nvidia
NVIDIA: Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
For $1, you can send approximately:
~476messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.06/M = $0.000420
Output cost per message7,000 x $0.24/M = $0.001680
Total cost per message$0.002100
Messages for $1476.19
Context window
262k
tokens
Max response
236k
tokens
Input price
$0.06
per million tokens
Output price
$0.24
per million tokens
Modalities
Input:textOutput:text
Description
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...