NVIDIA NIM models and pricing

We track 26 models on NVIDIA NIM from 10 labs. 26 models are listed free. The largest context window is 1M tokens (NVIDIA Nemotron 3.5 Super VL and Step 5 Preview). Prices last verified 18 Nov 2026.

Prices in USD per million tokens. Official site

Newest models on NVIDIA NIM

By the lab's release date.

All NVIDIA NIM models and prices

ModelLabInputOutputContextSource
MiniMax-M3.1-Flash
minimaxai/minimax-m3.1-flash
MiniMaxFreeFree262Kmodels.dev
NVIDIA Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl-120b-a12b
NVIDIAFreeFree1Mmodels.dev
Step 5 Preview
stepfun-ai/step-5-preview
StepFunFreeFree1Mmodels.dev
DeepSeek V4.1 Flash
deepseek-ai/deepseek-v4.1-flash
DeepSeekFreeFree1Mmodels.dev
GLM-5.3-Flash
z-ai/glm-5.3-flash
Zhipu AI (Z.ai)FreeFree1Mmodels.dev
Nemotron 3.5 Lightning 30B
nvidia/nemotron-3.5-lightning-30b-a3b
NVIDIAFreeFree262Kmodels.dev
Muse Glimmer 30B
meta/muse-glimmer-30b
MetaFreeFree131Kmodels.dev
Laguna XS 2.1
poolside/laguna-xs-2.1
PoolsideFreeFree262Kmodels.dev
DiffusionGemma 26B A4B IT
google/diffusiongemma-26b-a4b-it
Google DeepMindFreeFree250Kmodels.dev
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
NVIDIAFreeFree1Mmodels.dev
Nemotron 3.5 Content Safety
nvidia/nemotron-3.5-content-safety
NVIDIAFreeFree128Kmodels.dev
Nemotron 3 Nano Omni
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
NVIDIAFreeFree256Kmodels.dev
Gemma 4 31B IT
google/gemma-4-31b-it
Google DeepMindFreeFree256Kmodels.dev
nemotron-voicechat
nvidia/nemotron-voicechat
NVIDIAFreeFree128Kmodels.dev
FLUX.2 Klein 4B
black-forest-labs/flux_2-klein-4b
Black Forest LabsFreeFree–models.dev
llama-nemotron-embed-vl-1b-v2
nvidia/llama-nemotron-embed-vl-1b-v2
NVIDIAFreeFree8Kmodels.dev
llama-nemotron-rerank-vl-1b-v2
nvidia/llama-nemotron-rerank-vl-1b-v2
NVIDIAFreeFree10Kmodels.dev
llama-3.1-nemotron-safety-guard-8b-v3
nvidia/llama-3.1-nemotron-safety-guard-8b-v3
NVIDIAFreeFree128Kmodels.dev
gpt-oss-20b
openai/gpt-oss-20b
OpenAIFreeFree131Kmodels.dev
FLUX.1-Kontext-dev
black-forest-labs/flux_1-kontext-dev
Black Forest LabsFreeFree–models.dev
Llama Guard 4 12B
meta/llama-guard-4-12b
MetaFreeFree164Kmodels.dev
Llama-3.2-90B-Vision-Instruct
meta/llama-3.2-90b-vision-instruct
MetaFreeFree128Kmodels.dev
Llama 3.2 11b Vision Instruct
meta/llama-3.2-11b-vision-instruct
MetaFreeFree128Kmodels.dev
FLUX.1-dev
black-forest-labs/flux.1-dev
Black Forest LabsFreeFree–models.dev
FLUX.1-schnell
black-forest-labs/flux_1-schnell
Black Forest LabsFreeFree–models.dev
Whisper Large v3
openai/whisper-large-v3
OpenAIFreeFree448models.dev

Frequently asked questions

How many models does NVIDIA NIM offer?

We currently track 26 active models on NVIDIA NIM from 10 labs, led by NVIDIA (9), Black Forest Labs (4), Meta (4) and Google DeepMind (2).

Which model on NVIDIA NIM has the largest context window?

NVIDIA Nemotron 3.5 Super VL and Step 5 Preview share the largest context window we track on NVIDIA NIM: 1,048,576 tokens (1M).