by Nvidia

NVIDIA Nemotron 3 Ultra NVFP4.

text open weights 262K ctx

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 wo

Where to use it

Cheapest hosted endpoints.

Provider	Access	$/M in	$/M out
Fireworks AI	hosted inference	—	—	Launch ↗

FAQ

Frequently asked.

How do I run NVIDIA Nemotron 3 Ultra NVFP4?

NVIDIA Nemotron 3 Ultra NVFP4 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.

Where can I access NVIDIA Nemotron 3 Ultra NVFP4?

NVIDIA Nemotron 3 Ultra NVFP4 is available via Fireworks AI. Each access option lists its own pricing (per million tokens or hourly hosting).

How much does it cost to run NVIDIA Nemotron 3 Ultra NVFP4?

Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.

Is NVIDIA Nemotron 3 Ultra NVFP4 open-source or proprietary?

NVIDIA Nemotron 3 Ultra NVFP4 is open-weight under the license. You can download and self-host it.