# Mistral Large 4: price, benchmarks, context

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/mistral-large-4/
- **Idioma:** en
- **Atualizado:** 2026-11-17

---
**insufficient data** — 3 of 4 benchmarks

- technical tie with the top score — OTIS Mock AIME

- 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/)

Mistral AI

# Mistral Large 4

Benchmarks, price, context and versions

GPQA Diamond

Epoch AI

Input US$/1M

Official pricing

Output US$/1M

Official pricing

Context

tokens

## Direct answer

**Direct answer:** Mistral Large 4 is a model from Mistral AI. 90.2% on GPQA Diamond, per Epoch AI. US$ 0.70 per 1 million input tokens and US$ 2.10 per 1 million output tokens.

## ✓ Good for

- technical reasoning on science topics (44th of 195 on GPQA Diamond, in a statistical tie with 2 other models, per Epoch AI)
- very long documents or code (a window of 1 million tokens or more, according to OpenRouter)
- running on your own infrastructure (open weights)

## ✕ Not the best for

- answering short facts with little invention (74th of 87 on SimpleQA Verified, per Epoch AI)

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 is official pricing, published by the lab itself for its own API. 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/) | 90.2%**highest score on this metric 96.8%45º / 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/) | 99.4%**highest score on this metric 100%19º / 182 · [Epoch AI](https://epoch.ai/benchmarks/otis-mock-aime-2024-2025), latest version we checked |
| SimpleQA Verified[?](https://meirinho.com.br/en/ia/modelos/glossario/simpleqa-verified/) | 22.4%**highest score on this metric 94%74º / 87 · [Epoch AI](https://epoch.ai/benchmarks/simpleqa-verified), latest version we checked |

## Input US$/1M · Output US$/1M

Input US$/1M

US$ 0.70

Third-party provider pricing, OpenRouter: US$ 0.70 / US$ 2.10

Output US$/1M

US$ 2.10

Cache read US$/1M

US$ 0.07

## Key specs

| Lab | [Mistral AI](https://meirinho.com.br/en/ia/modelos/lab/mistral-ai/) |
| --- | --- |
| Origin | France |
| Family | Mistral Large provisional data |
| Weights[?](https://meirinho.com.br/en/ia/modelos/glossario/pesos-abertos/) | open |
| License | [Mistral Ecosystem Open-Weight License](https://docs.mistral.ai/models/mistral-large-4-0) |
| Also known as | API name: [mistral-large-4](https://docs.mistral.ai/inference/pricing) |
| Context[?](https://meirinho.com.br/en/ia/modelos/glossario/janela-de-contexto/) | 1,048,576 tokens |
| Parameters | no data |
| Input | image, text |
| OpenRouter usage[?](https://meirinho.com.br/en/ia/modelos/glossario/uso-no-openrouter/) | 0.05% OpenRouter |
| Downloads (30 days)[?](https://meirinho.com.br/en/ia/modelos/glossario/downloads-hugging-face/) | no data |
| 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 | November 5, 2026, official release date [Mistral AI](https://docs.mistral.ai/models/mistral-large-4-0)October 6, 2026, published, per Epoch AIOctober 6, 2026, listed on OpenRouter |

Collected November 17, 2026

## Version history

- October 6, 2026 [Mistral: Mistral Large 4](https://openrouter.ai/mistralai/mistral-large-4-0) OpenRouter, listed on OpenRouter
- September 30, 2026 [Mistral-Large-4-1T-A52B](https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B) Hugging Face Hub, Hugging Face repo created
- December 1, 2025 [Mistral: Mistral Large 3 2512](https://openrouter.ai/mistralai/mistral-large-2512) OpenRouter, listed on OpenRouter
- November 19, 2024 [Mistral Large 2407](https://openrouter.ai/mistralai/mistral-large-2407) OpenRouter, listed on OpenRouter
- February 26, 2024 [Mistral Large](https://openrouter.ai/mistralai/mistral-large) OpenRouter, listed on OpenRouter

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

## Sources for this model

- Official model page, [Mistral AI](https://docs.mistral.ai/models).
- Official pricing, [Mistral AI](https://docs.mistral.ai/inference/pricing).
- Launch announcement, [Mistral AI](https://docs.mistral.ai/models/mistral-large-4-0), November 5, 2026.
- Benchmarks: each score carries its own source, in the table above.

## FAQ

US$ 0.70 per 1 million input tokens and US$ 2.10 per 1 million output tokens.

Yes, it has open weights. License: Mistral Ecosystem Open-Weight License.

90.2% on GPQA Diamond, per Epoch AI.

Mistral Large 4 is a model from Mistral AI, with open weights, used for text, agents.

1,048,576 tokens, per OpenRouter.

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

It was made by Mistral AI, a lab from France.

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

## Compare with

### Models from Mistral AI

- [Mistral Large](https://meirinho.com.br/en/ia/modelos/mistral-large/)
- [Mistral Large 2](https://meirinho.com.br/en/ia/modelos/mistral-large-2/)

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

## How to cite

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

```
Adriano Meirinho. "Mistral Large 4". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/mistral-large-4/. 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).

[#](#)
