Mistral AIMixtralTool use

Mixtral 8x7B pricing

Mistral AI's mixture-of-experts model offering strong performance at moderate cost. This page tracks 8 listings in total. Highlighted lows are $0.070 per million input and $0.240 per million output (see table for which seller matches each).

32K context·8 providers·save up to 90% vs native via Perplexity·verified Apr 7, 2026
Best input$0.070per 1M tokens · Perplexity
Best output$0.240per 1M tokens · Groq

Pricing across providers

Every row is a seller of Mixtral 8x7B with token pricing we track. The cheapest input in this snapshot is from Perplexity. The bar chart shows the same input and output dollars per million for a quick scan.

O
Openrouter
Input / 1M
$0.540
Output / 1M
$0.540
S
Snowflake
Input / 1M
N/A
Output / 1M
N/A
G
Groq
Input / 1M
$0.240
Output / 1M
$0.240
FA
Fireworks AI
Input / 1M
$0.500
Output / 1M
$0.500
P
Perplexity
Input / 1M
$0.070
Output / 1M
$0.280
D
DeepInfra
Input / 1M
$0.240
Output / 1M
$0.240
TA
Together AI
Input / 1M
$0.600
Output / 1M
$0.600
MA
Mistral AInative
Input / 1M
$0.700
Output / 1M
$0.700

Input vs output · per provider

Cost calculator

Use this block to stress test Mixtral 8x7B cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.540/M·Out: $0.540/M

0.054000¢ / req

0.027000¢ / req

Daily
$8.10
Monthly
$243
Annual
$3.0K
23% cheaper than the native API at this usage level

Model specifications

These fields describe Mixtral 8x7B as we store it (Family: Mixtral. source: Mistral AI). They sit next to price so buyers can check limits and tools in one place.

Context window
32,000 tokens
Max output
4,096 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
Yes
Released
Dec 2023
Primary provider
Mistral AI
Model family
Mixtral

Compare Mixtral 8x7B

Open a pair page to see Mixtral 8x7B next to another model with a shared provider matrix. 6 shortcuts below.

Frequently asked questions

Quick frequently asked items for Mixtral 8x7B pricing and limits. The short model note from our index: Mistral AI's mixture-of-experts model offering strong performance at moderate cost.

Mixtral 8x7B costs $0.70 per million input tokens and $0.70 per million output tokens via the native API.

Also from Mistral AI

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