NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIAID: 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 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.

Pricing per 1M Tokens

Input (Prompt)$0.05
Output (Completion)$0.20
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length262K
Max Output TokensN/A
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context262K
Top Provider Max OutputN/A
ModeratedNo

Compare this model

See how NVIDIA: Nemotron 3 Nano 30B A3B stacks up against other models.

vs NVIDIA: Nemotron 3 Super (free)vs NVIDIA: Nemotron 3 Supervs NVIDIA: Nemotron 3 Nano 30B A3B (free)vs NVIDIA: Nemotron Nano 12B 2 VL (free)vs NVIDIA: Nemotron Nano 12B 2 VL

More from NVIDIA

NVIDIA: Nemotron 3 Super (free)
InputFree
Context262K
NVIDIA: Nemotron 3 Super
Input$0.10
Context262K
NVIDIA: Nemotron 3 Nano 30B A3B (free)
InputFree
Context256K
NVIDIA: Nemotron Nano 12B 2 VL (free)
InputFree
Context128K
NVIDIA: Nemotron Nano 12B 2 VL
Input$0.20
Context131K

Last updated: March 23, 2026

First tracked: March 23, 2026