nvidia

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.

Input Cost
$0.05
per 1M tokens
Output Cost
$0.20
per 1M tokens
Context Window
262,144
tokens
Compare vs GPT-4o
Developer ID: nvidia/nemotron-3-nano-30b-a3b

Related Models

nvidia
$0.10/1M

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model...

📝 131,072 ctx Compare →
nvidia
$0.20/1M

NVIDIA: Nemotron Nano 12B 2 VL

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model design...

📝 131,072 ctx Compare →
nvidia
$0.04/1M

NVIDIA: Nemotron Nano 9B V2

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA,...

📝 131,072 ctx Compare →