{"data":[{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000002394","completion":"0.000000375","input_cache_read":"0.000000000342"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":24.7,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"xiaomi/mimo-v2.6-flash","canonical_slug":"xiaomi/mimo-v2.6-flash-20260921","hugging_face_id":"XiaomiMiMo/MiMo-V2.6-Flash-RL","name":"Xiaomi: MiMo-V2.6-Flash","created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"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","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":0},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.6-flash-20260921/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":37.9,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false}},{"id":"stepfun/step-5-preview","canonical_slug":"stepfun/step-5-preview-20261008","hugging_face_id":"stepfun-ai/Step-5-Preview","name":"StepFun: Step 5 Preview","created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.0000027","input_cache_read":"0.0000001"},"top_provider":{"context_length":1000000,"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","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-5-preview-20261008/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":43.7,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash-20260826","hugging_face_id":"zai-org/GLM-5.3-Flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003"},"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1316,"win_rate":56.2,"rank":17},{"arena":"models","category":"asciiart","elo":1268,"win_rate":54.6,"rank":12},{"arena":"models","category":"codecategories","elo":1282,"win_rate":49.3,"rank":22},{"arena":"models","category":"dataviz","elo":1261,"win_rate":50.3,"rank":31},{"arena":"models","category":"gamedev","elo":1278,"win_rate":47.1,"rank":24},{"arena":"models","category":"svg","elo":1284,"win_rate":56.6,"rank":11},{"arena":"models","category":"uicomponent","elo":1316,"win_rate":54.6,"rank":14},{"arena":"models","category":"website","elo":1272,"win_rate":48.4,"rank":28}],"artificial_analysis":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"meta/muse-spark-1.3-contributor","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","hugging_face_id":null,"name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","web_search":"0.0025","input_cache_read":"0.000000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints"},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3-20260816","hugging_face_id":"zai-org/GLM-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000079","completion":"0.0000014","input_cache_read":"0.000000078"},"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":1332,"win_rate":59.3,"rank":14},{"arena":"models","category":"asciiart","elo":1213,"win_rate":47.7,"rank":20},{"arena":"models","category":"codecategories","elo":1304,"win_rate":54.1,"rank":15},{"arena":"models","category":"dataviz","elo":1259,"win_rate":51.8,"rank":32},{"arena":"models","category":"gamedev","elo":1311,"win_rate":52.5,"rank":17},{"arena":"models","category":"svg","elo":1293,"win_rate":56.9,"rank":8},{"arena":"models","category":"uicomponent","elo":1314,"win_rate":56.7,"rank":15},{"arena":"models","category":"website","elo":1295,"win_rate":54,"rank":18},{"arena":"agents","category":"htmlslides","elo":1189,"win_rate":39.1,"rank":9},{"arena":"agents","category":"mobileapps","elo":1194,"win_rate":52.2,"rank":19},{"arena":"agents","category":"python-pptxslides","elo":1255,"win_rate":51.2,"rank":8}],"artificial_analysis":{"intelligence_index":44.8,"coding_index":74.8,"agentic_index":53.1}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"deepseek/deepseek-v4.1-flash-1017","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003","overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":0,"utc_end":100,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":100,"utc_end":400,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":400,"utc_end":600,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":600,"utc_end":1000,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":1000,"utc_end":0,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"spreadsheet","elo":1233,"win_rate":51.2,"rank":7},{"arena":"models","category":"3d","elo":1372,"win_rate":60.7,"rank":9},{"arena":"models","category":"asciiart","elo":1244,"win_rate":55,"rank":18},{"arena":"models","category":"codecategories","elo":1335,"win_rate":58.8,"rank":8},{"arena":"models","category":"dataviz","elo":1335,"win_rate":58.8,"rank":9},{"arena":"models","category":"gamedev","elo":1363,"win_rate":62.1,"rank":7},{"arena":"models","category":"uicomponent","elo":1300,"win_rate":54.1,"rank":17},{"arena":"models","category":"website","elo":1312,"win_rate":56.3,"rank":11}],"artificial_analysis":{"intelligence_index":39.5,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"openai/gpt-6-luna","canonical_slug":"openai/gpt-6-luna-20260922","hugging_face_id":null,"name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000005","web_search":"0.01","input_cache_read":"0.00000001","input_cache_write":"0.000000125","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.00000075","input_cache_read":"0.00000002","input_cache_write":"0.00000025"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-6-luna-20260922/endpoints"},"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":38.1,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"anthropic/claude-opus-5.5","canonical_slug":"anthropic/claude-opus-5.5-20260921","hugging_face_id":null,"name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.000005","input_cache_write_1h":"0.000008"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5.5-20260921/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"mobileapps","elo":1312,"win_rate":62.5,"rank":2},{"arena":"agents","category":"spreadsheet","elo":1356,"win_rate":69.8,"rank":2},{"arena":"agents","category":"webapps","elo":1317,"win_rate":60.8,"rank":2},{"arena":"models","category":"3d","elo":1477,"win_rate":71.9,"rank":1},{"arena":"models","category":"codecategories","elo":1390,"win_rate":63.9,"rank":1},{"arena":"models","category":"dataviz","elo":1397,"win_rate":64.7,"rank":1},{"arena":"models","category":"gamedev","elo":1457,"win_rate":71.6,"rank":2},{"arena":"models","category":"svg","elo":1333,"win_rate":52.2,"rank":1},{"arena":"models","category":"uicomponent","elo":1394,"win_rate":65.1,"rank":1},{"arena":"models","category":"website","elo":1336,"win_rate":57.6,"rank":3}],"artificial_analysis":{"intelligence_index":57.6,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"tencent/hy4-preview","canonical_slug":"tencent/hy4-preview-20260827","hugging_face_id":"tencent/Hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000007506","completion":"0.0000022509","input_cache_read":"0.0000000378","overrides":[{"utc_start":0,"utc_end":1600,"prompt":"0.000000834","completion":"0.000002501","input_cache_read":"0.000000042"},{"utc_start":1600,"utc_end":0,"prompt":"0.0000007506","completion":"0.0000022509","input_cache_read":"0.0000000378"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","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":{},"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":"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":"0.000000239","completion":"0.000011936","input_cache_read":"0.00000021"},"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":1252,"win_rate":54.9,"rank":3},{"arena":"agents","category":"androidnative","elo":1256,"win_rate":55.8,"rank":5},{"arena":"agents","category":"fullstack","elo":1315,"win_rate":61.8,"rank":2},{"arena":"agents","category":"godotgamedev","elo":1223,"win_rate":48.2,"rank":14},{"arena":"agents","category":"htmlslides","elo":1256,"win_rate":59.6,"rank":2},{"arena":"agents","category":"mobileapps","elo":1268,"win_rate":57.2,"rank":3},{"arena":"agents","category":"python-pptxslides","elo":1273,"win_rate":59.2,"rank":4},{"arena":"agents","category":"spreadsheet","elo":1054,"win_rate":32.6,"rank":10},{"arena":"agents","category":"webapps","elo":1295,"win_rate":59.3,"rank":6},{"arena":"models","category":"3d","elo":1388,"win_rate":67.2,"rank":8},{"arena":"models","category":"codecategories","elo":1361,"win_rate":62.3,"rank":4},{"arena":"models","category":"dataviz","elo":1350,"win_rate":63.2,"rank":4},{"arena":"models","category":"gamedev","elo":1360,"win_rate":60.6,"rank":8},{"arena":"models","category":"svg","elo":1302,"win_rate":59.3,"rank":5},{"arena":"models","category":"uicomponent","elo":1344,"win_rate":60.1,"rank":6},{"arena":"models","category":"website","elo":1335,"win_rate":59.3,"rank":4}],"artificial_analysis":{"intelligence_index":43.6,"coding_index":76.2,"agentic_index":50}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-20260731","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000004444","completion":"0.00000013332","input_cache_read":"0.000000001414"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":[],"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":1209,"win_rate":48.7,"rank":45},{"arena":"models","category":"asciiart","elo":1090,"win_rate":33.3,"rank":63},{"arena":"models","category":"codecategories","elo":1230,"win_rate":46.4,"rank":51},{"arena":"models","category":"dataviz","elo":1180,"win_rate":41.1,"rank":64},{"arena":"models","category":"gamedev","elo":1208,"win_rate":44.6,"rank":53},{"arena":"models","category":"svg","elo":1185,"win_rate":45.1,"rank":31},{"arena":"models","category":"uicomponent","elo":1235,"win_rate":46.8,"rank":48},{"arena":"models","category":"website","elo":1238,"win_rate":46.7,"rank":51}],"artificial_analysis":{"intelligence_index":34.3,"coding_index":69.1,"agentic_index":41}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"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":"0.0000000341","completion":"0.000007","input_cache_read":"0.000000033"},"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,"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":1206,"win_rate":49,"rank":10},{"arena":"agents","category":"androidnative","elo":1184,"win_rate":53,"rank":18},{"arena":"agents","category":"fullstack","elo":1241,"win_rate":60.5,"rank":12},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":22},{"arena":"agents","category":"htmlslides","elo":1175,"win_rate":49.5,"rank":13},{"arena":"agents","category":"mobileapps","elo":1160,"win_rate":48,"rank":27},{"arena":"agents","category":"python-pptxslides","elo":1195,"win_rate":48.8,"rank":17},{"arena":"agents","category":"webapps","elo":1222,"win_rate":55.8,"rank":16},{"arena":"models","category":"3d","elo":1288,"win_rate":53.3,"rank":21},{"arena":"models","category":"asciiart","elo":1190,"win_rate":46,"rank":29},{"arena":"models","category":"codecategories","elo":1288,"win_rate":50.4,"rank":21},{"arena":"models","category":"dataviz","elo":1285,"win_rate":52,"rank":17},{"arena":"models","category":"gamedev","elo":1268,"win_rate":49.5,"rank":27},{"arena":"models","category":"svg","elo":1214,"win_rate":48.6,"rank":22},{"arena":"models","category":"uicomponent","elo":1296,"win_rate":55.3,"rank":20},{"arena":"models","category":"website","elo":1285,"win_rate":49.5,"rank":23}],"artificial_analysis":{"intelligence_index":33.7,"coding_index":68.8,"agentic_index":38.4}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"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":"0.00000015","completion":"0.0000006","input_cache_read":"0.00000003"},"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","reasoning_effort","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":1105,"win_rate":30,"rank":37},{"arena":"models","category":"3d","elo":1178,"win_rate":46.4,"rank":57},{"arena":"models","category":"codecategories","elo":1182,"win_rate":39,"rank":65},{"arena":"models","category":"dataviz","elo":1177,"win_rate":41.3,"rank":67},{"arena":"models","category":"gamedev","elo":1170,"win_rate":39.9,"rank":68},{"arena":"models","category":"uicomponent","elo":1150,"win_rate":35.5,"rank":77},{"arena":"models","category":"website","elo":1177,"win_rate":37.5,"rank":78}],"artificial_analysis":{"intelligence_index":28.2,"coding_index":52.7,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"xiaomi/mimo-v2.6-pro","canonical_slug":"xiaomi/mimo-v2.6-pro-20260921","hugging_face_id":"XiaomiMiMo/MiMo-V2.6-Pro-RL","name":"Xiaomi: MiMo-V2.6-Pro","created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000435","completion":"0.00000087","input_cache_read":"0.0000000036"},"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,"frequency_penalty":0},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.6-pro-20260921/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"webapps","elo":1290,"win_rate":58.3,"rank":7},{"arena":"models","category":"3d","elo":1331,"win_rate":56.8,"rank":15},{"arena":"models","category":"codecategories","elo":1316,"win_rate":52.5,"rank":11},{"arena":"models","category":"dataviz","elo":1336,"win_rate":58.8,"rank":8},{"arena":"models","category":"gamedev","elo":1313,"win_rate":53.1,"rank":14},{"arena":"models","category":"uicomponent","elo":1339,"win_rate":59.1,"rank":9},{"arena":"models","category":"website","elo":1308,"win_rate":50.7,"rank":13}],"artificial_analysis":{"intelligence_index":46.3,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false}},{"id":"openai/gpt-6.1-sol","canonical_slug":"openai/gpt-6.1-sol-20260929","hugging_face_id":null,"name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000002","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"mobileapps","elo":1200,"win_rate":47.7,"rank":17},{"arena":"agents","category":"spreadsheet","elo":1244,"win_rate":52,"rank":6},{"arena":"models","category":"3d","elo":1463,"win_rate":70.5,"rank":2},{"arena":"models","category":"codecategories","elo":1345,"win_rate":58.3,"rank":6},{"arena":"models","category":"dataviz","elo":1280,"win_rate":50.9,"rank":20},{"arena":"models","category":"gamedev","elo":1389,"win_rate":63.7,"rank":3},{"arena":"models","category":"uicomponent","elo":1330,"win_rate":55.9,"rank":11},{"arena":"models","category":"website","elo":1320,"win_rate":55.7,"rank":6}],"artificial_analysis":{"intelligence_index":51.8,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"upstage/solar-mini4","canonical_slug":"upstage/solar-mini4-20260922","hugging_face_id":null,"name":"Upstage: Solar Mini 4","created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","context_length":524288,"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":"0.000000005"},"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","reasoning_effort","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-mini4-20260922/endpoints"},"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1153,"win_rate":32.2,"rank":83},{"arena":"models","category":"gamedev","elo":1113,"win_rate":28.5,"rank":91},{"arena":"models","category":"website","elo":1160,"win_rate":33.3,"rank":88}],"artificial_analysis":{"intelligence_index":24.1,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"anthropic/claude-sonnet-5.5","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","hugging_face_id":null,"name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5.5-20260928/endpoints"},"benchmarks":{"design_arena":[{"arena":"agents","category":"mobileapps","elo":1262,"win_rate":56.9,"rank":6},{"arena":"agents","category":"spreadsheet","elo":1248,"win_rate":51.7,"rank":5},{"arena":"agents","category":"webapps","elo":1305,"win_rate":60.3,"rank":3},{"arena":"models","category":"3d","elo":1456,"win_rate":69.5,"rank":3},{"arena":"models","category":"codecategories","elo":1364,"win_rate":60.7,"rank":3},{"arena":"models","category":"dataviz","elo":1390,"win_rate":67.2,"rank":2},{"arena":"models","category":"gamedev","elo":1468,"win_rate":72,"rank":1},{"arena":"models","category":"uicomponent","elo":1369,"win_rate":62.2,"rank":3},{"arena":"models","category":"website","elo":1327,"win_rate":56.1,"rank":5}],"artificial_analysis":{"intelligence_index":56,"coding_index":null,"agentic_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"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":1132,"win_rate":38.9,"rank":76},{"arena":"models","category":"asciiart","elo":1099,"win_rate":37.6,"rank":60},{"arena":"models","category":"codecategories","elo":1147,"win_rate":36.1,"rank":87},{"arena":"models","category":"dataviz","elo":1141,"win_rate":37.5,"rank":84},{"arena":"models","category":"gamedev","elo":1138,"win_rate":36.2,"rank":81},{"arena":"models","category":"svg","elo":1069,"win_rate":32.3,"rank":69},{"arena":"models","category":"uicomponent","elo":1139,"win_rate":35.9,"rank":83},{"arena":"models","category":"website","elo":1145,"win_rate":35.2,"rank":96}],"artificial_analysis":{"intelligence_index":22.9,"coding_index":49.3,"agentic_index":20.1}},"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true,"supported_efforts":["high","medium","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":44.3,"rank":19},{"arena":"agents","category":"androidnative","elo":1163,"win_rate":44.3,"rank":24},{"arena":"agents","category":"fullstack","elo":1197,"win_rate":47.2,"rank":19},{"arena":"agents","category":"htmlslides","elo":1180,"win_rate":46.7,"rank":12},{"arena":"agents","category":"mobileapps","elo":1169,"win_rate":45.8,"rank":25},{"arena":"agents","category":"python-pptxslides","elo":1205,"win_rate":47,"rank":14},{"arena":"agents","category":"spreadsheet","elo":1018,"win_rate":48.9,"rank":14},{"arena":"agents","category":"webapps","elo":1200,"win_rate":46.9,"rank":23},{"arena":"models","category":"3d","elo":1209,"win_rate":50.1,"rank":47},{"arena":"models","category":"asciiart","elo":1160,"win_rate":46.4,"rank":37},{"arena":"models","category":"codecategories","elo":1247,"win_rate":50.8,"rank":41},{"arena":"models","category":"dataviz","elo":1235,"win_rate":51.4,"rank":42},{"arena":"models","category":"gamedev","elo":1211,"win_rate":45.7,"rank":50},{"arena":"models","category":"svg","elo":1162,"win_rate":45.2,"rank":39},{"arena":"models","category":"uicomponent","elo":1245,"win_rate":50.6,"rank":43},{"arena":"models","category":"website","elo":1257,"win_rate":51.7,"rank":40}],"artificial_analysis":{"intelligence_index":29.2,"coding_index":58.6,"agentic_index":29.5}},"reasoning":{"mandatory":false}}],"total_count":20,"links":{"next":null}}