NVIDIA: Nemotron 3 Nano 30B A3B chat

openrouter
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...

Capabilities

Context Window 262k tokens
Max Output 228k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.05
Output $0.20
Cache Read -
Cache Write -

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Move Chat

Select a destination folder:

Move Folder

Select a parent folder:

Folder Settings