Back to Models

NVIDIA: Nemotron 3 Nano 30B A3B

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...

Modalities

Input

text

Output

text
Pricing
Cost per 1 million tokens
Input
$0.06
Output
$0.24
Model Specs
Context Window
262,144
Max Output
52,429
Release Date
2024-12
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-02-04

Provider: