NVIDIA models

NVIDIA has 58 models in the directory. The newest is Nemotron 3.5 Super VL 120B A12B, released Oct 15, 2026.

The cheapest to run is Nemotron 3.5 Lightning 30B A3B at $0.05 per million input tokens.

Nemotron 3.5 Super VL 120B A12B has the longest context window, 1.05M tokens.

NVIDIA Nemotron 3 Ultra 550B A55B scores highest on the independent Intelligence Index, at 22.9.

Models: 58
Newest: Oct 15, 2026
From: $0.05/M input
Longest context: 1.05M

All NVIDIA models

Filter in the directory

Nemotron 3.5 Super VL 120B A12B
1.05M context
Reads text, images and video. Tool calling, reasoning.
by nvidiaOct 15, 2026$0/M input tokens$0/M output tokens
NVIDIA Nemotron 3.5 Lightning 30B A3B
Index 12.9
Reads text. Reasoning.
by nvidiaAug 11, 20261M context
Nemotron 3.5 Lightning 30B A3B
262K context
Reads text. Tool calling, structured output, reasoning. Served by 11 providers.
by nvidiaAug 11, 2026$0.05/M input tokens$0.20/M output tokens11 providers
NVIDIA Nemotron 3 Ultra 550B A55B
Index 22.9
Reads text. Reasoning.
by nvidiaJun 4, 20261M context
Nemotron 3 Ultra 550B A55B
1M context
Reads text. Tool calling, structured output, reasoning. Served by 20 providers.
by nvidiaJun 4, 2026$0.50/M input tokens$2.50/M output tokens20 providers
Nemotron 3.5 Content Safety
128K context
Reads text and images. Reasoning. Served by 6 providers.
by nvidiaJun 4, 2026$0.05/M input tokens$0.15/M output tokens6 providers
Nemotron 3 Nano Omni
256K context
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.
by nvidiaApr 28, 2026$0.10/M input tokens$0.25/M output tokens7 providers
Active Speaker Detection
Reads video.
by nvidiaApr 16, 2026$0/M input tokens$0/M output tokens
synthetic-video-detector
Reads video.
by nvidiaApr 16, 2026$0/M input tokens$0/M output tokens
Gemma-4-31B-IT
256K context
Reads text, images and video. Tool calling, reasoning.
by nvidiaApr 2, 2026$0/M input tokens$0/M output tokens
llama-nemotron-rerank-vl-1b-v2
Rerank
128K context
Reorders search results by relevance to a query.
by nvidiaMar 31, 2026$0/M input tokens
nemotron-voicechat
128K context
Reads text and audio. Tool calling.
by nvidiaMar 16, 2026$0/M input tokens$0/M output tokens
Nemotron 3 Super 120B
1M context
Reads text. Tool calling, structured output, reasoning. Served by 17 providers.
by nvidiaMar 1, 2026$0.05/M input tokens$0.25/M output tokens17 providers
cosmos-transfer2.5-2b
Video
Generates video from text, images and video.
by nvidiaFeb 26, 2026$0/M input tokens$0/M output tokens
llama-nemotron-embed-vl-1b-v2
Embeddings
33K context
Turns text and images into vectors for search and retrieval.
by nvidiaFeb 10, 2026$0/M input tokens
FLUX.2 Klein 4B
Image
41K context
Generates images from text and images.
by nvidiaJan 14, 2026$0/M input tokens$0/M output tokens
usdcode
128K context
Reads text.
by nvidiaJan 1, 2026$0/M input tokens$0/M output tokens
riva-translate-4b-instruct-v1_1
128K context
Reads text.
by nvidiaDec 12, 2025$0/M input tokens$0/M output tokens
Cosmos Reason2 8B
131K context
Reads text, images and video. Tool calling, reasoning.
by nvidiaDec 1, 2025$0/M input tokens$0/M output tokens
streampetr
128K context
Reads video.
by nvidiaNov 13, 2025$0/M input tokens$0/M output tokens
llama-3.1-nemotron-safety-guard-8b-v3
128K context
Reads text.
by nvidiaOct 28, 2025$0/M input tokens$0/M output tokens
Nvidia Nemotron Nano 12B V2 VL
131K context
Reads text and images. Tool calling, structured output, reasoning. Served by 3 providers.
by nvidiaOct 28, 2025$0.20/M input tokens$0.60/M output tokens3 providers
Llama Nemotron Embed 1B v2
Embeddings
8K context
Turns text into vectors for search and retrieval.
by nvidiaOct 16, 2025
Magistral Small 2506
33K context
Reads text.
by nvidiaSep 25, 2025$0/M input tokens$0/M output tokens
Mistral Medium 3
131K context
Reads text and images.
by nvidiaSep 25, 2025$0/M input tokens$0/M output tokens
Qwen Image Edit
Image
Generates images from text and images.
by nvidiaAug 19, 2025$0/M input tokens$0/M output tokens
Nvidia Nemotron Nano 9B V2
131K context
Reads text. Tool calling, structured output, reasoning. Served by 3 providers.
by nvidiaAug 18, 2025$0.06/M input tokens$0.23/M output tokens3 providers
FLUX.1-Kontext-dev
Image
41K context
Generates images from text and images.
by nvidiaAug 12, 2025$0/M input tokens$0/M output tokens
Nvidia Nemotron Super 49B
128K context
Reads text.
by nvidiaAug 8, 2025$0.15/M input tokens$0.15/M output tokens
Qwen Image
Image
8K context
Generates images from text and images. Served by 2 providers.
by nvidiaAug 7, 2025$0.50/M input tokens$2/M output tokens2 providers
GPT OSS 20B
131K context
Reads text. Tool calling, structured output, reasoning.
by nvidiaAug 5, 2025$0/M input tokens$0/M output tokens
llama-3_2-nemoretriever-300m-embed-v1
Embeddings
33K context
Turns text into vectors for search and retrieval.
by nvidiaJul 24, 2025$0/M input tokens
cosmos-transfer1-7b
Video
Generates video from text, images and video.
by nvidiaJun 13, 2025$0/M input tokens$0/M output tokens
magpie-tts-zeroshot
Speech
Turns text into spoken audio.
by nvidiaMay 22, 2025$0/M input tokens$0/M output tokens
Llama 3.1 Nemotron 70B Instruct
128K context
Reads text. Tool calling. Served by 3 providers.
by nvidiaApr 15, 2025$0.357/M input tokens$0.408/M output tokens3 providers
Nvidia Nemotron 3 Nano 30B
262K context
Reads text. Tool calling, structured output. Served by 14 providers.
by nvidiaApr 14, 2025$0.05/M input tokens$0.20/M output tokens14 providers
Llama 3.1 Nemotron Ultra 253B
128K context
Reads text. Tool calling, reasoning.
by nvidiaApr 7, 2025$0/M input tokens$0/M output tokens
Llama Guard 4 12B
128K context
Reads text and images.
by nvidiaApr 5, 2025$0/M input tokens$0/M output tokens
bevformer
128K context
Reads video.
by nvidiaMar 18, 2025$0/M input tokens$0/M output tokens
cosmos-predict1-5b
Video
Generates video from text, images and video.
by nvidiaMar 18, 2025$0/M input tokens$0/M output tokens
sparsedrive
128K context
Reads video.
by nvidiaMar 18, 2025$0/M input tokens$0/M output tokens
nv-embedcode-7b-v1
Embeddings
33K context
Turns text into vectors for search and retrieval.
by nvidiaMar 17, 2025$0/M input tokens
Gemma 3 12B IT
131K context
Reads text and images. Tool calling.
by nvidiaMar 12, 2025$0/M input tokens$0/M output tokens
Gemma 3 4B IT
131K context
Reads text and images. Tool calling.
by nvidiaMar 12, 2025$0/M input tokens$0/M output tokens
studiovoice
128K context
Reads text.
by nvidiaOct 3, 2024$0/M input tokens$0/M output tokens
Llama-3.2-90B-Vision-Instruct
128K context
Reads text and images. Tool calling.
by nvidiaSep 25, 2024$0/M input tokens$0/M output tokens
Llama 3.2 11b Vision Instruct
128K context
Reads text and images. Tool calling, structured output.
by nvidiaSep 18, 2024$0/M input tokens$0/M output tokens
esm2-650m
128K context
Reads text.
by nvidiaAug 29, 2024$0/M input tokens$0/M output tokens
FLUX.1-schnell
Image
77 context
Generates images from text.
by nvidiaAug 1, 2024$0/M input tokens$0/M output tokens
FLUX.1-dev
Image
4K context
Generates images from text.
by nvidiaAug 1, 2024$0/M input tokens$0/M output tokens
usdvalidate
Reads text.
by nvidiaJul 24, 2024$0/M input tokens$0/M output tokens
nv-embed-v1
Embeddings
33K context
Turns text into vectors for search and retrieval.
by nvidiaJun 7, 2024$0/M input tokens
Mistral-7B-Instruct-v0.3
66K context
Reads text. Tool calling, structured output. Served by 3 providers.
by nvidiaMay 22, 2024$0.111/M input tokens$0.111/M output tokens3 providers
paligemma
128K context
Reads text and images.
by nvidiaMay 14, 2024$0/M input tokens$0/M output tokens
rerank-qa-mistral-4b
Rerank
128K context
Reorders search results by relevance to a query.
by nvidiaMar 17, 2024$0/M input tokens
esmfold
128K context
Reads text.
by nvidiaMar 15, 2024$0/M input tokens$0/M output tokens
BGE M3
8K context
Reads text.
by nvidiaJan 30, 2024$0/M input tokens$0/M output tokens
Whisper Large v3
Transcription
Turns speech into text.
by nvidiaSep 1, 2023$0/M input tokens$0/M output tokens

Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.

Not sure which NVIDIA model fits?

I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.

Book Meeting