4","created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000009","completion":"0.00000036","input_cache_read":"0.000000018"},"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/upstage/solar-pro4-20260810/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"webapps","elo":1125,"win_rate":30.3,"rank":31},{"arena":"models","category":"3d","elo":1207,"win_rate":46.4,"rank":46},{"arena":"models","category":"codecategories","elo":1196,"win_rate":38.9,"rank":54},{"arena":"models","category":"dataviz","elo":1195,"win_rate":41.5,"rank":56},{"arena":"models","category":"gamedev","elo":1193,"win_rate":39.8,"rank":55},{"arena":"models","category":"uicomponent","elo":1165,"win_rate":35.5,"rank":66},{"arena":"models","category":"website","elo":1188,"win_rate":37.4,"rank":65}],"artificial_analysis":{"intelligence_index":null,"coding_index":52.7,"agentic_index":null}},"reasoning":{"mandatory":false}},{"id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000008708","completion":"0.00000017416","input_cache_read":"0.000000017416"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1217,"win_rate":49.3,"rank":44},{"arena":"models","category":"asciiart","elo":1131,"win_rate":42.8,"rank":51},{"arena":"models","category":"codecategories","elo":1220,"win_rate":48.9,"rank":47},{"arena":"models","category":"dataviz","elo":1142,"win_rate":40.6,"rank":79},{"arena":"models","category":"gamedev","elo":1219,"win_rate":50.2,"rank":43},{"arena":"models","category":"svg","elo":1181,"win_rate":48.4,"rank":36},{"arena":"models","category":"uicomponent","elo":1179,"win_rate":44.7,"rank":62},{"arena":"models","category":"website","elo":1220,"win_rate":49.1,"rank":48}],"artificial_analysis":{"intelligence_index":24.8,"coding_index":52,"agentic_index":27.9}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"}},{"id":"tencent/hy3","canonical_slug":"tencent/hy3-20260706","hugging_face_id":"tencent/Hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033","overrides":[{"utc_start":0,"utc_end":1600,"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033"},{"utc_start":1600,"utc_end":0,"prompt":"0.0000000825","completion":"0.00000033","input_cache_read":"0.000000020625"}]},"top_provider":{"context_length":262144,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy3-20260706/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1205,"win_rate":43.8,"rank":47},{"arena":"models","category":"codecategories","elo":1191,"win_rate":41.1,"rank":58},{"arena":"models","category":"dataviz","elo":1141,"win_rate":36.1,"rank":81},{"arena":"models","category":"gamedev","elo":1159,"win_rate":38.6,"rank":67},{"arena":"models","category":"uicomponent","elo":1178,"win_rate":40.2,"rank":63},{"arena":"models","category":"website","elo":1194,"win_rate":41.3,"rank":62}]},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"minimax/minimax-m3","canonical_slug":"minimax/minimax-m3-20260531","hugging_face_id":"MiniMaxAI/Minimax-M3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"top_provider":{"context_length":524288,"max_completion_tokens":512000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1158,"win_rate":44.5,"rank":19},{"arena":"agents","category":"androidnative","elo":1170,"win_rate":44,"rank":23},{"arena":"agents","category":"fullstack","elo":1207,"win_rate":48.7,"rank":18},{"arena":"agents","category":"htmlslides","elo":1181,"win_rate":46.3,"rank":11},{"arena":"agents","category":"mobileapps","elo":1189,"win_rate":46,"rank":21},{"arena":"agents","category":"python-pptxslides","elo":1205,"win_rate":46.9,"rank":14},{"arena":"agents","category":"webapps","elo":1220,"win_rate":48.6,"rank":18},{"arena":"models","category":"3d","elo":1239,"win_rate":51.5,"rank":35},{"arena":"models","category":"asciiart","elo":1184,"win_rate":47.7,"rank":30},{"arena":"models","category":"codecategories","elo":1264,"win_rate":52,"rank":31},{"arena":"models","category":"dataviz","elo":1249,"win_rate":51.6,"rank":34},{"arena":"models","category":"gamedev","elo":1235,"win_rate":47.2,"rank":37},{"arena":"models","category":"svg","elo":1195,"win_rate":48.3,"rank":32},{"arena":"models","category":"uicomponent","elo":1260,"win_rate":51.6,"rank":32},{"arena":"models","category":"website","elo":1271,"win_rate":52.6,"rank":29}],"artificial_analysis":{"intelligence_index":29.6,"coding_index":58.6,"agentic_index":30.8}},"reasoning":{"mandatory":false}},{"id":"openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol-20260709","hugging_face_id":null,"name":"OpenAI: GPT-5.6 Sol","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000004","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":47.1,"coding_index":77.4,"agentic_index":50.5}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"google/gemini-3.7-flash","canonical_slug":"google/gemini-3.7-flash-20260813","hugging_face_id":null,"name":"Google: Gemini 3.7 Flash","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","audio":"0.00000075","input_audio_cache":"0.000000075","web_search":"0.014","internal_reasoning":"0.00000375","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.7-flash-20260813/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1235,"win_rate":52.1,"rank":5},{"arena":"agents","category":"androidnative","elo":1260,"win_rate":53.7,"rank":5},{"arena":"agents","category":"fullstack","elo":1215,"win_rate":44.8,"rank":16},{"arena":"agents","category":"mobileapps","elo":1256,"win_rate":53.3,"rank":6},{"arena":"agents","category":"webapps","elo":1243,"win_rate":48.7,"rank":11},{"arena":"models","category":"3d","elo":1336,"win_rate":59.6,"rank":10},{"arena":"models","category":"asciiart","elo":1252,"win_rate":52.2,"rank":16},{"arena":"models","category":"codecategories","elo":1320,"win_rate":57.2,"rank":9},{"arena":"models","category":"dataviz","elo":1328,"win_rate":58.6,"rank":6},{"arena":"models","category":"gamedev","elo":1341,"win_rate":57.2,"rank":7},{"arena":"models","category":"uicomponent","elo":1309,"win_rate":53.6,"rank":13},{"arena":"models","category":"website","elo":1315,"win_rate":57,"rank":7}],"artificial_analysis":{"intelligence_index":39.4,"coding_index":76.1,"agentic_index":36.4}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek/deepseek-v4-pro-20260813","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.0000010494","completion":"0.0000031482","input_cache_read":"0.00000003498"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260813/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":36.3,"coding_index":68.8,"agentic_index":42.3}},"reasoning":{"mandatory":false,"supported_efforts":["max","high","low"],"default_effort":"high"}},{"id":"anthropic/claude-opus-5","canonical_slug":"anthropic/claude-opus-5-20260723","hugging_face_id":null,"name":"Claude Opus 5","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000025","web_search":"0.01","input_cache_read":"0.0000005","input_cache_write":"0.00000625","input_cache_write_1h":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1265,"win_rate":54.3,"rank":2},{"arena":"agents","category":"androidnative","elo":1268,"win_rate":54.8,"rank":3},{"arena":"agents","category":"fullstack","elo":1331,"win_rate":62.3,"rank":2},{"arena":"agents","category":"mobileapps","elo":1348,"win_rate":67.1,"rank":1},{"arena":"agents","category":"python-pptxslides","elo":1265,"win_rate":54,"rank":5},{"arena":"agents","category":"webapps","elo":1277,"win_rate":56.1,"rank":4},{"arena":"models","category":"3d","elo":1364,"win_rate":61.7,"rank":6},{"arena":"models","category":"asciiart","elo":1386,"win_rate":70.3,"rank":1},{"arena":"models","category":"codecategories","elo":1339,"win_rate":58.4,"rank":4},{"arena":"models","category":"dataviz","elo":1355,"win_rate":61.2,"rank":4},{"arena":"models","category":"gamedev","elo":1366,"win_rate":59.7,"rank":4},{"arena":"models","category":"svg","elo":1351,"win_rate":62.2,"rank":2},{"arena":"models","category":"uicomponent","elo":1360,"win_rate":61.3,"rank":3},{"arena":"models","category":"website","elo":1320,"win_rate":56.5,"rank":5}],"artificial_analysis":{"intelligence_index":50.7,"coding_index":78,"agentic_index":56.2}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra (free)","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1163,"win_rate":40.6,"rank":62},{"arena":"models","category":"asciiart","elo":1101,"win_rate":37.3,"rank":59},{"arena":"models","category":"codecategories","elo":1154,"win_rate":36.3,"rank":77},{"arena":"models","category":"dataviz","elo":1156,"win_rate":38.4,"rank":74},{"arena":"models","category":"gamedev","elo":1153,"win_rate":36.9,"rank":72},{"arena":"models","category":"svg","elo":1099,"win_rate":35.6,"rank":60},{"arena":"models","category":"uicomponent","elo":1151,"win_rate":37.3,"rank":73},{"arena":"models","category":"website","elo":1144,"win_rate":34.4,"rank":84}],"artificial_analysis":{"intelligence_index":23.4,"coding_index":49.3,"agentic_index":21.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium"],"default_effort":"high"}},{"id":"deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro-20260423","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000954738","completion":"0.000001909476","input_cache_read":"0.0000000795615"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":1},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":948,"win_rate":22.1,"rank":42},{"arena":"agents","category":"godotgamedev","elo":1059,"win_rate":34,"rank":26},{"arena":"agents","category":"webapps","elo":1000,"win_rate":26.4,"rank":38},{"arena":"models","category":"3d","elo":1283,"win_rate":56.9,"rank":22},{"arena":"models","category":"asciiart","elo":1170,"win_rate":46.5,"rank":34},{"arena":"models","category":"codecategories","elo":1256,"win_rate":52,"rank":35},{"arena":"models","category":"dataviz","elo":1218,"win_rate":48.6,"rank":47},{"arena":"models","category":"gamedev","elo":1252,"win_rate":52.4,"rank":33},{"arena":"models","category":"svg","elo":1165,"win_rate":45.4,"rank":43},{"arena":"models","category":"uicomponent","elo":1237,"win_rate":50.6,"rank":41},{"arena":"models","category":"website","elo":1247,"win_rate":50.7,"rank":39}],"artificial_analysis":{"intelligence_index":30.9,"coding_index":59.4,"agentic_index":27.7}},"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high"],"default_effort":"high"}}],"total_count":20,"links":{"next":null}}