How much does Mistral: Mixtral 8x22B Instruct cost per 1M tokens?

Mistral: Mixtral 8x22B Instruct costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on the standard tier. Cached input is $0.200 per 1M.

What is Mistral: Mixtral 8x22B Instruct's context window?

Mistral: Mixtral 8x22B Instruct accepts up to 65,536 tokens in a single request, and can return up to 52,428 output tokens.

Is there a cheaper OpenRouter model than Mistral: Mixtral 8x22B Instruct?

Yes. OpenAI: GPT-3.5 Turbo is $0.500 per 1M input tokens versus $2.00 for Mistral: Mixtral 8x22B Instruct, with a 16,385 token context window.

Where does this Mistral: Mixtral 8x22B Instruct price come from?

From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.

Mistral: Mixtral 8x22B Instruct pricing

Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Mistral: Mixtral 8x22B Instruct from OpenRouter costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. Cached input is $0.200 per 1M. Context window 65,536 tokens.

API id mistralai/mixtral-8x22b-instruct · OpenRouter · source · updated 2026-09-25 · general-purpose

$2.00

Input / 1M tokens

$6.00

Output / 1M tokens

$0.200

Cached input / 1M

66K

Context window

Mistral: Mixtral 8x22B Instruct specifications

Provider: OpenRouter
API id: mistralai/mixtral-8x22b-instruct
Model type: general-purpose
Context window: 66K tokens
Max output: 52K tokens
Currency: USD
Price source: Provider API
Last checked: 2026-09-25

What Mistral: Mixtral 8x22B Instruct costs in practice

Estimated cost at common usage volumes
Workload	Input tokens	Output tokens	Estimated cost
Short chat turn	1,000	500	$0.0050
Document summary	50,000	2,000	$0.11
1M tokens in, 200K out	1,000,000	200,000	$3.20

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does Mistral: Mixtral 8x22B Instruct cost per 1M tokens?: Mistral: Mixtral 8x22B Instruct costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on the standard tier. Cached input is $0.200 per 1M.
What is Mistral: Mixtral 8x22B Instruct's context window?: Mistral: Mixtral 8x22B Instruct accepts up to 65,536 tokens in a single request, and can return up to 52,428 output tokens.
Is there a cheaper OpenRouter model than Mistral: Mixtral 8x22B Instruct?: Yes. OpenAI: GPT-3.5 Turbo is $0.500 per 1M input tokens versus $2.00 for Mistral: Mixtral 8x22B Instruct, with a 16,385 token context window.
Where does this Mistral: Mixtral 8x22B Instruct price come from?: From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.

Head-to-head comparisons

Compare Mistral: Mixtral 8x22B Instruct with another model →

Other OpenRouter models

See all OpenRouter pricing →