All Models

NVIDIA Nemotron 3 Nano 30B

nemotron Tool Calling Open Weights Structured Output

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 open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Providers 2
Released Dec 15, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

13.2
Intelligence Index
15.8
Coding Index
13.3
Math Index

Available Providers (2)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Venice AI nvidia-nemotron-3-nano-30b-a3b $0.07/MTok $0.30/MTok 128K 16.4K
NanoGPT nvidia/nemotron-3-nano-30b-a3b $0.17/MTok $0.68/MTok 256K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output