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...
by Nvidia|262K context|$0.50/M input tokens|$2.20/M output tokens
Endpoints
Available providers for this model, with details on pricing, context limits, and real-time health metrics.
