ModelRegistry
Explore text, image, video and speech models
Find the right AI by model, modality and provider.
Browse modelsChoose with facts
Turn the model directory into an actionable evaluation workflow.
Clear capabilities
Review modalities, protocols, limits and status.
Transparent coverage
See which providers expose each model.
Easy comparison
Compare candidates using consistent dimensions.
Start exploring the directory
Begin with a model, provider or organization.
Model spotlight
Nemotron 3 Ultra 550B A55B
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Compare modelsCore capabilities
A compact view of the model contract before integration.
Input and output
See supported modalities and generation directions.
Limits and context
Check context, output limits and release details.
Provider coverage
Compare the providers and protocols that expose this version.
Nemotron 3 Ultra 550B A55B FAQ
Start building with Nemotron 3 Ultra 550B A55B
Move from model evaluation to a production-ready workflow.
Core specifications
Released
2026-06-04
Context window
1M
Max output
128K
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- nemotron-3-ultra-550b-a55b
- Aliases
- Nemotron 3 Ultra 550B A55B
Resources
Capabilities
Open weightReasoningTemperatureTool call
Pricing
IN $0.5/M
OUT $2.5/M
Read $0.15/M
Capabilities and fit
Model summary
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Text
Open weightReasoningTemperatureTool call
- Output
- Text
- Capabilities
- 4
- Catalog updated
- 2026-06-04T00:00:00.000Z
- Status
Benchmark results
| Benchmark | Type | Score / rank | Evaluated |
|---|---|---|---|
| SWE-Bench Verified | Coding | 70.7 | 2026-06-04T00:00:00.000Z |
| SWE-Bench Multilingual | Coding | 67.7 | 2026-06-04T00:00:00.000Z |
| Terminal-Bench | Coding | 56.4 | 2026-06-04T00:00:00.000Z |
| GPQA | Reasoning | 87 | 2026-06-04T00:00:00.000Z |
| Humanity's Last Exam | General | 26.7 | 2026-06-04T00:00:00.000Z |
| Humanity's Last Exam | General | 37.4 | 2026-06-04T00:00:00.000Z |
| LiveCodeBench | Coding | 89 | 2026-06-04T00:00:00.000Z |
| MMLU-Pro | Knowledge | 86.8 | 2026-06-04T00:00:00.000Z |
| BrowseComp | General | 44.4 | 2026-06-04T00:00:00.000Z |
| IFBench | General | 81.7 | 2026-06-04T00:00:00.000Z |
| GDPval | General | 46.7 | 2026-06-04T00:00:00.000Z |
Provider coverage
| Provider | Input | Output | Pricing |
|---|---|---|---|
| Nvidia | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| Kenari | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| UnoRouter | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| Together AI | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| Vercel AI Gateway | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| OpenRouter | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| OpenRouter | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| NanoGPT Nvidia Nemotron 3 Ultra 550B | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| Kilo Gateway NVIDIA: Nemotron 3 Ultra (free) | IN $0.5/M OUT $2.5/M Read $0.15/M | ||
| Kilo Gateway Nemotron 3 Ultra 550B A55B | IN $0.5/M OUT $2.5/M Read $0.15/M |