Mixtral 8x7B

Open weights Retired Text LLM MoE mixtral-8x7b

First famous open MoE: 8 experts, 12.9B active.

Released
Dec 11, 2023
Context window
32.8K tokens
Max output
8.2K tokens
Parameters
46.7B 12.9B active
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

No list price recorded for this model yet.

Specifications

Developer
Mistral AI
Model type
Text LLM
Architecture
MoE
Parameters
46.7B (12.9B active)
Input
Text
Output
Text
Knowledge cutoff
Not disclosed
License
Apache License 2.0
API access
First-party API
End of life
Mar 30, 2025
Capabilities
Flagship