Price Per TokenPrice Per Token
Mistral AI

Mixtral 8x22B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Mixtral 8x22B Instruct. Find the best value for your use case.

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

112 out of our 301 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Last updated: February 15, 2026 at 08:07 AM

Overview

Mixtral 8x22B Instruct was released on April 17, 2024. Pricing starts at $2.00 per million input tokens and $6.00 per million output tokens. The model supports a context window of up to 66K tokens. API access is available through Mistral AI.

Context Window
66K
tokens
Pricing
Input$2.00
Output$6.00
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Text only

Pricing Comparison

Compare Mixtral 8x22B Instruct with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$2.000
$6.000
14.8
53.7
33.2
65,536
Try
$1.250
$10.000
84.6
87.1
85.4
400,000
Try
$1.250
$10.000
80.1
86.2
84.4
1,048,576
Try
$1.250
$10.000
1,048,576
Try
$1.250
$1.250
128,000
Try
$1.480
$1.480
45.5
10.8
8,192
Try
$1.500
$2.000
4,095
Try
$1.600
$6.400
35.9
76.2
58.7
32,768
Try
$1.750
$14.000
400,000
Try
$1.750
$14.000
128,000
Try
$1.750
$14.000
66.9
81.4
71.2
400,000
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Mixtral 8x22B Instruct is available from multiple providers with different pricing and availability.

3
Providers
$1.200
Cheapest Input/M
$1.200
Cheapest Output/M
Vercel
Best Price

Provider Pricing

3 models

Provider
Input $/M
Output $/M
Uptime
V
Vercel
Best Price
$1.200
$1.200
-
F
Fireworks
Best Price
$1.200
$1.200
-
Mistral
Mistral
$2.000
$6.000
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Mixtral 8x22B Instruct perform? Vote based on your experience.

Cost vs. Quality

Compare Mixtral 8x22B Instruct's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Mixtral 8x22B Instruct
Other models

Detailed Benchmark Scores

Intelligence
9.8 (6th pct)
Coding
-
Math
-
MMLU Pro
53.7 (15th pct)
GPQA
33.2 (11th pct)
LiveCodeBench
14.8 (7th pct)
AIME
- (0th pct)
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Mixtral 8x22B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Mixtral 8x22B Instruct directly in your browser.

Open Playground

Frequently Asked Questions

Mixtral 8x22B Instruct costs $0.002000 per 1,000 input tokens and $0.006000 per 1,000 output tokens.
Mixtral 8x22B Instruct is available from 3 provider(s). Vercel offers the best price.
We compare Mixtral 8x22B Instruct with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Mistral AI Models

See pricing for all Mistral AI models.

View all Mistral AI models →