# Nemotron 3 Ultra: price, benchmarks, context

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/nemotron-3-ultra/
- **Idioma:** en
- **Atualizado:** 2026-11-17

---
**insufficient data** — 2 of 4 benchmarks

- GPQA Diamond — low-resolution caveat (S index)
- OTIS Mock AIME — saturated benchmark

Methodology v2 · updated November 21, 2026 · [Technical tie](https://meirinho.com.br/en/ia/modelos/metodologia/#empate-tecnico) · [Minimum of 4 benchmarks](https://meirinho.com.br/en/ia/modelos/metodologia/#minimo-3-benchmarks) · [Methodology](https://meirinho.com.br/en/ia/modelos/metodologia/)

NVIDIA

# Nemotron 3 Ultra

Benchmarks, price, context and versions

GPQA Diamond

Epoch AI

Input US$/1M

Third-party provider

Output US$/1M

Third-party provider

Context

tokens

## Direct answer

**Direct answer:** Nemotron 3 Ultra is a model from NVIDIA. 85.4% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 0.50 per 1 million input tokens and US$ 2.20 per 1 million output tokens.

## ✓ Good for

- running on your own infrastructure (open weights)

## ✕ Not the best for

- Not enough data in the open sources this section uses to build this block.

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. The price uses OpenRouter. Context uses OpenRouter. Scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

## Benchmarks

| GPQA Diamond[? what it is](https://meirinho.com.br/en/ia/modelos/glossario/gpqa-diamond/) | 85.4%**highest score on this metric 96.8%74º / 195 · [Epoch AI](https://epoch.ai/benchmarks/gpqa-diamond), latest version we checked |
| --- | --- |
| OTIS Mock AIME[?](https://meirinho.com.br/en/ia/modelos/glossario/otis-mock-aime/) | 86.7%**highest score on this metric 100%74º / 182 · [Epoch AI](https://epoch.ai/benchmarks/otis-mock-aime-2024-2025), latest version we checked |

## Input US$/1M · Output US$/1M

Input US$/1M

US$ 0.50

Output US$/1M

US$ 2.20

## Key specs

| Lab | [NVIDIA](https://meirinho.com.br/en/ia/modelos/lab/nvidia/) |
| --- | --- |
| Origin | the US |
| Family | Nemotron provisional data |
| Weights[?](https://meirinho.com.br/en/ia/modelos/glossario/pesos-abertos/) | open |
| License | [openmdw-1.1](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16) |
| Also known as | no data |
| Context[?](https://meirinho.com.br/en/ia/modelos/glossario/janela-de-contexto/) | 262,144 tokens |
| Parameters | 560,524,578,816 |
| Input | text |
| OpenRouter usage[?](https://meirinho.com.br/en/ia/modelos/glossario/uso-no-openrouter/) | 1.67% OpenRouter |
| Downloads (30 days)[?](https://meirinho.com.br/en/ia/modelos/glossario/downloads-hugging-face/) | 1,080,025 |
| Use cases provisional data | [Text](https://meirinho.com.br/en/ia/modelos/uso/texto/) [Agents](https://meirinho.com.br/en/ia/modelos/uso/agentes/) |
| Dates in sources | no official dateJune 4, 2026, published, per Epoch AIJune 4, 2026, listed on OpenRouterJune 3, 2026, Hugging Face repo created |

Collected November 17, 2026

## Version history

- no data

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

## Sources for this model

- Third-party provider pricing, [OpenRouter](https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b).
- No official launch announcement.
- Weights and license (openmdw-1.1), [Hugging Face](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16).
- Benchmarks: each score carries its own source, in the table above.

## FAQ

On OpenRouter, US$ 0.50 per 1 million input tokens and US$ 2.20 per 1 million output tokens.

Yes, it has open weights. License: openmdw-1.1.

85.4% on GPQA Diamond, per Epoch AI.

Nemotron 3 Ultra is a model from NVIDIA, with open weights, used for text, agents.

262,144 tokens, per OpenRouter.

No data: there is no SWE-bench Verified measurement for it in open sources.

It was made by NVIDIA, a lab from the US.

provisional data Questions ordered by what shows up in public Google search suggestions (no volume). Answers use source data only.

## Compare with

### Models from NVIDIA

- [Nemotron 3.5 Super VL](https://meirinho.com.br/en/ia/modelos/nemotron-3-5-super-vl/)
- [Nemotron 3.5 Lightning](https://meirinho.com.br/en/ia/modelos/nemotron-3-5-lightning/)
- [Nemotron 3 Super](https://meirinho.com.br/en/ia/modelos/nemotron-3-super-120b-a12b/)
- [Nemotron 3 Nano 30B A3B](https://meirinho.com.br/en/ia/modelos/nemotron-3-nano-30b-a3b/)
- [Nemotron 3.5 Content Safety](https://meirinho.com.br/en/ia/modelos/nemotron-3-5-content-safety/)
- [Switchyard](https://meirinho.com.br/en/ia/modelos/switchyard/)

[See lab](https://meirinho.com.br/en/ia/modelos/lab/nvidia/)

## How to cite

If you use this data, cite the page and the date you accessed it.

```
Adriano Meirinho. "Nemotron 3 Ultra". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/nemotron-3-ultra/. Accessed November 21, 2026.
```

Third-party data follows the license of each source. The full table is available as [CSV](https://meirinho.com.br/ia/modelos/dados.csv) and [JSON](https://meirinho.com.br/ia/modelos/dados.json).

[#](#)
