OpenBrowse
← All providers

Nvidia

94 models · routes through the OpenAI-Compatible adapter

API endpoint

https://integrate.api.nvidia.com/v1

Required environment variables

  • NVIDIA_API_KEY
Official documentation →

Models

ModelContextInputOutputCapabilities
nvidia/nemotron-3-ultra-550b-a55b1000k$0.50 / 1M$2.50 / 1Mtools, reasoning, open-weights
stepfun-ai/step-3.7-flash256kfreefreetools, reasoning, open-weights, vision
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning256kfreefreetools, reasoning, open-weights, vision
deepseek-ai/deepseek-v4-flash1049k$0.14 / 1M$0.28 / 1Mtools, reasoning, open-weights
deepseek-ai/deepseek-v4-pro1049k$0.43 / 1M$0.87 / 1Mtools, reasoning, open-weights
moonshotai/kimi-k2.6262kfreefreetools, reasoning, open-weights, vision
nvidia/active-speaker-detection—freefreeopen-weights
nvidia/nemotron-3-content-safety128kfreefreeopen-weights
nvidia/synthetic-video-detector—freefreeopen-weights
google/gemma-4-31b-it256kfreefreetools, reasoning, open-weights, vision
nvidia/llama-nemotron-rerank-vl-1b-v2128kfreefreeopen-weights, vision
z-ai/glm-5.1131kfreefreetools, reasoning, open-weights
minimaxai/minimax-m2.7205kfreefreetools, reasoning, open-weights
mistralai/mistral-small-4-119b-2603128kfreefreetools, open-weights
nvidia/nemotron-voicechat128kfreefreetools, open-weights
nvidia/nemotron-3-super-120b-a12b262k$0.20 / 1M$0.80 / 1Mtools, reasoning, open-weights
nvidia/gliner-pii128kfreefreeopen-weights
nvidia/cosmos-transfer2_5-2b—freefreeopen-weights, vision
qwen/qwen3.5-122b-a10b262kfreefreetools, reasoning, open-weights, vision
qwen/qwen3.5-397b-a17b262kfreefreetools, reasoning, open-weights, vision
minimaxai/minimax-m2.5205kfreefreetools, reasoning, open-weights
nvidia/llama-nemotron-embed-vl-1b-v233kfreefreeopen-weights, vision
stepfun-ai/step-3.5-flash256kfreefreetools, reasoning, open-weights
nvidia/nemotron-content-safety-reasoning-4b128kfreefreereasoning, open-weights
black-forest-labs/flux_2-klein-4b41kfreefreeopen-weights, vision
nvidia/usdcode128kfreefree—
z-ai/glm4.7205kfreefreetools, reasoning, open-weights
nvidia/riva-translate-4b-instruct-v1_1128kfreefreeopen-weights
mistralai/devstral-2-123b-instruct-2512262kfreefreetools, reasoning, open-weights
mistralai/mistral-large-3-675b-instruct-2512262kfreefreetools, open-weights, vision
deepseek-ai/deepseek-v3.2164kfreefreetools, reasoning
nvidia/streampetr128kfreefreeopen-weights
moonshotai/kimi-k2-thinking262kfreefreetools, reasoning, open-weights
nvidia/llama-3_1-nemotron-safety-guard-8b-v3128kfreefreeopen-weights
mistralai/magistral-small-250633kfreefree—
mistralai/mistral-medium-3-instruct131kfreefreevision
deepseek-ai/deepseek-v3.1-terminus128kfreefreetools, reasoning
moonshotai/kimi-k2-instruct-0905262kfreefreetools, open-weights
bytedance/seed-oss-36b-instruct262kfreefreetools
qwen/qwen-image-edit—freefreevision
nvidia/nvidia-nemotron-nano-9b-v2131kfreefreetools, reasoning, open-weights
black-forest-labs/flux_1-kontext-dev41kfreefreeopen-weights, vision
qwen/qwen-image—freefreevision
openai/gpt-oss-20b131kfreefreetools, reasoning, open-weights
openai/gpt-oss-120b128kfreefreereasoning
microsoft/phi-4-multimodal-instruct128kfreefree—
nvidia/llama-3_3-nemotron-super-49b-v1_5131kfreefreetools, reasoning, open-weights
sarvamai/sarvam-m128kfreefreetools, open-weights
nvidia/llama-3_2-nemoretriever-300m-embed-v133kfreefreeopen-weights
qwen/qwen3-coder-480b-a35b-instruct262kfreefreetools
nvidia/cosmos-transfer1-7b—freefreeopen-weights, vision
google/gemma-3n-e2b-it128kfreefreetools, open-weights, vision
mistralai/mistral-nemotron128kfreefreetools, open-weights
google/gemma-3n-e4b-it128kfreefreetools, open-weights, vision
nvidia/magpie-tts-zeroshot—freefreeopen-weights
nvidia/llama-3_3-nemotron-super-49b-v1131kfreefreetools, reasoning, open-weights
meta/llama-guard-4-12b128kfreefreeopen-weights, vision
meta/llama-4-maverick-17b-128e-instruct128kfreefreetools, open-weights, vision
mistralai/mistral-7b-instruct-v0366kfreefreetools, open-weights
nvidia/bevformer128kfreefreeopen-weights
nvidia/cosmos-predict1-5b—freefreeopen-weights, vision
nvidia/sparsedrive128kfreefreeopen-weights
nvidia/nv-embedcode-7b-v133kfreefreeopen-weights
meta/llama-3.1-8b-instruct16kfreefreetools, open-weights
moonshotai/kimi-k2-instruct128kfreefreetools, reasoning
google/gemma-3-27b-it131kfreefreetools, reasoning, vision
microsoft/phi-4-mini-instruct131kfreefreetools, reasoning, vision
qwen/qwen3-next-80b-a3b-instruct262kfreefreetools
qwen/qwen3-next-80b-a3b-thinking262kfreefreetools, reasoning, open-weights
nvidia/nemotron-3-nano-30b-a3b131kfreefreetools, reasoning, open-weights
meta/llama-3.3-70b-instruct128kfreefreetools, open-weights
qwen/qwen2.5-coder-32b-instruct128kfreefreetools, open-weights
nvidia/studiovoice128kfreefreeopen-weights
meta/llama-3.2-90b-vision-instruct128kfreefreetools, open-weights, vision
meta/llama-3.2-11b-vision-instruct128kfreefreetools, open-weights, vision
meta/llama-3.2-1b-instruct128kfreefreetools, open-weights
meta/llama-3.2-3b-instruct33kfreefreeopen-weights
abacusai/dracarys-llama-3_1-70b-instruct128kfreefreetools, open-weights
meta/esm2-650m128kfreefreeopen-weights
nvidia/nemotron-mini-4b-instruct128kfreefreetools, open-weights
black-forest-labs/flux_1-schnell0kfreefreeopen-weights
black-forest-labs/flux.1-dev4kfreefree—
nvidia/usdvalidate—freefreeopen-weights
google/gemma-2-2b-it128kfreefreetools, open-weights
meta/llama-3.1-70b-instruct128kfreefreetools, open-weights
nvidia/nv-embed-v133kfreefreeopen-weights
upstage/solar-10_7b-instruct128kfreefreetools, open-weights
google/google-paligemma128kfreefreeopen-weights, vision
mistralai/mixtral-8x22b-instruct66kfreefreetools, open-weights
nvidia/rerank-qa-mistral-4b128kfreefreeopen-weights
meta/esmfold128kfreefreeopen-weights
baai/bge-m38kfreefreeopen-weights
mistralai/mixtral-8x7b-instruct33kfreefreetools, open-weights
openai/whisper-large-v3—freefreeopen-weights

Sourced from models.dev. Pricing reflects the catalog at the time this page was rendered.