Nemotron 3 Ultra 550B A55B specs, prices, where it runs and its benchmark standing

Name: Nemotron 3 Ultra 550B A55B
Author: Nvidia

open weights · top 10 on 0 of 3 · released Jun 4, 2026

Provider: Nvidia
Release date: Jun 4, 2026; Boards
Parameters: 561B total, 55B active per token; Hugging Face
Modalities: Text to Text; OpenRouter
License: OpenMDW 1.1; Hugging Face
Context window: 262K tokens; Pricing
Pricing: $0.4 in / $1.76 out per 1M tokens; All prices
Hosting: 5 priced API routes · OpenRouter · self-host: weights on Hugging Face; Pricing
Hardware: Estimate: about 1121 GB of weights as published (BF16), about 561 GB at 8-bit, about 280 GB at 4-bit, plus memory for the context; Hugging Face config
Weights: Open weights
Benchmarks: 3 boards captured

Rank	Board	Category	Score	Of
14	OpenRouterUsage · as “nvidia/nemotron-3-ultra-550b-a55b-20260604”	Usage	3.0T tok	18
38	AA IntelligenceReasoning · as “Nemotron 3 Ultra 550B A55B (Reasoning)”	Reasoning	11.8	50
58	LiveBenchReasoning · as “nemotron-3-ultra-550b-a55b”	Reasoning	67.4%	64

Versions and release history

2 versions in this line since Jun 4, 2026, from Pricing, OpenRouter and the boards.

Version	Released	Source
Nemotron 3 Ultra	Jun 4, 20265 months ago	Boards
Nemotron 3 Ultra 550B A55Bthis model	Jun 4, 20265 months ago	Boards

Category ranks, more models and catalog changes