NVIDIA Models
NVIDIA logo

Nemotron 3 Nano 30B A3B

30B

by NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security. Note: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.

Chat with Nemotron 3 Nano 30B A3B
Input Price$0.06/1M tokens
Output Price$0.24/1M tokens
Intelligence24.3
Coding19.0

Specifications

Technical details and pricing.

ProviderNVIDIA
Context Window262,144 tokens
Release DateDec 15, 2025
ModalitiesText

Benchmarks

10 benchmark scores from Artificial Analysis.

GPQA75.7%
MMLU Pro79.4%
HLE10.2%
LiveCodeBench74.1%
AIME 202591.0%
SciCode29.6%
LCR33.7%
IFBench71.1%
Tau240.9%
TerminalBench Hard13.6%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Nemotron 3 Nano 30B A3B good for?

Use Nemotron 3 Nano 30B A3B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Nemotron 3 Nano 30B A3B cost?

Pricing is based on usage. Current rates are $0.06/1M tokens for input and $0.24/1M tokens for output.

Can I try Nemotron 3 Nano 30B A3B for free?

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

Does Nemotron 3 Nano 30B A3B support images or audio?

Nemotron 3 Nano 30B A3B focuses on text-based tasks.

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