# Ministral 8B Instruct

> Ministral 8B Instruct is an open-weight language model from Mistral AI, released on 16 Oct 2024. It accepts text and generates text, with a 128K-token context window and up to 4K output tokens per response.

Source page: https://www.aimodel.directory/models/ministral-8b-instruct
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Mistral AI
- **Release date:** 16 Oct 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/pioneer/models/mistralai/Ministral-8B-Instruct-2410.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of Ministral 8B Instruct?

Ministral 8B Instruct has a context window of 128,000 tokens (128K) and can generate up to 4,000 tokens in a single response, according to models.dev.

### Is Ministral 8B Instruct open source?

Ministral 8B Instruct is an open-weight model. Check the license terms before commercial use.

### When was Ministral 8B Instruct released?

Mistral AI released Ministral 8B Instruct on 16 Oct 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Ministral 8B Instruct", https://www.aimodel.directory/models/ministral-8b-instruct