Mixtral 8x22B

mistral

Mixtral 8x22B is currently the most performant open model. A 22B sparse Mixture-of-Experts (SMoE). Uses only 39B active parameters out of 141B.

Try Now

Capabilities

Tool Use

Image Input

PDF Input

Example Use Cases

Complex task requiring large model capacity

Multilingual generation

Math and coding on a budget

Technical Specifications

Context Window

65,536 tokens

Max Output

65,536 tokens

Cache Miss Cost

$2 per 1M tokens

Non-Reasoning Cost

$6 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus