NVIDIA NIM
info Notes
Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model.
key How to get API key
General steps — follow the official NVIDIA NIM page for exact details.
- Open the NVIDIA NIM API key page ↗
- Create a new account, or sign in if you already have one.
- Generate an API key from the dashboard or settings.
layers Available models 94
| Model | Capabilities | Context | Output | Rate limit |
|---|---|---|---|---|
`nvidia/nemotron-3-super-120b-a12b`
`nvidia/nemotron-3-super-120b-a12b` |
description
| 1M | — | 40 RPM, 10,000 RPD |
`nvidia/nemotron-3-nano-30b-a3b`
`nvidia/nemotron-3-nano-30b-a3b` |
description
| 262K | — | 40 RPM, 10,000 RPD |
`nvidia/llama-3.1-nemotron-ultra-253b-v1`
`nvidia/llama-3.1-nemotron-ultra-253b-v1` |
description
| 128K | — | 40 RPM, 10,000 RPD |
`meta/llama-3.3-70b-instruct`
`meta/llama-3.3-70b-instruct` |
description
| 128K | — | 40 RPM, 10,000 RPD |
`mistralai/mistral-nemotron`
`mistralai/mistral-nemotron` |
description
| 128K | — | 40 RPM, 10,000 RPD |
`google/gemma-4-31b-it`
`google/gemma-4-31b-it` |
description
| 262K | — | 40 RPM, 10,000 RPD |
`mistralai/mistral-large-2-instruct`
`mistralai/mistral-large-2-instruct` |
description
| 128K | — | 40 RPM, 10,000 RPD |
`minimaxai/minimax-m3`
`minimaxai/minimax-m3` |
description
| 1M | — | 40 RPM, 10,000 RPD |
`nvidia/nemotron-3-ultra-550b-a55b`
`nvidia/nemotron-3-ultra-550b-a55b` |
description
| 1M | — | 40 RPM, 10,000 RPD |
`openai/gpt-oss-120b`
`openai/gpt-oss-120b` |
description
| 131K | — | 40 RPM, 10,000 RPD |
`openai/gpt-oss-20b`
`openai/gpt-oss-20b` |
description
| 131K | — | 40 RPM, 10,000 RPD |
+ 92 more models
+-92-more-models |
Text, Image, Video, Speech, Embeddings | Varies | — | 40 RPM, 10,000 RPD |
GPT-OSS 120B
gpt-oss-120b |
description
| 1M | — | 40 requests per minute |
Yi Large
yi-large |
description
| 1M | — | 40 requests per minute |
Fuyu 8B
fuyu-8b |
description
| 1M | — | 40 requests per minute |
Jamba 1.5 Large
jamba-1.5-large |
description
| 1M | — | 40 requests per minute |
Sea Lion 7B
sea-lion-7b |
description
| 1M | — | 40 requests per minute |
Starcoder 2 15B
starcoder-2-15b |
description
| 1M | — | 40 requests per minute |
Dbrx
dbrx |
description
| 1M | — | 40 requests per minute |
DeepSeek Coder 6.7B
deepseek-coder-6.7b |
description
| 1M | — | 40 requests per minute |
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731 |
description
| 1M | — | 40 requests per minute |
DeepSeek V4 Pro 0813
deepseek-v4-pro-0813 |
description
| 1M | — | 40 requests per minute |
Codegemma 1.1 7B
codegemma-1.1-7b |
description
| 1M | — | 40 requests per minute |
Codegemma 7B
codegemma-7b |
description
| 1M | — | 40 requests per minute |
Deplot
deplot |
description
| 1M | — | 40 requests per minute |
Diffusiongemma 26B A4B
diffusiongemma-26b-a4b |
description
| 1M | — | 40 requests per minute |
Gemma 2B
gemma-2b |
description
| 1M | — | 40 requests per minute |
Gemma 3 12B
gemma-3-12b |
description
| 1M | — | 40 requests per minute |
Gemma 3 4B
gemma-3-4b |
description
| 1M | — | 40 requests per minute |
Gemma 4 31B
gemma-4-31b |
description
| 1M | — | 40 requests per minute |
Recurrentgemma 2B
recurrentgemma-2b |
description
| 1M | — | 40 requests per minute |
Granite 3.0 3B A800m
granite-3.0-3b-a800m |
description
| 1M | — | 40 requests per minute |
Granite 3.0 8B
granite-3.0-8b |
description
| 1M | — | 40 requests per minute |
Granite 34B Code
granite-34b-code |
description
| 1M | — | 40 requests per minute |
Granite 8B Code
granite-8b-code |
description
| 1M | — | 40 requests per minute |
Codellama 70B
codellama-70b |
description
| 1M | — | 40 requests per minute |
Llama 3.2 11B Vision
llama-3.2-11b-vision |
description
| 1M | — | 40 requests per minute |
Llama 3.2 90B Vision
llama-3.2-90b-vision |
description
| 1M | — | 40 requests per minute |
Llama Guard 4 12B
llama-guard-4-12b |
description
| 1M | — | 40 requests per minute |
Llama 2 70B
llama-2-70b |
description
| 1M | — | 40 requests per minute |
Muse Glimmer 30B
muse-glimmer-30b |
description
| 1M | — | 40 requests per minute |
Kosmos 2
kosmos-2 |
description
| 1M | — | 40 requests per minute |
Phi 3 Vision 128k
phi-3-vision-128k |
description
| 1M | — | 40 requests per minute |
Phi 3.5 MoE
phi-3.5-moe |
description
| 1M | — | 40 requests per minute |
MiniMax M3
minimax-m3 |
description
| 1M | — | 40 requests per minute |
Codestral 22B V0.1
codestral-22b-v0.1 |
description
| 1M | — | 40 requests per minute |
Mistral 7B V0.3
mistral-7b-v0.3 |
description
| 1M | — | 40 requests per minute |
Mistral Large
mistral-large |
description
| 1M | — | 40 requests per minute |
Mistral Large 2
mistral-large-2 |
description
| 1M | — | 40 requests per minute |
Mistral Nemotron
mistral-nemotron |
description
| 1M | — | 40 requests per minute |
Mixtral 8x22B V0.1
mixtral-8x22b-v0.1 |
description
| 1M | — | 40 requests per minute |
Kimi K2.6
kimi-k2.6 |
description
| 1M | — | 40 requests per minute |
Kimi K3
kimi-k3 |
description
| 1M | — | 40 requests per minute |
Mistral Nemo 12B
mistral-nemo-12b |
description
| 1M | — | 40 requests per minute |
Ai Synthetic Video Detector
ai-synthetic-video-detector |
description
| 1M | — | 40 requests per minute |
Cosmos Reason 2 8B
cosmos-reason-2-8b |
description
| 1M | — | 40 requests per minute |
Embed Qa 4
embed-qa-4 |
description
| 1M | — | 40 requests per minute |
Ising Calibration 1.5 31B
ising-calibration-1.5-31b |
description
| 1M | — | 40 requests per minute |
Llama 3.1 Nemoguard 8B Content Safety
llama-3.1-nemoguard-8b-content-safety |
description
| 1M | — | 40 requests per minute |
Llama 3.1 Nemoguard 8B Topic Control
llama-3.1-nemoguard-8b-topic-control |
description
| 1M | — | 40 requests per minute |
Llama 3.1 Nemotron 51B
llama-3.1-nemotron-51b |
description
| 1M | — | 40 requests per minute |
Llama 3.1 Nemotron 70B
llama-3.1-nemotron-70b |
description
| 1M | — | 40 requests per minute |
Llama 3.1 Nemotron Safety Guard 8B V3
llama-3.1-nemotron-safety-guard-8b-v3 |
description
| 1M | — | 40 requests per minute |
Llama 3.1 Nemotron Ultra 253B V1
llama-3.1-nemotron-ultra-253b-v1 |
description
| 1M | — | 40 requests per minute |
Llama 3.2 Nemoretriever 1B Vlm Embed V1
llama-3.2-nemoretriever-1b-vlm-embed-v1 |
description
| 1M | — | 40 requests per minute |
Llama 3.2 Nv Embedqa 1B V1
llama-3.2-nv-embedqa-1b-v1 |
description
| 1M | — | 40 requests per minute |
Llama Nemotron Embed VL 1B V2
llama-nemotron-embed-vl-1b-v2 |
description
| 1M | — | 40 requests per minute |
Llama 3 Chatqa 1.5 70B
llama-3-chatqa-1.5-70b |
description
| 1M | — | 40 requests per minute |
Mistral Nemo Minitron 8B 8k
mistral-nemo-minitron-8b-8k |
description
| 1M | — | 40 requests per minute |
Nemotron 3 Embed 1B
nemotron-3-embed-1b |
description
| 1M | — | 40 requests per minute |
Nemotron 3 Nano Omni 30B A3B Reasoning
nemotron-3-nano-omni-30b-a3b-reasoning |
description
| 1M | — | 40 requests per minute |
Nemotron 3 Super 120B A12B
nemotron-3-super-120b-a12b |
description
| 1M | — | 40 requests per minute |
Nemotron 3 Ultra 550B A55B
nemotron-3-ultra-550b-a55b |
description
| 1M | — | 40 requests per minute |
Nemotron 3.5 Content Safety
nemotron-3.5-content-safety |
description
| 1M | — | 40 requests per minute |
Nemotron 3.5 Lightning 30B A3B
nemotron-3.5-lightning-30b-a3b |
description
| 1M | — | 40 requests per minute |
Nemotron 4 340B
nemotron-4-340b |
description
| 1M | — | 40 requests per minute |
Nemotron 4 340B Reward
nemotron-4-340b-reward |
description
| 1M | — | 40 requests per minute |
Nemotron Nano 3 30B A3B
nemotron-nano-3-30b-a3b |
description
| 1M | — | 40 requests per minute |
Nemotron Parse
nemotron-parse |
description
| 1M | — | 40 requests per minute |
Neva 22B
neva-22b |
description
| 1M | — | 40 requests per minute |
Nv Embedqa Mistral 7B V2
nv-embedqa-mistral-7b-v2 |
description
| 1M | — | 40 requests per minute |
Nvclip
nvclip |
description
| 1M | — | 40 requests per minute |
Riva Translate 4B
riva-translate-4b |
description
| 1M | — | 40 requests per minute |
Riva Translate 4B V1.1
riva-translate-4b-v1.1 |
description
| 1M | — | 40 requests per minute |
Riva Translate 4B V2
riva-translate-4b-v2 |
description
| 1M | — | 40 requests per minute |
Vila
vila |
description
| 1M | — | 40 requests per minute |
GPT-OSS 20B
gpt-oss-20b |
description
| 1M | — | 40 requests per minute |
Laguna XS 2.1
laguna-xs-2.1 |
description
| 1M | — | 40 requests per minute |
Arctic Embed L
arctic-embed-l |
description
| 1M | — | 40 requests per minute |
Palmyra Creative 122B
palmyra-creative-122b |
description
| 1M | — | 40 requests per minute |
Palmyra Fin 70B 32k
palmyra-fin-70b-32k |
description
| 1M | — | 40 requests per minute |
Palmyra Med 70B
palmyra-med-70b |
description
| 1M | — | 40 requests per minute |
Palmyra Med 70B 32k
palmyra-med-70b-32k |
description
| 1M | — | 40 requests per minute |
Zamba 2 7B
zamba-2-7b |
description
| 1M | — | 40 requests per minute |
help Frequently Asked Questions
NVIDIA NIM offers 94 free models.
The largest context window is 1,000,000 tokens.
The free tier is limited to 40 requests per minute.