Mistral
Efficient

Mixtral 8x22B

Open MoE

Largest open-weights Mixtral MoE. Cheap-to-serve frontier-ish quality before Llama 3.1 405B and DeepSeek V3 took the open-weights lead.

Mixtral 8x22B is a efficient AI model from Mistral. It costs $0.9000 per million input tokens and $0.9000 per million output tokens (blended $0.9000/M), with a 64,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.9000/M
per million input tokens
OUTPUT
$0.9000/M
per million output tokens
BLENDED 70/30
$0.9000/M
unchanged since 3 May
CONTEXT
64,000
tokens

Hand-maintained from Mistral's published pricing; no check date on record.

What it is good at
  • Open-weights MoE
  • Cheap inference per active parameter
  • 64K context
Typical use cases
  • Self-hosted chat at scale
  • Fine-tune base

Benchmarks

vs. best public score
MMLU78%
Multitask academic knowledge across 57 subjects. No source recorded yet.
MATH42%
High-school competition math problems. No source recorded yet.
Python function synthesis from docstrings. No source recorded yet.
LMArena Elo1230 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Mistral

See all 15 →

Frequently asked questions

How much does Mixtral 8x22B cost?

Mixtral 8x22B costs $0.9000 per million input tokens and $0.9000 per million output tokens, for a blended reference rate of $0.9000 per million tokens.

What is Mixtral 8x22B's context window?

Mixtral 8x22B supports up to 64,000 tokens of context in a single request.

What is Mixtral 8x22B best for?

Mixtral 8x22B is well suited to Open-weights MoE, Cheap inference per active parameter and 64K context.

Who makes Mixtral 8x22B?

Mixtral 8x22B is developed and served by Mistral. It was released in Apr 2024.

Terms used on this page