nvidia
NVIDIA: Nemotron 3 Ultra (free)
nvidia/nemotron-3-ultra-550b-a55b:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
nvidia/nemotron-3-ultra-550b-a55b:free is a text-to-text NVIDIA model listed by OpenRouter with configurable reasoning, tool-related parameters, and a very large context window. NVIDIA's documentation for the linked BF16 checkpoint describes a 550B-total, 55B-active hybrid Mamba-2/MoE/attention model trained for reasoning, agentic workflows, long-context analysis, and multilingual use. Published benchmark tables indicate broad coverage, but they are vendor-reported; this pack does not establish endpoint-specific serving behavior or independent results.[1][2]
Strengths
- OpenRouter catalogs configurable reasoning, enabled by default with adjustable effort, plus tools and tool_choice parameters.[1]
- NVIDIA documentation reports up to a 1M-token context and support for English, Spanish, Brazilian Portuguese, and other languages.[1][2]
- The documented LatentMoE design combines Mamba-2, MoE, attention, and multi-token prediction, with 55B of 550B parameters active.[2]
Limitations
- Evidence is limited to OpenRouter catalog metadata plus NVIDIA-authored documentation; no independent model card or third-party evaluation is supplied.[1][2]
- Published benchmark tables are vendor-collected, so they do not prove performance on your data; workload validation remains necessary.[2]
- Endpoint-specific throughput, latency, context enforcement, and serving configuration for the :free variant are not documented in this pack.[1]
Where to use it
- Pilot long-document or large-codebase analysis where the reported large context window is relevant, after validating retrieval quality on representative inputs.[1][2]
- Evaluate tool-using agent workflows, since the catalog exposes tool parameters and NVIDIA describes agentic and tool-use training; test reliability before production.[1][2]
- Consider multilingual drafting or analysis across the documented language set, while validating the specific languages and domains you need.[2]
Sources
- [1] OpenRouter catalog · NVIDIA: Nemotron 3 Ultra (free)Sources checked: Nov 13, 2026
- [2] Model documentation · NVIDIA: Nemotron 3 Ultra (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Specifications
- Model ID
- nvidia/nemotron-3-ultra-550b-a55b:free
- Canonical ID
- nvidia/nemotron-3-ultra-550b-a55b-20260604
- Creator
- nvidia
- Added to OpenRouter
- 04.06.2026
- Context length
- 1,000,000
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · default high · efforts: high, medium, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | BB — next 30% of the cohort | — |
| Agents | BB — next 30% of the cohort | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, medium, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 11.8 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 49.3 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 20.1 | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 38% · rank 87 | 1,111Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · asciiartwin rate 36.8% · rank 65 | 1,093Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 35.4% · rank 96 | 1,133Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 37.2% · rank 87 | 1,139Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 35.4% · rank 87 | 1,127Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 32.1% · rank 78 | 1,062Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 35.3% · rank 92 | 1,128Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 34.4% · rank 102 | 1,131Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nvidia | 1,000,000 | $0 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.