AI model · Mistral
Mixtral 8x22B Instruct
Model ID: mistralai/mixtral-8x22b-instruct
- Input
- $2 per 1M tokens
- Output
- $6 per 1M tokens
- Context
- 66K tokens at once
- Max output
- 52K tokens per reply
- Released
- 17 Apr 2024 Mistral
What it can do
- NoReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text, file; gives text.
How its listing describes it
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.
Sources
- Mistral: Mixtral 8x22B Instruct on OpenRouter — read 2 Oct 2026