nvidia

NVIDIA: Nemotron 3 Nano 30B A3B (free)

The Nemotron 3 Nano 30B A3B from NVIDIA is designed for text processing with an impressive context length of up to 256,000 tokens and supports tools and reasoning, making it versatile for complex tasks. Despite its robust capabilities, the model operates without structured output, limiting its use to unstructured data handling. Given its free availability, the Nemotron 3 Nano 30B A3B is an attractive option for users prioritizing cost-effectiveness; however, with a blended benchmark score of 10.6 across one independent test as of August 2, 2026, it may not be at the top tier in performance. Nevertheless, its open and accessible nature makes it suitable for those on a budget or starting their exploration into AI models.

Quality Score
88/100
price + capability + benchmarks
Input Price
Free
per 1M tokens
Output Price
Free
per 1M tokens
Context Window
256,000
tokens

Benchmark results

Independent, published benchmarks. Blended score 10.6 across 1 benchmark, last refreshed 2026-08-02. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 12.2
Model ID
nvidia/nemotron-3-nano-30b-a3b:free
Vendor
nvidia
Released
December 2025
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
default
Tool Calling
✓ supported
Structured Output
not supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

Similar models

Quick answers

Is NVIDIA: Nemotron 3 Nano 30B A3B (free) free to use?
Yes. It is currently listed at no cost per token via OpenRouter, subject to provider rate limits.
What is NVIDIA: Nemotron 3 Nano 30B A3B (free)'s context window?
256,000 tokens, roughly 384 pages of text in a single request.
Does NVIDIA: Nemotron 3 Nano 30B A3B (free) support tool calling?
It supports tool calling, a reasoning mode.
Can NVIDIA: Nemotron 3 Nano 30B A3B (free) process images?
No, it is text-only on the input side.