Back to all models
nvidia
nvidiaNVIDIA: 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...
nvidia/nemotron-3-nano-30b-a3b
Context Size
262.144K
Input Price
9,000 pts/M554 Ks/M
Output Price
36,000 pts/M2,214 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerOther
Max Completion235,929 tokens
Provider Context262.144K tokens
ModeratedNo
CreatedDec 14, 2025