# Mixtral 8x22B Instruct

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:
- strong math, coding, and reasoning
- large context length (64k)
- fluency in English, French, Italian, German, and Spanish

See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/).
#moe

## Model Information

- **Organization**: [Mistral](/llm.txt)
- **Slug**: mixtral-8x22b-instruct
- **Available at Providers**: 9
- **Release Date**: April 17, 2024

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [OpenRouter](/llm/openrouter.txt) | Mixtral 8x22B Instruct | 2.00 | 6.00 |  | [View](https://openrouter.ai/mistralai/mixtral-8x22b-instruct) |
| [ValorGPT](/llm/valorgpt.txt) | Mixtral 8x22B Instruct |  |  |  | [View](https://www.valorgpt.com/models/mistralai-mixtral-8x22b-instruct) |
| [Vercel AI Gateway](/llm/vercel.txt) | Mixtral MoE 8x22B Instruct | 1.20 | 1.20 |  |  |
| [Yupp](/llm/yupp.txt) | Mixtral 8x22B Instruct (OpenRouter) |  |  |  |  |
| [LangDB](/llm/langdb.txt) | mixtral-8x22b-instruct |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | Mistral: Mixtral 8x22B Instruct | 2.00 | 6.00 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | Mistral: Mixtral 8x22B Instruct | 0.90 | 0.90 |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | mixtral-8x22b-instruct | 2.20 | 6.60 |  |  |
| [Writingmate](/llm/writingmate.txt) | Mistral: Mixtral 8x22B Instruct |  |  |  | [View](https://writingmate.ai/models/mistralai/mixtral-8x22b-instruct) |

---

[← Back to all providers](/llm.txt)