Skip to content
ModelCap

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4

Official build · attached, unrankedRestricted license

NVIDIA·nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 has a published context limit of 262K tokens in the ModelCap catalogue as of 22 Sept 2026, 03:10 UTC.

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 weight access is restricted license, from ModelCap classification of published repository metadata as of 22 Sept 2026, 03:10 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index
See primary model · Nemotron 3 Ultra
This release is visible for discovery, not ranked as a peer model
Market Gravity
10.8
Secondary market signal

This separately configured or accelerated route is reviewed as the same underlying model identity as Nemotron 3 Ultra. That canonical product owns rank and capability evidence; pricing, providers and other operational differences remain route-specific below.

OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.

Input
Unlisted
no listed API price
Output
Unlisted
no listed API price
Context
262K
tokens
Providers
0
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
fireworks-ai
live
$0.60$2.40262K384 ms110.9 tok/stools · structured

Reported evaluation leads (7)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
joelniklaus/LEXam-hard
lexam_hard
—36.69
Pinned
1bd50ee3ac80286fed27e5b89f03f4d8b4494244
Reported
Quarantined
cais/hle
hle
—26.1
Unpinned
not published
Reported
Quarantined
cais/hle
hle
—37.4
Unpinned
not published
Reported
Quarantined
harborframework/terminal-bench-2.1
terminalbench_2_1
—53.9
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—87.9
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
—69.7
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
—86.8
Unpinned
not published
Reported
Quarantined

Deployment readiness

Metadata index
70.7
partial · 88% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
92.5
Deployability
54.7
Evaluation provenance
51.5

Missing: artifactReproducibility.base-lineage, deployability.measured-provider-uptime, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
10.8
OpenRouter weekly popularity
Not listed

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Market Gravity breakdown

Usage55%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
65.7

Time since first public availability, on a six-month half-life.

Specification

Context window
262K tokens
Max output
—
Inputs
Text
Outputs
Text
Tokenizer
—
Cached input tokens
Not offered
First seen on OpenRouter
3 Jun 2026

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Licence
openmdw-1.1
Pinned revision
02462641f13d
Parameters
302.8B
Architecture
NemotronHForCausalLM
Model type
nemotron_h
Hugging Face downloads (30d)
342K
Downloads (all time)
1.4M
Likes
335
Repository
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Repository updated
24 Aug 2026, 23:46 UTC