Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for the most demanding workloads, including complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science. The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Like the Super model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is trained using an NVFP4 pre-training recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.
Specification
most-agreed values
Price
US dollars per million tokens · most-agreed
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| fireworks_ai | $0.60 | $2.40 | $0.12 | — | 262K | 33K | — |
| fireworks-ai · accounts | $0.60 | $2.40 | $0.119 | — | 262K | 128K | — |
| requesty | $0.60 | $2.40 | $0.12 | — | 262K | 262K | — |
More from NVIDIA
most-hosted first