Home/Models/Nemotron 3 Nano 30B A3B
NVIDIA logo

Nemotron 3 Nano 30B A3B

by NVIDIA · Released Dec 2025

Open Source
Compare
Context
262K tokens (~131 books)
Input $/1M
$0.05
Output $/1M
$0.20
Type
text
License
Open Source
Benchmarks
0 tested
Data as of
About

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...

No benchmark data available yet.

Recently Happened
Nemotron 3 Nano 30B A3B pricing dropped 17%
Sep 22, 2026
Nemotron 3 Nano 30B A3B pricing increased 20%
Sep 17, 2026
Links
Documentation
Community
BenchGecko API
nemotron-3-nano-30b-a3b
Specifications
  • Typetext
  • Context262K tokens (~131 books)
  • ReleasedDec 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.000
Available On
NVIDIA logoNVIDIA$0.05
Share & Export
Tweet
Nemotron 3 Nano 30B A3B is an open-source text AI model by NVIDIA, released in December 2025. Context window: 262K tokens.

Key facts · as of 2026-10-05

  • Nemotron 3 Nano 30B A3B by NVIDIA. Not enough public benchmark scores to rank yet.
  • List price $0.0500 input · $0.20 output per 1M tokens (as of 2026-10-05).
  • Sold by 4 providers (as of 2026-10-05): Crusoe (fp8) $0.0500 in / $0.20 out · DeepInfra (fp4) $0.0500 in / $0.20 out · Novita (fp4) $0.0500 in / $0.20 out · Nebius (fp8) $0.0600 in / $0.24 out. Every provider

How to cite · data as of 2026-10-05

Nemotron 3 Nano 30B A3B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/nemotron-3-nano-30b-a3b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP