Mixtral 8x22B

Mistral AI llm

Mistral AI's second open sparse mixture-of-experts model, using only 39B of its 141B parameters per token. Scores are for the base model.

overall ⌄

—

nothing published

price · $/M tokens

2 / 6

in / out, as of 2026-07-25

to run it yourself ⌄

85 GB

minimum · 338 GB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

Nothing is both cheaper and ranked as high. This model is on the value frontier — whatever you pay for it, you are paying for something.

No recorded lineage — root or standalone model.