M
Mistral AI

Mixtral 8x22B Instruct pricing & price history

toolsmistralai/mixtral-8x22b-instruct

Mixtral 8x22B Instruct by Mistral AI costs $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 66K token context window.

$2.00Input / 1M tokens
$6.00Output / 1M tokens
66KContext window
Intelligence index

Price history

$0.00$3.45$6.90 2026-09-24today input /1M output /1M

No price changes since tracking began on 2026-09-24. We check hourly.

Cost calculator

Cheaper alternatives to Mixtral 8x22B Instruct

ModelInputOutputContextIntel.
$0.08$0.20262K12.9compare
$0.04$0.321.3M34.3compare
$0.15$0.15262K5.5compare
M
Llama 4 Scout
Meta Llama
$0.10$0.301.3Mcompare
$0.14$0.281Mcompare
$0.18$0.18164Kcompare
$0.10$0.501.1Mcompare
O
$0.10$0.501.1M37.3compare

About Mixtral 8x22B Instruct

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,...

FAQ

How much does Mixtral 8x22B Instruct cost?

Mixtral 8x22B Instruct by Mistral AI costs $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 66K token context window. A typical request with 2,000 input and 500 output tokens costs about $0.007.

What is the context window of Mixtral 8x22B Instruct?

Mixtral 8x22B Instruct supports up to 65,536 tokens of context and up to 52,428 output tokens per request.

Has Mixtral 8x22B Instruct’s price changed?

No price changes recorded since ModelBank started tracking it on 2026-09-24.

Is Mixtral 8x22B Instruct being deprecated?

No retirement date has been announced for Mixtral 8x22B Instruct as of 2026-09-24.

What are cheaper alternatives to Mixtral 8x22B Instruct?

Cheaper options include Nemotron 3.5 Lightning ($0.08/$0.20), DeepSeek V4 Flash 0731 ($0.04/$0.32), Ministral 3 8B 2512 ($0.15/$0.15), Llama 4 Scout ($0.10/$0.30).