NVIDIA Models
NVIDIA logo

Nemotron 3 Super

120B

byNVIDIA

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Input Price$0.30/1M tokens
Output Price$0.75/1M tokens
Intelligence36.0
Coding31.2

Specifications

Technical details and pricing.

ProviderNVIDIA
Context Window262,144 tokens
Release DateMar 11, 2026
ModalitiesText

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA80.0%
HLE19.2%
SciCode36.0%
LCR60.0%
IFBench71.5%
Tau267.8%
TerminalBench Hard28.8%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Nemotron 3 Super good for?

Use Nemotron 3 Super for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Nemotron 3 Super cost?

Pricing is based on usage. Current rates are $0.30/1M tokens for input and $0.75/1M tokens for output.

Can I try Nemotron 3 Super for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Nemotron 3 Super support images or audio?

Nemotron 3 Super focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.

Customer Support