Pass IndexThe State of AISign in

Mixtral-8x22B-Instruct-v0.1

This is the instruction fine-tuned version of Mixtral-8x22B - the latest and largest mixture of experts large language model (LLM) from Mistral AI.

text → text · made by Mistral AI

$0.6$0.6per Mtok in / out
Nscale · 2 sellers

Sold by 2 ways

SellerLaneRate
Nscale aggregatorstandard$0.6per Mtok in$0.6per Mtok outraw.githubusercontent.com · read 2026-09-16
DeepInfra aggregatorstandard$0.65per Mtok in$0.65per Mtok outapi.deepinfra.com · read 2026-08-25

Measured 5 standings

PlaceBoardMetricScore
19thof 22Cybench — Epoch AIUnguided % Solved0.075
72ndof 81Forecastbench — Epoch AIOverall score56.3
128thof 161Dtbench — Epoch AIAccuracy55.14
169thof 170Weirdml — Epoch AIAccuracy3.17
571stof 656Epoch capabilities index — Epoch AIECI Score121.98

About

Mixtral-8x22B-Instruct-v0.1 — a text model from Mistral AI, sold by 2 companies from $0.6 in and $0.6 out per million tokens, placed 128th of 161 on Dtbench — Epoch AI.

It takes text and returns text, with a context window of 65,536 tokens. The catalogue files it under agents. Two companies sell it. The cheapest is $0.6 in and $0.6 out per million tokens at Nscale. It has been measured on 5 boards, and stands best at 128th of 161 on Dtbench — Epoch AI.

Every current figure

Maker
Mistral AI
Register
model
Takes
text
Returns
text
Context
65,536 tokens
Licence
not read
Sellers
2
Maker's own price
not read
Price
$0.6 in and $0.6 out per million tokens — Nscale
Boards
5
Best place
128th of 161 — Dtbench — Epoch AI

Known as 1 name

mistralai/Mixtral-8x22B-Instruct-v0.1