NVIDIA: Nemotron 3 Super chat
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Capabilities
Context Window 1M tokens
Max Output 16k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.08
Output $0.40
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p