All Providers
105Models
23Families
1.0MMax Context
$0–$0.50Input Cost/MTok
$0–$2.50Output Cost/MTok

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights

Setup

Set the following environment variable to use Nvidia:

NVIDIA_API_KEY

Models (105)

ModelModel IDInput CostOutput CostContextCapabilities
Qwen3 Next 80B A3B Instructqwenqwen/qwen3-next-80b-a3b-instruct$0/MTok$0/MTok262.1KTools
Qwen 3.5 397B A17Bqwenqwen/qwen3.5-397b-a17b$0/MTok$0/MTok262.1KReasoningToolsFilesOpen
Qwen 3.5 122B A10Bqwenqwen/qwen3.5-122b-a10b$0/MTok$0/MTok262.1KReasoningToolsFilesOpen
Qwen Imageqwenqwen/qwen-image$0/MTok$0/MTok—Files
Qwen3 Coder 480B A35B Instructqwenqwen/qwen3-coder-480b-a35b-instruct$0/MTok$0/MTok262.1KTools
Qwen Image Editqwenqwen/qwen-image-edit$0/MTok$0/MTok—Files
Qwen 2.5 Coder 32b Instructqwen/qwen2.5-coder-32b-instruct$0/MTok$0/MTok128KToolsOpen
Step 3.7 Flashstepfun-ai/step-3.7-flash$0/MTok$0/MTok256KReasoningToolsFilesOpen
Step 3.5 Flashstepfun-ai/step-3.5-flash$0/MTok$0/MTok256KReasoningToolsOpen
DeepSeek V4 Pro 0813deepseek-thinkingdeepseek-ai/deepseek-v4-pro-0813$0/MTok$0/MTok1MReasoningToolsOpen
DeepSeek V4 Flash 0731deepseek-flashdeepseek-ai/deepseek-v4-flash-0731$0/MTok$0/MTok1MReasoningToolsOpen
Laguna XS 2.1lagunapoolside/laguna-xs-2.1$0/MTok$0/MTok262.1KReasoningToolsOpen
Mistral Large 3 675B Instruct 2512mistral-largemistralai/mistral-large-3-675b-instruct-2512$0/MTok$0/MTok262.1KToolsFilesOpen
mistral nemotronnemotronmistralai/mistral-nemotron$0/MTok$0/MTok128KToolsOpen
Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct$0/MTok$0/MTok65.5KToolsOpen
Ministral 3 14B Instruct 2512ministralmistralai/ministral-14b-instruct-2512$0/MTok$0/MTok262.1KToolsFilesOpen
mistral small 4 119b 2603mistralai/mistral-small-4-119b-2603$0/MTok$0/MTok128KReasoningToolsFilesOpen
Mixtral 8x7B Instructmistralai/mixtral-8x7b-instruct$0/MTok$0/MTok32.8KToolsOpen
Mistral Medium 3.5mistral-mediummistralai/mistral-medium-3.5-128b$0/MTok$0/MTok262.1KReasoningToolsFilesOpen
Mistral 7B Instruct v0.3mistralai/mistral-7b-instruct-v0.3$0/MTok$0/MTok65.5KToolsOpen
Mistral Medium 3mistral-mediummistralai/mistral-medium-3-instruct$0/MTok$0/MTok131.1KFiles
Magistral Small 2506mistralai/magistral-small-2506$0/MTok$0/MTok32.8K
streampetrnvidia/streampetr$0/MTok$0/MTok128KFilesOpen
Llama 3.3 Nemotron Super 49B v1.5nemotronnvidia/llama-3.3-nemotron-super-49b-v1.5$0/MTok$0/MTok131.1KReasoningToolsOpen
usdcodenvidia/usdcode$0/MTok$0/MTok128K
Nemotron 3 Nano Omninemotronnvidia/nemotron-3-nano-omni-30b-a3b-reasoning$0/MTok$0/MTok256KReasoningToolsFilesOpen
cosmos transfer 1.7bnvidia/cosmos-transfer1-7b$0/MTok$0/MTok—FilesOpen
nemotron voicechatnemotronnvidia/nemotron-voicechat$0/MTok$0/MTok128KToolsFilesOpen
studiovoicenvidia/studiovoice$0/MTok$0/MTok128KOpen
nemotron 3 content safetynemotronnvidia/nemotron-3-content-safety$0/MTok$0/MTok128KOpen
cosmos transfer 2.5 2bnvidia/cosmos-transfer2_5-2b$0/MTok$0/MTok—FilesOpen
bevformernvidia/bevformer$0/MTok$0/MTok128KFilesOpen
Llama 3.1 Nemotron Nano VL 8B v1nemotronnvidia/llama-3.1-nemotron-nano-vl-8b-v1$0/MTok$0/MTok32.8KReasoningToolsFilesOpen
magpie tts zeroshotnvidia/magpie-tts-zeroshot$0/MTok$0/MTok—FilesOpen
Nemotron Nano 12B v2 VLnemotronnvidia/nemotron-nano-12b-v2-vl$0/MTok$0/MTok128KReasoningToolsFilesOpen
sparsedrivenvidia/sparsedrive$0/MTok$0/MTok128KFilesOpen
llama nemotron embed vl 1b v2nemotronnvidia/llama-nemotron-embed-vl-1b-v2$0/MTok$0/MTok32.8KFilesOpen
synthetic video detectornvidia/synthetic-video-detector$0/MTok$0/MTok—FilesOpen
llama nemotron rerank vl 1b v2nemotronnvidia/llama-nemotron-rerank-vl-1b-v2$0/MTok$0/MTok128KFilesOpen
usdvalidatenvidia/usdvalidate$0/MTok$0/MTok—Open
Active Speaker Detectionnvidia/active-speaker-detection$0/MTok$0/MTok—FilesOpen
Llama 3.1 Nemotron Ultra 253Bnemotronnvidia/llama-3.1-nemotron-ultra-253b-v1$0/MTok$0/MTok128KReasoningToolsOpen
llama 3 2 nemoretriever 300m embed v1nvidia/llama-3_2-nemoretriever-300m-embed-v1$0/MTok$0/MTok32.8KOpen
nv embedcode 7b v1nvidia/nv-embedcode-7b-v1$0/MTok$0/MTok32.8KOpen
llama 3.1 nemotron safety guard 8b v3nemotronnvidia/llama-3.1-nemotron-safety-guard-8b-v3$0/MTok$0/MTok128KOpen
nemotron mini 4b instructnemotronnvidia/nemotron-mini-4b-instruct$0/MTok$0/MTok128KToolsOpen
cosmos predict 1.5bnvidia/cosmos-predict1-5b$0/MTok$0/MTok—FilesOpen
nemotron content safety reasoning 4bnemotronnvidia/nemotron-content-safety-reasoning-4b$0/MTok$0/MTok128KReasoningOpen
riva translate 4b instruct v1 1nvidia/riva-translate-4b-instruct-v1.1$0/MTok$0/MTok128KOpen
nvidia nemotron nano 9b v2nemotronnvidia/nvidia-nemotron-nano-9b-v2$0/MTok$0/MTok131.1KReasoningToolsOpen
gliner piinvidia/gliner-pii$0/MTok$0/MTok128KOpen
Llama 3.1 Nemotron Nano 8B v1nemotronnvidia/llama-3.1-nemotron-nano-8b-v1$0/MTok$0/MTok131.1KReasoningToolsOpen
nv embed v1nvidia/nv-embed-v1$0/MTok$0/MTok32.8KOpen
rerank qa mistral 4bnvidia/rerank-qa-mistral-4b$0/MTok$0/MTok128KOpen
Nemotron 3.5 Lightning 30B A3Bnemotronnvidia/nemotron-3.5-lightning-30b-a3b$0/MTok$0/MTok262.1KReasoningToolsOpen
Llama 3.3 Nemotron Super 49B v1nemotronnvidia/llama-3.3-nemotron-super-49b-v1$0/MTok$0/MTok131.1KReasoningToolsOpen
nemotron 3 nano 30b a3bnemotronnvidia/nemotron-3-nano-30b-a3b$0/MTok$0/MTok131.1KReasoningToolsOpen
Llama 3.1 Nemotron 70B Instructnemotronnvidia/llama-3.1-nemotron-70b-instruct$0/MTok$0/MTok128KToolsOpen
Cosmos Reason2 8Bnvidia/cosmos-reason2-8b$0/MTok$0/MTok131.1KReasoningToolsFilesOpen
Gemma 3 4B ITgemmagoogle/gemma-3-4b-it$0/MTok$0/MTok131.1KToolsFilesOpen
Gemma 3n E2b Itgoogle/gemma-3n-e2b-it$0/MTok$0/MTok128KToolsFilesOpen
paligemmagoogle/google-paligemma$0/MTok$0/MTok128KFilesOpen
Gemma 2 2b Itgoogle/gemma-2-2b-it$0/MTok$0/MTok128KToolsOpen
Gemma 4 31B ITgemmagoogle/gemma-4-31b-it$0/MTok$0/MTok256KReasoningToolsFilesOpen
Gemma 3n E4b Itgoogle/gemma-3n-e4b-it$0/MTok$0/MTok128KToolsFilesOpen
Gemma 3 12B ITgemmagoogle/gemma-3-12b-it$0/MTok$0/MTok131.1KToolsFilesOpen
Inklinglingthinkingmachines/inkling$0/MTok$0/MTok1.0MReasoningToolsFilesOpen
Llama 3.1 8B Instructllamameta/llama-3.1-8b-instruct$0/MTok$0/MTok16KToolsOpen
Llama Guard 4 12Bllamameta/llama-guard-4-12b$0/MTok$0/MTok128KFilesOpen
Llama 3.2 90B Vision Instructllamameta/llama-3.2-90b-vision-instruct$0/MTok$0/MTok128KToolsFilesOpen
Llama 3.2 3B Instructllamameta/llama-3.2-3b-instruct$0/MTok$0/MTok32.8KOpen
Llama 3.2 1b Instructmeta/llama-3.2-1b-instruct$0/MTok$0/MTok128KToolsOpen
esmfoldmeta/esmfold$0/MTok$0/MTok128KOpen
Llama 4 Maverick 17b 128e Instructmeta/llama-4-maverick-17b-128e-instruct$0/MTok$0/MTok128KToolsFilesOpen
Muse Glimmer 30Bmusemeta/muse-glimmer-30b$0/MTok$0/MTok131.1KReasoningToolsFilesOpen
esm2 650mmeta/esm2-650m$0/MTok$0/MTok128KOpen
Llama 3.2 11b Vision Instructmeta/llama-3.2-11b-vision-instruct$0/MTok$0/MTok128KToolsFilesOpen
Llama 3.1 70b Instructmeta/llama-3.1-70b-instruct$0/MTok$0/MTok128KToolsOpen
Llama 3.3 70b Instructmeta/llama-3.3-70b-instruct$0/MTok$0/MTok128KToolsOpen
ByteDance Seed Seed OSS 36B Instructseedbytedance/seed-oss-36b-instruct$0/MTok$0/MTok262KTools
sarvam msarvamai/sarvam-m$0/MTok$0/MTok128KToolsOpen
Phi 4 Multimodalmicrosoft/phi-4-multimodal-instruct$0/MTok$0/MTok128K
Phi 4 Miniphimicrosoft/phi-4-mini-instruct$0/MTok$0/MTok131.1KToolsOpen
MiniMax M2.7minimaxminimaxai/minimax-m2.7$0/MTok$0/MTok204.8KReasoningToolsOpen
MiniMax M3minimaxminimaxai/minimax-m3$0/MTok$0/MTok1MReasoningToolsFilesOpen
BGE M3bgebaai/bge-m3$0/MTok$0/MTok8.2KOpen
dracarys llama 3.1 70b instructabacusai/dracarys-llama-3.1-70b-instruct$0/MTok$0/MTok128KToolsOpen
GPT OSS 20Bgpt-ossopenai/gpt-oss-20b$0/MTok$0/MTok131.1KReasoningToolsOpen
Whisper Large v3whisperopenai/whisper-large-v3$0/MTok$0/MTok—Open
GPT OSS 120Bgpt-ossopenai/gpt-oss-120b$0/MTok$0/MTok128KReasoningToolsOpen
Kimi K2.6kimi-k2moonshotai/kimi-k2.6$0/MTok$0/MTok262.1KReasoningToolsFilesOpen
Kimi K2 0905kimi-k2moonshotai/kimi-k2-instruct-0905$0/MTok$0/MTok262.1KToolsOpen
Kimi K3kimi-k3moonshotai/kimi-k3$0/MTok$0/MTok1.0MReasoningToolsFilesOpen
solar 10.7b instructupstage/solar-10.7b-instruct$0/MTok$0/MTok128KToolsOpen
GLM 5.2glmz-ai/glm-5.2$0/MTok$0/MTok1MReasoningToolsOpen
GLM 5.3 Flashglm-flashz-ai/glm-5.3-flash$0/MTok$0/MTok1MReasoningToolsFilesOpen
GLM 5.3glmz-ai/glm-5.3$0/MTok$0/MTok1MReasoningToolsOpen
FLUX.1 Kontext devblack-forest-labs/flux_1-kontext-dev$0/MTok$0/MTok41.0KFilesOpen
FLUX.1 schnellblack-forest-labs/flux_1-schnell$0/MTok$0/MTok77Open
FLUX.2 Klein 4Bfluxblack-forest-labs/flux_2-klein-4b$0/MTok$0/MTok41.0KOpen
FLUX.1 devfluxblack-forest-labs/flux.1-dev$0/MTok$0/MTok4.1K
DeepSeek V4 Flashdeepseek-flashdeepseek-ai/deepseek-v4-flash$0.14/MTok$0.28/MTok1.0MReasoningToolsOpen
Nemotron 3 Supernemotronnvidia/nemotron-3-super-120b-a12b$0.20/MTok$0.80/MTok262.1KReasoningToolsOpen
DeepSeek V4 Prodeepseek-thinkingdeepseek-ai/deepseek-v4-pro$0.43/MTok$0.87/MTok1.0MReasoningToolsOpen
Nemotron 3 Ultra 550B A55Bnemotronnvidia/nemotron-3-ultra-550b-a55b$0.50/MTok$2.50/MTok1MReasoningToolsOpen