Mistral AIMixtralTool use

Mixtral 8x22B Instruct pricing

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/). #moe. Below you will find 3 current rows with input and output dollars per million. Right now the lowest input is $0.650 and the lowest output is $0.650.

66K context·3 providers·verified May 2, 2026
Best input$0.650per 1M tokens · Openrouter
Best output$0.650per 1M tokens · Openrouter

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 3 offers are listed for Mixtral 8x22B Instruct. Best input in this view: Openrouter.

O
Openrouter
Input / 1M
$0.650
Output / 1M
$0.650
VA
Vercel Ai Gateway
Input / 1M
$1.20
Output / 1M
$1.20
FA
Fireworks AI
Input / 1M
$1.20
Output / 1M
$1.20

Input vs output · per provider

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Mixtral 8x22B Instruct cost scales with traffic.

Provider

In: $0.650/M·Out: $0.650/M

0.065000¢ / req

0.032500¢ / req

Daily
$9.75
Monthly
$293
Annual
$3.6K

Model specifications

Quick spec sheet for Mixtral 8x22B Instruct before you dive back into pricing. Family: Mixtral. Reported under Mistral AI.

Context window
65,536 tokens
Max output
N/A
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Apr 2024
Primary provider
Mistral AI
Model family
Mixtral

Compare Mixtral 8x22B Instruct

These links open full side by side pages for Mixtral 8x22B Instruct. We picked pairs that people often shop together. 6 ready to open.

Frequently asked questions

Read these after the table if you want plain language around Mixtral 8x22B Instruct rates. The short model note from our index: Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - ...

Yes. Mixtral 8x22B Instruct is available on Openrouter, Vercel Ai Gateway, Fireworks AI.

Also from Mistral AI

Other models by Mistral AI with live pricing in our catalog.