Free Nemotron model via API

Ultra, Super, and Nano from the Nemotron 3 and 4 line. The catalog mixes NVIDIA NIM and compatible aggregators without merging their quotas.

17 models8 providersup to 1M contextbest: Nemotron 3 UltraUpdated: October 31, 2026 at 01:14 PM UTC

NVIDIA Build needs a developer account. A third-party :free route is a different key and a different cap.

#	Model ↕	AA Index ↕	GPQA ↕	Context ↕	Size ↕	Free at ↕
1	Nemotron 3 Ultra NVIDIA · 550B · 55B ReasoningCodingTool useOpen weights	22.9	87%	1M	Frontier	OpenRouter, NVIDIA Build, UnoRouter
2	Nemotron 3.5 Lightning NVIDIA · 30B · 3B ReasoningTool useOpen weights	12.9	74%	1M	Mid-size	+1OpenRouter, NVIDIA Build, Vercel AI Gateway, UnoRouter, OpenCode Zen
3	Nemotron 3 Nano Omni NVIDIA · 30B · 3B VisionReasoningTool useOpen weights	10.3	47%	262K	Mid-size	+1OpenRouter, Together AI, NVIDIA Build, TokenRouter, UnoRouter
4	Nemotron 3 Super NVIDIA · 120B · 12B ReasoningCodingTool useOpen weights	12.8	80%	262K	Frontier	NVIDIA Build, UnoRouter
5	Nemotron 3 120B NVIDIA · 120B · 12B ReasoningTool useOpen weights	—	—	256K	Frontier	Cloudflare Workers AI
6	Nemotron 3.5 Super VL NVIDIA VisionReasoningTool useOpen weights	—	—	1M	Mid-size	OpenRouter, UnoRouter, OpenCode Zen
7	Nemotron 3.5 Super VL 120B NVIDIA · 120B · 12B VisionReasoningTool useOpen weights	—	—	—	Frontier	NVIDIA Build
8	Nvidia Nemotron 3 Super NVIDIA · 120B · 12B ReasoningCodingTool useOpen weights	12.8	80%	262K	Frontier	Together AI
9	Nemotron 3 Nano NVIDIA · 30B · 3B Tool useOpen weights	8.9	76%	1M	Mid-size	NVIDIA Build
10	Nvidia Nemotron 3 Nano NVIDIA · 30B · 3B ReasoningTool useOpen weights	8.9	76%	262K	Mid-size	Together AI
11	Nemotron 3.5 Bolt E4b NVIDIA ReasoningTool useOpen weights	—	—	—	Mid-size	NVIDIA Build
12	Llama 3.3 Nemotron Super 49B NVIDIA · 49B Tool useOpen weights	8.9	64%	16K	Mid-size	Together AI
13	Llama 3.1 Nemotron Ultra 253B NVIDIA · 253B Tool useOpen weights	7.5	73%	128K	Frontier	NVIDIA Build
14	Nemotron 4 340B NVIDIA · 340B · Legacy Open weights	—	—	—	Frontier	NVIDIA Build
15	Llama 3.1 Nemotron 51B NVIDIA · 51B · Legacy Open weights	—	—	—	Mid-size	NVIDIA Build
16	Llama 3.1 Nemotron 70B NVIDIA · 70B · Legacy Open weights	6.9	47%	16K	Frontier	Together AI, NVIDIA Build
17	Nemotron 3.5 Content Safety NVIDIA · Moderation Open weights	—	—	128K	Mid-size	OpenRouter

Benchmarks: Artificial Analysis (September 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.

About Nemotron

NVIDIA · open weights

NVIDIA's Nemotron line covers open reasoning and agent models from Nano to Ultra, many built on hybrid Mamba-Transformer MoE architectures.

Official site

FAQ

Which Nemotron models are free?

Currently 17 models are free: Nemotron 3 Ultra, Nemotron 3.5 Lightning, Nemotron 3 Nano Omni, Nemotron 3 Super, Nemotron 3 120B, Nemotron 3.5 Super VL.

Where can I get a free Nemotron API key?

Free Nemotron routes are available at: OpenRouter, NVIDIA Build, UnoRouter, Vercel AI Gateway, OpenCode Zen, Together AI, TokenRouter, Cloudflare Workers AI. Get a key in the provider's dashboard; links are on each model card.

Who develops Nemotron?

NVIDIA's Nemotron line covers open reasoning and agent models from Nano to Ultra, many built on hybrid Mamba-Transformer MoE architectures.

About Nemotron

FAQ

See also