Pass IndexThe State of AISign in

Mixtral 8x22B Instruct

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b).

text + file → text · made by Mistral AI

$1.2$1.2per Mtok in / out
Fireworks AI · 3 sellers

Sold by 4 ways

SellerLaneRate
Fireworks AI aggregatorstandard$1.2per Mtok in$1.2per Mtok outraw.githubusercontent.com · read 2026-09-16
Nous Research aggregatorstandard$2per Mtok in$6per Mtok out$0.2per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
OpenRouter 2 ways$2per Mtok in$6per Mtok out$0.2per Mtok cached
OpenRouter aggregatorstandard$2per Mtok in$6per Mtok out$0.2per Mtok cachedopenrouter.ai · read 2026-08-24
OpenRouter aggregatormistral/eu$2.2per Mtok in$6.6per Mtok out$0.22per Mtok cachedopenrouter.ai · read 2026-08-27

About

Mixtral 8x22B Instruct — a text model from Mistral AI, sold by 3 companies from $1.2 in and $1.2 out per million tokens.

It takes text and files and returns text, with a context window of 65,536 tokens. It was published in April 2024, trained on material up to January 2024. Its sellers say it can call a tool. The catalogue files it under chat. Three companies sell it. The cheapest is $1.2 in and $1.2 out per million tokens at Fireworks AI. Beside the standard rate there is a regional lane.

Every current figure

Maker
Mistral AI
Register
model
Takes
text + file
Returns
text
Context
65,536 tokens
Longest answer
52,428 tokens
Published
April 2024
Knowledge to
January 2024
Sellers
3
Maker's own price
not read
Price
$1.2 in and $1.2 out per million tokens — Fireworks AI

Known as 1 name

mistralai/mixtral-8x22b-instruct