{"source":"https://models.dev/api.json","loaded_at":"2026-08-10T17:59:51.394Z","pricing":"provider-declared (per 1M tokens, USD); jishie-measured evals are a later step","total":98,"returned":98,"models":[{"key":"nvidia/microsoft/phi-4-mini-instruct","model":"microsoft/phi-4-mini-instruct","name":"Phi-4-Mini","provider":"nvidia","provider_name":"Nvidia","family":"phi","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/microsoft/phi-4-multimodal-instruct","model":"microsoft/phi-4-multimodal-instruct","name":"Phi 4 Multimodal","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":16384,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/magpie-tts-zeroshot","model":"nvidia/magpie-tts-zeroshot","name":"magpie-tts-zeroshot","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["text","audio"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nv-embedcode-7b-v1","model":"nvidia/nv-embedcode-7b-v1","name":"nv-embedcode-7b-v1","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":2048,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/studiovoice","model":"nvidia/studiovoice","name":"studiovoice","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/sparsedrive","model":"nvidia/sparsedrive","name":"sparsedrive","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/cosmos-reason2-8b","model":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":16384,"modalities":["text","image","video"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/nemotron-nano-12b-v2-vl","model":"nvidia/nemotron-nano-12b-v2-vl","name":"Nemotron Nano 12B v2 VL","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":128000,"modalities":["text","image","video"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/bevformer","model":"nvidia/bevformer","name":"bevformer","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nemotron-3-nano-30b-a3b","model":"nvidia/nemotron-3-nano-30b-a3b","name":"nemotron-3-nano-30b-a3b","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":131072,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/llama-3.3-nemotron-super-49b-v1.5","model":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":65536,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/cosmos-transfer2_5-2b","model":"nvidia/cosmos-transfer2_5-2b","name":"cosmos-transfer2.5-2b","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["text","image","video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/llama-3.1-nemotron-nano-8b-v1","model":"nvidia/llama-3.1-nemotron-nano-8b-v1","name":"Llama 3.1 Nemotron Nano 8B v1","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/active-speaker-detection","model":"nvidia/active-speaker-detection","name":"Active Speaker Detection","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/usdvalidate","model":"nvidia/usdvalidate","name":"usdvalidate","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/llama-3.1-nemotron-safety-guard-8b-v3","model":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","name":"llama-3.1-nemotron-safety-guard-8b-v3","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/llama-3.3-nemotron-super-49b-v1","model":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":65536,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/llama-3.1-nemotron-70b-instruct","model":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/nvidia/nemotron-3-content-safety","model":"nvidia/nemotron-3-content-safety","name":"nemotron-3-content-safety","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/cosmos-transfer1-7b","model":"nvidia/cosmos-transfer1-7b","name":"cosmos-transfer1-7b","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["text","image","video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1","model":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/llama-3_2-nemoretriever-300m-embed-v1","model":"nvidia/llama-3_2-nemoretriever-300m-embed-v1","name":"llama-3_2-nemoretriever-300m-embed-v1","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":2048,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","model":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":256000,"max_output":65536,"modalities":["text","image","video","audio"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/gliner-pii","model":"nvidia/gliner-pii","name":"gliner-pii","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/rerank-qa-mistral-4b","model":"nvidia/rerank-qa-mistral-4b","name":"rerank-qa-mistral-4b","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/llama-3.1-nemotron-nano-vl-8b-v1","model":"nvidia/llama-3.1-nemotron-nano-vl-8b-v1","name":"Llama 3.1 Nemotron Nano VL 8B v1","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":16384,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/synthetic-video-detector","model":"nvidia/synthetic-video-detector","name":"synthetic-video-detector","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/streampetr","model":"nvidia/streampetr","name":"streampetr","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nemotron-voicechat","model":"nvidia/nemotron-voicechat","name":"nemotron-voicechat","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text","audio"],"tool_call":true,"reasoning":false},{"key":"nvidia/nvidia/llama-nemotron-embed-vl-1b-v2","model":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"llama-nemotron-embed-vl-1b-v2","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":2048,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nvidia-nemotron-nano-9b-v2","model":"nvidia/nvidia-nemotron-nano-9b-v2","name":"nvidia-nemotron-nano-9b-v2","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":131072,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/riva-translate-4b-instruct-v1.1","model":"nvidia/riva-translate-4b-instruct-v1.1","name":"riva-translate-4b-instruct-v1_1","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nemotron-content-safety-reasoning-4b","model":"nvidia/nemotron-content-safety-reasoning-4b","name":"nemotron-content-safety-reasoning-4b","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":true},{"key":"nvidia/nvidia/llama-nemotron-rerank-vl-1b-v2","model":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"llama-nemotron-rerank-vl-1b-v2","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nv-embed-v1","model":"nvidia/nv-embed-v1","name":"nv-embed-v1","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":2048,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/cosmos-predict1-5b","model":"nvidia/cosmos-predict1-5b","name":"cosmos-predict1-5b","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["text","image","video"],"tool_call":false,"reasoning":false},{"key":"nvidia/nvidia/nemotron-mini-4b-instruct","model":"nvidia/nemotron-mini-4b-instruct","name":"nemotron-mini-4b-instruct","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/nvidia/usdcode","model":"nvidia/usdcode","name":"usdcode","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/google/google-paligemma","model":"google/google-paligemma","name":"paligemma","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/google/gemma-3-4b-it","model":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","provider":"nvidia","provider_name":"Nvidia","family":"gemma","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":16384,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/google/gemma-2-2b-it","model":"google/gemma-2-2b-it","name":"Gemma 2 2b It","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/google/gemma-3-12b-it","model":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","provider":"nvidia","provider_name":"Nvidia","family":"gemma","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":16384,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/google/gemma-4-31b-it","model":"google/gemma-4-31b-it","name":"Gemma-4-31B-IT","provider":"nvidia","provider_name":"Nvidia","family":"gemma","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":256000,"max_output":16384,"modalities":["text","image","video"],"tool_call":true,"reasoning":true},{"key":"nvidia/google/gemma-3n-e4b-it","model":"google/gemma-3n-e4b-it","name":"Gemma 3n E4b It","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/google/gemma-3n-e2b-it","model":"google/gemma-3n-e2b-it","name":"Gemma 3n E2b It","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/thinkingmachines/inkling","model":"thinkingmachines/inkling","name":"Inkling","provider":"nvidia","provider_name":"Nvidia","family":"ling","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":1048576,"max_output":16384,"modalities":["text","image","audio"],"tool_call":true,"reasoning":true},{"key":"nvidia/baai/bge-m3","model":"baai/bge-m3","name":"BGE M3","provider":"nvidia","provider_name":"Nvidia","family":"bge","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":8192,"max_output":1024,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/qwen/qwen3-coder-480b-a35b-instruct","model":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","provider":"nvidia","provider_name":"Nvidia","family":"qwen","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":66536,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/qwen/qwen-image-edit","model":"qwen/qwen-image-edit","name":"Qwen Image Edit","provider":"nvidia","provider_name":"Nvidia","family":"qwen","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":0,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/qwen/qwen2.5-coder-32b-instruct","model":"qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32b Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/qwen/qwen-image","model":"qwen/qwen-image","name":"Qwen Image","provider":"nvidia","provider_name":"Nvidia","family":"qwen","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":0,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/qwen/qwen3.5-397b-a17b","model":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","provider":"nvidia","provider_name":"Nvidia","family":"qwen","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nvidia/qwen/qwen3.5-122b-a10b","model":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","provider":"nvidia","provider_name":"Nvidia","family":"qwen","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":65536,"modalities":["text","image","video","audio"],"tool_call":true,"reasoning":true},{"key":"nvidia/qwen/qwen3-next-80b-a3b-instruct","model":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","provider":"nvidia","provider_name":"Nvidia","family":"qwen","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/abacusai/dracarys-llama-3.1-70b-instruct","model":"abacusai/dracarys-llama-3.1-70b-instruct","name":"dracarys-llama-3.1-70b-instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/upstage/solar-10.7b-instruct","model":"upstage/solar-10.7b-instruct","name":"solar-10.7b-instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/black-forest-labs/flux_2-klein-4b","model":"black-forest-labs/flux_2-klein-4b","name":"FLUX.2 Klein 4B","provider":"nvidia","provider_name":"Nvidia","family":"flux","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":40960,"max_output":40960,"modalities":["image","text"],"tool_call":false,"reasoning":false},{"key":"nvidia/black-forest-labs/flux_1-schnell","model":"black-forest-labs/flux_1-schnell","name":"FLUX.1-schnell","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":77,"max_output":0,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/black-forest-labs/flux_1-kontext-dev","model":"black-forest-labs/flux_1-kontext-dev","name":"FLUX.1-Kontext-dev","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":40960,"max_output":40960,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/black-forest-labs/flux.1-dev","model":"black-forest-labs/flux.1-dev","name":"FLUX.1-dev","provider":"nvidia","provider_name":"Nvidia","family":"flux","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":4096,"max_output":0,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/mistralai/mistral-medium-3.5-128b","model":"mistralai/mistral-medium-3.5-128b","name":"Mistral Medium 3.5","provider":"nvidia","provider_name":"Nvidia","family":"mistral-medium","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":32768,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nvidia/mistralai/mistral-nemotron","model":"mistralai/mistral-nemotron","name":"mistral-nemotron","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/mistralai/mistral-medium-3-instruct","model":"mistralai/mistral-medium-3-instruct","name":"Mistral Medium 3","provider":"nvidia","provider_name":"Nvidia","family":"mistral-medium","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":32768,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/mistralai/mistral-small-4-119b-2603","model":"mistralai/mistral-small-4-119b-2603","name":"mistral-small-4-119b-2603","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nvidia/mistralai/mistral-large-3-675b-instruct-2512","model":"mistralai/mistral-large-3-675b-instruct-2512","name":"Mistral Large 3 675B Instruct 2512","provider":"nvidia","provider_name":"Nvidia","family":"mistral-large","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":262144,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/mistralai/ministral-14b-instruct-2512","model":"mistralai/ministral-14b-instruct-2512","name":"Ministral 3 14B Instruct 2512","provider":"nvidia","provider_name":"Nvidia","family":"ministral","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":16384,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/mistralai/mixtral-8x22b-instruct","model":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":65536,"max_output":13108,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/mistralai/magistral-small-2506","model":"mistralai/magistral-small-2506","name":"Magistral Small 2506","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":32768,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/mistralai/mixtral-8x7b-instruct","model":"mistralai/mixtral-8x7b-instruct","name":"Mistral: Mixtral 8x7B Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/mistralai/mistral-7b-instruct-v0.3","model":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":65536,"max_output":65536,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/bytedance/seed-oss-36b-instruct","model":"bytedance/seed-oss-36b-instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","provider":"nvidia","provider_name":"Nvidia","family":"seed","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262000,"max_output":262000,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/llama-3.1-70b-instruct","model":"meta/llama-3.1-70b-instruct","name":"Llama 3.1 70b Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/llama-4-maverick-17b-128e-instruct","model":"meta/llama-4-maverick-17b-128e-instruct","name":"Llama 4 Maverick 17b 128e Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/llama-guard-4-12b","model":"meta/llama-guard-4-12b","name":"Llama Guard 4 12B","provider":"nvidia","provider_name":"Nvidia","family":"llama","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":16384,"modalities":["text","image"],"tool_call":false,"reasoning":false},{"key":"nvidia/meta/llama-3.2-1b-instruct","model":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1b Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/llama-3.3-70b-instruct","model":"meta/llama-3.3-70b-instruct","name":"Llama 3.3 70b Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/llama-3.2-3b-instruct","model":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","provider":"nvidia","provider_name":"Nvidia","family":"llama","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":32000,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/meta/llama-3.2-90b-vision-instruct","model":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","provider":"nvidia","provider_name":"Nvidia","family":"llama","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/esmfold","model":"meta/esmfold","name":"esmfold","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/meta/llama-3.1-8b-instruct","model":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","provider":"nvidia","provider_name":"Nvidia","family":"llama","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":16000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/llama-3.2-11b-vision-instruct","model":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11b Vision Instruct","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nvidia/meta/esm2-650m","model":"meta/esm2-650m","name":"esm2-650m","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nvidia/poolside/laguna-xs-2.1","model":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","provider":"nvidia","provider_name":"Nvidia","family":"laguna","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/stepfun-ai/step-3.5-flash","model":"stepfun-ai/step-3.5-flash","name":"Step 3.5 Flash","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":256000,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/stepfun-ai/step-3.7-flash","model":"stepfun-ai/step-3.7-flash","name":"Step 3.7 Flash","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":256000,"max_output":16384,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nvidia/z-ai/glm-5.2","model":"z-ai/glm-5.2","name":"GLM-5.2","provider":"nvidia","provider_name":"Nvidia","family":"glm","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":1000000,"max_output":131072,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/moonshotai/kimi-k2.6","model":"moonshotai/kimi-k2.6","name":"Kimi K2.6","provider":"nvidia","provider_name":"Nvidia","family":"kimi-k2","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":262144,"modalities":["text","image","video"],"tool_call":true,"reasoning":true},{"key":"nvidia/moonshotai/kimi-k2-instruct-0905","model":"moonshotai/kimi-k2-instruct-0905","name":"Kimi K2 0905","provider":"nvidia","provider_name":"Nvidia","family":"kimi-k2","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":262144,"max_output":262144,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/openai/gpt-oss-20b","model":"openai/gpt-oss-20b","name":"GPT OSS 20B","provider":"nvidia","provider_name":"Nvidia","family":"gpt-oss","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":131072,"max_output":32768,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/openai/whisper-large-v3","model":"openai/whisper-large-v3","name":"Whisper Large v3","provider":"nvidia","provider_name":"Nvidia","family":"whisper","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":0,"max_output":4096,"modalities":["audio"],"tool_call":false,"reasoning":false},{"key":"nvidia/openai/gpt-oss-120b","model":"openai/gpt-oss-120b","name":"GPT-OSS-120B","provider":"nvidia","provider_name":"Nvidia","family":"gpt-oss","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/minimaxai/minimax-m2.7","model":"minimaxai/minimax-m2.7","name":"MiniMax-M2.7","provider":"nvidia","provider_name":"Nvidia","family":"minimax","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":204800,"max_output":131072,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/minimaxai/minimax-m3","model":"minimaxai/minimax-m3","name":"MiniMax-M3","provider":"nvidia","provider_name":"Nvidia","family":"minimax","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":1000000,"max_output":16384,"modalities":["text","image","video"],"tool_call":true,"reasoning":true},{"key":"nvidia/sarvamai/sarvam-m","model":"sarvamai/sarvam-m","name":"sarvam-m","provider":"nvidia","provider_name":"Nvidia","input_per_mtok":0,"output_per_mtok":0,"cache_read_per_mtok":null,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nvidia/deepseek-ai/deepseek-v4-flash","model":"deepseek-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"nvidia","provider_name":"Nvidia","family":"deepseek-flash","input_per_mtok":0.14,"output_per_mtok":0.28,"cache_read_per_mtok":0.0028,"context":1048576,"max_output":393216,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/nemotron-3-super-120b-a12b","model":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0.2,"output_per_mtok":0.8,"cache_read_per_mtok":null,"context":262144,"max_output":262144,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/deepseek-ai/deepseek-v4-pro","model":"deepseek-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"nvidia","provider_name":"Nvidia","family":"deepseek-thinking","input_per_mtok":0.435,"output_per_mtok":0.87,"cache_read_per_mtok":0.003625,"context":1048576,"max_output":393216,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nvidia/nvidia/nemotron-3-ultra-550b-a55b","model":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","provider":"nvidia","provider_name":"Nvidia","family":"nemotron","input_per_mtok":0.5,"output_per_mtok":2.5,"cache_read_per_mtok":0.15,"context":1000000,"max_output":65536,"modalities":["text"],"tool_call":true,"reasoning":true}]}