modelgrep
M

Mistral: Mixtral 8x22B Instruct

mistralai/mixtral-8x22b-instruct

ToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
112
49th fastest
Latency
363ms
first token
Input price
$2.00
250th cheapest
Context
66K

How it compares

Faster than84%
of all ranked models
Cheaper than16%
of all ranked models

Overview

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,...

Benchmarks

independent · via OpenRouter
Artificial Analysis
GPQA Diamond
33%
Humanity's Last Exam
4%
SciCode
19%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Mistral$2.00$6.00100%

Specifications

Context window66K
Max output
Knowledge cutoffJan 2024
Input modalitiestext, file
Output modalitiestext
Prompt caching
Cache read price$0.200/M
ModeratedNo

Mixtral 8x22B Instruct FAQ

How much does Mixtral 8x22B Instruct cost?

Mixtral 8x22B Instruct costs $2.00 per million input tokens and $6.00 per million output tokens via OpenRouter, making it 250th cheapest of 298 paid models.

How fast is Mixtral 8x22B Instruct?

Mixtral 8x22B Instruct generates around 112 tokens per second with 363ms time-to-first-token (p50), the 49th fastest tracked model.

What is Mixtral 8x22B Instruct's context window?

Mixtral 8x22B Instruct supports a 66K-token context window. It accepts text, file input.

Compare head-to-head