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.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Mixtral 8x22B Instruct was released on April 17, 2024. Pricing starts at $1.20 per million input tokens and $1.20 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$1.20
Output$1.20
Cached$0.200
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ToolsCaching

Mixtral 8x22B Instruct is priced at $1.20 per million input tokens and $1.20 per million output tokens. It has a context window of 65,536 tokens. It is available from 4 providers, with Vercel the cheapest at $1.20 per million input tokens (input prices range from $1.20 to $2.00).

Pricing Comparison

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

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$1.200
$1.200
—
—
—
65,536
Try
$1.027
$6.162
—
—
—
262,144
Try
$1.040
$4.160
—
—
—
32,768
Try
$1.100
$4.400
—
—
—
200,000
Try
$1.100
$4.400
—
—
—
200,000
Try
$1.100
$4.400
—
—
—
200,000
Try
$1.100
$4.400
—
—
—
200,000
Try
$1.130
$3.940
—
—
—
-
Try
$1.200
$4.000
—
—
—
202,752
Try
$1.200
$4.000
—
—
—
202,752
Try
$1.200
$1.200
—
—
—
65,336
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.

4
Providers
$1.200
Cheapest Input/M
$1.200
Cheapest Output/M
Vercel
Best Price

Provider Pricing

4 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
V
Vercel
Best Price
$1.200
$1.200
-
-
-
Fireworks
Fireworks
Best Price
$1.200
$1.200
$0.600
-
-
Mistral
Mistral
$2.000
$6.000
$0.200
-
-
$2.000
$6.000
$0.200
-
-
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...
Other models

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 $0.001200 per 1,000 input tokens and $0.001200 per 1,000 output tokens.
Mixtral 8x22B Instruct is available from 4 providers. Vercel offers the best price.
Vercel offers Mixtral 8x22B Instruct at $1.20 per million input tokens, the lowest of 4 providers (input prices range from $1.20 to $2.00 per million tokens).
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 →