NVIDIA: Nemotron 3 Ultra (batch) reasoning
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Capabilities
Context Window 512k tokens
Max Output 0 tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.30
Output $1.80
Cache Read $0.10
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p