Mixtral 8x22B Instruct

mistralai/mixtral-8x22b-instruct

The Mixtral 8x22B Instruct model from Mistral AI processes text and file inputs to generate text outputs. It supports a context length of 65,536 tokens and includes tool use capabilities. Pricing is set at $2 per million input tokens and $6 per million output tokens.

  • tool use
  • structured outputs
  • open-weight

At a glance

providermistralai
releasedApr 17, 2024
context66K
input / M$2

Specifications

What the API gives you

Context window
66K tokens
Max output
52K tokens
Input price
$2 / 1M tokens
Output price
$6 / 1M tokens
Cache read
$0.20 / 1M tokens
Modalities
text, file → text
Knowledge cutoff
Jan 31, 2024
Released
Apr 17, 2024

Benchmarks

No independent benchmark results are linked to this model yet. We keep it visible while withholding quality claims until usable results arrive.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

No exact-version task evidence is linked yet. Official release claims will appear provisionally; independent results are required for established status.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.