Magica logo

Nemotron 3 Nano 30B A3B Model Specs, Costs & Benchmarks (July 2026)

Nemotron 3 Nano 30B A3B, developed by NVIDIA, features a context window of 262.1K tokens. The model costs $0.05 per million tokens for input and $0.20 per million tokens for output. It was released on December 14, 2025, and has achieved impressive scores in various benchmarks.
Access Nemotron 3 Nano 30B A3B & 210+ other AI models all in one platformTry Magica for free

Overview

Nemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B
Model Provider
The organization behind this AI's development
NVIDIA logoNVIDIA
Input Context Window
Maximum input tokens this model can process at once
262.1K
tokens
Output Token Limit
Maximum output tokens this model can generate at once
262.1K
tokens
Release Date
When this model first became publicly available
December 14th, 2025

Pricing

Nemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B
Input Token Cost
Cost per million input tokens
$0.05
per million tokens
Output Token Cost
Cost per million output tokens
$0.20
per million tokens
Cache Read Cost
Cost to reuse cached input tokens
$0.03
per million tokens

Capabilities & Features

Nemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B
Input Types
Supported input formats
text
Output Types
Supported output formats
text
Tokenizer
Text encoding system
Other
Key Features
Advanced capabilities
βœ“ Function Callingβœ“ Structured Outputβœ“ Reasoning Mode
Reasoning Controls
Defaults and configurable reasoning effort
Optional
Open Source
Model availability

Benchmarks

Nemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B
Intelligence Index
Overall model quality across independent evaluations
14.2
(Artificial Analysis index; higher is better)
Coding Index
Programming performance across independent evaluations
14.4
(Artificial Analysis index; higher is better)
Agentic Index
Ability to complete multi-step agentic tasks
2
(Artificial Analysis index; higher is better)