This model is over 2 years old. The same company has since released something newer: Shieldstral-1.0-3B (2026-08-05). The details below are still accurate for this model — it just is not what we would recommend today.

Mixtral 8x22B Instruct

Mistral AI🇫🇷 France
active
Context window66K tokens
Input / 1M tokens$2
Output / 1M tokens$6

Version History

8x22b-instructmajor

Initial release of instruct fine-tuned Mixtral 8x22B with 39B active parameters out of 141B total. Optimized for cost-efficient inference with 64K context window.