← Providers
Nvidia
At a glance
Models hosted100With public price 4 · Free ($0) 96
Cheapest anywhere1
Model typesText / Chat 77Image gen 6Embedding 5Classify / Safety 4Video gen 4Rerank 2Speech / Audio 2
Cheapest model hereDeepSeek V4 Flash
SDK package@ai-sdk/openai-compatible
APIhttps://integrate.api.nvidia.com/v1
Hosted models by blended price asc
100 of 100
| Cheapest here? | |||||
|---|---|---|---|---|---|
| GLM-5.2z-ai/glm-5.2 | Free | — | 1,000,000 | — | |
| Qwen3.5 397B-A17Bqwen/qwen3.5-397b-a17b | Free | — | 262,144 | — | |
| Qwen3.5 122B-A10Bqwen/qwen3.5-122b-a10b | Free | — | 262,144 | — | |
| GPT OSS 120Bopenai/gpt-oss-120b | Free | — | 128,000 | — | |
| Qwen3-Coder 480B-A35B Instructqwen/qwen3-coder-480b-a35b-instruct | Free | — | 262,144 | — | |
| Qwen3-Next 80B-A3B Instructqwen/qwen3-next-80b-a3b-instruct | Free | — | 262,144 | — | |
| GPT OSS 20Bopenai/gpt-oss-20b | Free | — | 131,072 | — | |
| Kimi K2 0905moonshotai/kimi-k2-instruct-0905 | Free | — | 262,144 | — | |
| Kimi K2.6moonshotai/kimi-k2.6 | Free | — | 262,144 | — | |
| Llama 3.2 3B Instructmeta/llama-3.2-3b-instruct | Free | — | 32,768 | — | |
| Llama 3.2 1B Instructmeta/llama-3.2-1b-instruct | Free | — | 128,000 | — | |
| Llama-3.2-11B-Vision-Instructmeta/llama-3.2-11b-vision-instruct | Free | — | 128,000 | — | |
| Qwen2.5-Coder-32B-Instructqwen/qwen2.5-coder-32b-instruct | Free | — | 128,000 | — | |
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | Free | — | 128,000 | — | |
| Gemma 4 31B ITgoogle/gemma-4-31b-it | Free | — | 256,000 | — | |
| MiniMax-M2.7minimaxai/minimax-m2.7 | Free | — | 204,800 | — | |
| Llama 3.3 Nemotron Super 49B v1nvidia/llama-3.3-nemotron-super-49b-v1 | Free | — | 131,072 | Only channel | |
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | Free | — | 131,072 | — | |
| Active Speaker DetectionClassify / Safetynvidia/active-speaker-detection | Free | — | 0 | Only channel | |
| Llama 3.1 Nemotron Nano 8B v1nvidia/llama-3.1-nemotron-nano-8b-v1 | Free | — | 131,072 | Only channel | |
| gliner-piinvidia/gliner-pii | Free | — | 128,000 | Only channel | |
| Nemotron 3 Content Safetynvidia/nemotron-3-content-safety | Free | — | 128,000 | Only channel | |
| cosmos-transfer2.5-2bVideo gennvidia/cosmos-transfer2_5-2b | Free | — | 0 | Only channel | |
| Llama 3.1 Nemotron 70B Instructnvidia/llama-3.1-nemotron-70b-instruct | Free | — | 128,000 | Only channel | |
| Nemotron Nano 12B v2 VLnvidia/nemotron-nano-12b-v2-vl | Free | — | 128,000 | Only channel | |
| Nemotron VoiceChatnvidia/nemotron-voicechat | Free | — | 128,000 | Only channel | |
| studiovoicenvidia/studiovoice | Free | — | 128,000 | Only channel | |
| Llama Nemotron Rerank VL 1B v2Reranknvidia/llama-nemotron-rerank-vl-1b-v2 | Free | — | 128,000 | Only channel | |
| Llama 3.3 Nemotron Super 49B v1.5nvidia/llama-3.3-nemotron-super-49b-v1.5 | Free | — | 131,072 | Only channel | |
| llama-3_2-nemoretriever-300m-embed-v1Embeddingnvidia/llama-3_2-nemoretriever-300m-embed-v1 | Free | — | 32,768 | Only channel | |
| Nemotron 3 Nano Omninvidia/nemotron-3-nano-omni-30b-a3b-reasoning | Free | — | 256,000 | — | |
| rerank-qa-mistral-4bReranknvidia/rerank-qa-mistral-4b | Free | — | 128,000 | Only channel | |
| nv-embed-v1Embeddingnvidia/nv-embed-v1 | Free | — | 32,768 | Only channel | |
| cosmos-transfer1-7bVideo gennvidia/cosmos-transfer1-7b | Free | — | 0 | Only channel | |
| streampetrnvidia/streampetr | Free | — | 128,000 | Only channel | |
| nv-embedcode-7b-v1Embeddingnvidia/nv-embedcode-7b-v1 | Free | — | 32,768 | Only channel | |
| usdvalidatenvidia/usdvalidate | Free | — | 0 | Only channel | |
| Nemotron Content Safety Reasoning 4Bnvidia/nemotron-content-safety-reasoning-4b | Free | — | 128,000 | Only channel | |
| cosmos-predict1-5bVideo gennvidia/cosmos-predict1-5b | Free | — | 0 | Only channel | |
| magpie-tts-zeroshotSpeech / Audionvidia/magpie-tts-zeroshot | Free | — | 0 | Only channel | |
| nvidia-nemotron-nano-9b-v2nvidia/nvidia-nemotron-nano-9b-v2 | Free | — | 131,072 | — | |
| Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b | Free | — | 262,144 | — | |
| riva-translate-4b-instruct-v1_1nvidia/riva-translate-4b-instruct-v1.1 | Free | — | 128,000 | Only channel | |
| Llama 3.1 Nemotron Ultra 253Bnvidia/llama-3.1-nemotron-ultra-253b-v1 | Free | — | 128,000 | Only channel | |
| sparsedrivenvidia/sparsedrive | Free | — | 128,000 | Only channel | |
| usdcodenvidia/usdcode | Free | — | 128,000 | Only channel | |
| Llama 3.1 Nemotron Safety Guard 8B v3Classify / Safetynvidia/llama-3.1-nemotron-safety-guard-8b-v3 | Free | — | 128,000 | Only channel | |
| bevformernvidia/bevformer | Free | — | 128,000 | Only channel | |
| Cosmos Reason2 8Bnvidia/cosmos-reason2-8b | Free | — | 131,072 | Only channel | |
| Llama 3.1 Nemotron Nano VL 8B v1nvidia/llama-3.1-nemotron-nano-vl-8b-v1 | Free | — | 32,768 | Only channel | |
| Nemotron Mini 4B Instructnvidia/nemotron-mini-4b-instruct | Free | — | 128,000 | Only channel | |
| Llama Nemotron Embed VL 1B v2Embeddingnvidia/llama-nemotron-embed-vl-1b-v2 | Free | — | 32,768 | Only channel | |
| synthetic-video-detectorClassify / Safetynvidia/synthetic-video-detector | Free | — | 0 | Only channel | |
| Phi 4 Multimodalmicrosoft/phi-4-multimodal-instruct | Free | — | 128,000 | — | |
| Phi-4-minimicrosoft/phi-4-mini-instruct | Free | — | 131,072 | — | |
| Gemma 3n E2b Itgoogle/gemma-3n-e2b-it | Free | — | 128,000 | Only channel | |
| paligemmagoogle/google-paligemma | Free | — | 128,000 | Only channel | |
| Gemma 3 4B ITgoogle/gemma-3-4b-it | Free | — | 131,072 | — | |
| Gemma 3n E4b Itgoogle/gemma-3n-e4b-it | Free | — | 128,000 | Only channel | |
| Gemma 3 12B ITgoogle/gemma-3-12b-it | Free | — | 131,072 | Only channel | |
| Gemma 2 2b Itgoogle/gemma-2-2b-it | Free | — | 128,000 | Only channel | |
| esmfoldmeta/esmfold | Free | — | 128,000 | Only channel | |
| Llama Guard 4 12BClassify / Safetymeta/llama-guard-4-12b | Free | — | 128,000 | Only channel | |
| Muse Glimmer 30Bmeta/muse-glimmer-30b | Free | — | 131,072 | — | |
| Llama-3.1-8B-Instructmeta/llama-3.1-8b-instruct | Free | — | 16,000 | — | |
| Llama 3.1 70B Instructmeta/llama-3.1-70b-instruct | Free | — | 128,000 | — | |
| esm2-650mmeta/esm2-650m | Free | — | 128,000 | Only channel | |
| Llama-3.2-90B-Vision-Instructmeta/llama-3.2-90b-vision-instruct | Free | — | 128,000 | Only channel | |
| Llama 4 Maverick 17B 128E Instructmeta/llama-4-maverick-17b-128e-instruct | Free | — | 128,000 | — | |
| Laguna XS 2.1poolside/laguna-xs-2.1 | Free | — | 262,144 | Only channel | |
| ByteDance-Seed/Seed-OSS-36B-Instructbytedance/seed-oss-36b-instruct | Free | — | 262,000 | — | |
| Whisper Large v3Speech / Audioopenai/whisper-large-v3 | Free | — | 0 | — | |
| Step 3.5 Flashstepfun-ai/step-3.5-flash | Free | — | 256,000 | — | |
| Step 3.7 Flashstepfun-ai/step-3.7-flash | Free | — | 256,000 | — | |
| BGE M3Embeddingbaai/bge-m3 | Free | — | 8,192 | Only channel | |
| Qwen ImageImage genqwen/qwen-image | Free | — | 0 | Only channel | |
| Qwen Image EditImage genqwen/qwen-image-edit | Free | — | 0 | Only channel | |
| dracarys-llama-3.1-70b-instructabacusai/dracarys-llama-3.1-70b-instruct | Free | — | 128,000 | Only channel | |
| InklingVideo genthinkingmachines/inkling | Free | — | 1,048,576 | — | |
| Magistral Small 2506mistralai/magistral-small-2506 | Free | — | 32,768 | Only channel | |
| Mistral-7B-Instruct-v0.3mistralai/mistral-7b-instruct-v0.3 | Free | — | 65,536 | — | |
| Mistral Large 3 675B Instruct 2512mistralai/mistral-large-3-675b-instruct-2512 | Free | — | 262,144 | Only channel | |
| Mistral Nemotronmistralai/mistral-nemotron | Free | — | 128,000 | Only channel | |
| mistral-small-4-119b-2603mistralai/mistral-small-4-119b-2603 | Free | — | 128,000 | Only channel | |
| Mistral: Mixtral 8x7B Instructmistralai/mixtral-8x7b-instruct | Free | — | 32,768 | Only channel | |
| Mistral Medium 3.5mistralai/mistral-medium-3.5-128b | Free | — | 262,144 | — | |
| Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Free | — | 65,536 | Only channel | |
| Mistral Medium 3mistralai/mistral-medium-3-instruct | Free | — | 131,072 | — | |
| Ministral 3 14B Instruct 2512mistralai/ministral-14b-instruct-2512 | Free | — | 262,144 | Only channel | |
| MiniMax-M3minimaxai/minimax-m3 | Free | — | 1,000,000 | — | |
| solar-10.7b-instructupstage/solar-10.7b-instruct | Free | — | 128,000 | Only channel | |
| sarvam-msarvamai/sarvam-m | Free | — | 128,000 | Only channel | |
| FLUX.2 Klein 4BImage genblack-forest-labs/flux_2-klein-4b | Free | — | 40,960 | Only channel | |
| FLUX.1-devImage genblack-forest-labs/flux.1-dev | Free | — | 4,096 | Only channel | |
| FLUX.1-schnellImage genblack-forest-labs/flux_1-schnell | Free | — | 77 | Only channel | |
| FLUX.1-Kontext-devImage genblack-forest-labs/flux_1-kontext-dev | Free | — | 40,960 | Only channel | |
| DeepSeek V4 Flashdeepseek-ai/deepseek-v4-flash | $0.14 | $0.28 | $0.0028 | 1,048,576 | 2.2× pricier |
| Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | $0.20 | $0.80 | — | 262,144 | Lowest anywhere |
| DeepSeek V4 Prodeepseek-ai/deepseek-v4-pro | $0.435 | $0.87 | $0.0036 | 1,048,576 | 1.3× pricier |
| Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b | $0.50 | $2.50 | $0.15 | 1,000,000 | 10.0× pricier |