Nemotron 3 Nano 30B A3B, the NVIDIA model in numbers

Overview

Nemotron 3 Nano 30B A3B is a language model from NVIDIA, released on December 15, 2025. That makes it 10 months old as of October 22, 2026. It is an open-weight model: you can host it yourself on infrastructure you control, and 18 API providers listed on models.dev also offer it. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money.

We file it under open-weight models (68 models in this category on the site).

How much does Nemotron 3 Nano 30B A3B cost?

Nemotron 3 Nano 30B A3B costs $0.05 per million input tokens and $0.20 per million output tokens (median of 18 providers, checked on October 22, 2026).

In practice, an agent task that reads 20,000 tokens and writes 2,000 costs about $0.001, or $1.4 for 1,000 such tasks.

That is 5 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

Measured performance

As of October 22, 2026, Epoch AI publishes no score for Nemotron 3 Nano 30B A3B on our basket's benchmarks. To place it, rely on its specifications and price, then test it on your own cases.

Technical specifications

Its context window reaches 262,144 tokens, roughly 393 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 262,144 tokens.

It accepts as input: text. Its knowledge stops at June 25, 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs), which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16): 31.6 billion parameters, other license and 1,272,181 downloads over the last 30 days. See also our list of open-source models.

When to choose it

Given its category, Nemotron 3 Nano 30B A3B is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

What could replace it?

In the same category, the models closest to Nemotron 3 Nano 30B A3B are:

• Nemotron 3.5 Lightning 30B A3B (NVIDIA, $0.20 per million output tokens)
• Ling 3.0 Flash Fin (inclusionAI (Ant Group), $0.22 per million output tokens)
• Ling 3.0 Flash VL (inclusionAI (Ant Group), $0.18 per million output tokens)
• Laguna S 2.1 (Poolside, $0.18 per million output tokens)