# Mixtral 8x22B

> Mixtral 8x22B is an open-weight language model from Mistral AI, released on 17 Apr 2024. It accepts text and generates text, with a 64K-token context window and up to 64K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $2 per million input tokens and $6 per million output tokens (Mistral API), across 1 provider we track.

Source page: https://www.aimodel.directory/models/open-mixtral-8x22b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Mistral AI
- **Release date:** 17 Apr 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Context window:** 64K (64,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Max output:** 64K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Knowledge cutoff:** Apr 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/mistral/models/open-mixtral-8x22b.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Mistral API | $2 | $6 | – | 64K |

## FAQ

### What is the context window of Mixtral 8x22B?

Mixtral 8x22B has a context window of 64,000 tokens (64K) and can generate up to 64,000 tokens in a single response, according to models.dev.

### How much does the Mixtral 8x22B API cost?

Through Mistral API, Mixtral 8x22B costs $2 per million input tokens and $6 per million output tokens. Prices last verified 4 Oct 2026.

### Is Mixtral 8x22B open source?

Mixtral 8x22B is an open-weight model. Check the license terms before commercial use.

### When was Mixtral 8x22B released?

Mistral AI released Mixtral 8x22B on 17 Apr 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Mixtral 8x22B", https://www.aimodel.directory/models/open-mixtral-8x22b