# NVIDIA: Nemotron 3 Nano 30B A3B

Provider: nvidia  
Category: llm  
Model ID: `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...

## Specs

- Context length: 262144 tokens
- Max output: unknown tokens
- Modalities: text
- Released: 2025-12-14

## Pricing

- Input: $0.05 per million tokens
- Output: $0.20 per million tokens

## Providers

- **nvidia** — ctx 262144, input $0.05/M, output $0.20/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/nemotron-3-nano-30b-a3b