Provider logo

Mixtral 8x22B

mistralai/mixtral-8x22b-instruct-v0.1
Provider logo

Mixtral 8x22B

mistralai/mixtral-8x22b-instruct-v0.1

Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.

Added Dec 11, 2025

Model weights

Context Window

65.5K

Max Output

65.5K

Input Price (Auto)

$2.00/1M

Output Price (Auto)

$6.00/1M

Cache Read (Auto)

$0.20/1M

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

4.4

Better than 13% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

33.2%

Better than 12% of models compared

HLE

Humanity's Last Exam

4.1%

Better than 15% of models compared

Coding

SciCode

Python programming for scientific computing

18.8%

Better than 21% of models compared

LiveCodeBench

Contamination-free coding benchmark

14.8%

Better than 15% of models compared

Math

AIME

American Invitational Mathematics Examination

0.0%

Better than 3% of models compared

Math-500

Diverse mathematical problem solving benchmark

54.5%

Better than 17% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

53.7%

Better than 17% of models compared

Last updated Jun 28, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Mixtral 8x22B with similar models from the same provider or model family.