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 $1.20 and the lowest output is $1.20.

66K context·3 providers·verified Sep 4, 2026
Best input$1.20per 1M tokens · Fireworks AI
Best output$1.20per 1M tokens · Fireworks AI

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: Fireworks AI.

FA
Fireworks AI
Input / 1M
$1.20
Output / 1M
$1.20
O
Openrouter
Input / 1M
$2.00
Output / 1M
$6.00
VA
Vercel Ai Gateway
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: $1.20/M·Out: $1.20/M

0.120000¢ / req

0.060000¢ / req

Daily
$18
Monthly
$540
Annual
$6.6K

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.

Locked

Compare with

Pick a model on both sides.

Popular Mixtral 8x22B Instruct comparisons

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 Fireworks AI, Openrouter, Vercel Ai Gateway.

Related models

Models close to Mixtral 8x22B Instruct by family, provider, and context window — each with live pricing in our catalog.