Models·NVIDIA

Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3b

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...

$0.050Input, per million tokens
$0.20Output, per million tokens
262KContext window
236KLongest answer

262K tokens of context — about 196,608 words, on a scale that ends at 2M.

What it can do

  • Reasoning
  • Tool use
  • Open weights
  • Takes text
  • Gives text

Released 14 Dec 2025 · checked 3 Oct 2026.

On these boards

More from NVIDIA