Home › Providers › mistralai › Mistral: Mixtral 8x22B Instruct

Mistral: Mixtral 8x22B Instruct API Pricing

Mistral: Mixtral 8x22B Instruct is an API model from mistralai. It costs $2 per 1M input tokens and $6 per 1M output tokens, with cached input at $0.2. Its context window is 65,536 tokens with up to 52,428 output tokens. A workload of 10M input + 2M output tokens costs about $32 per month.
Input
$2
per 1M tokens
Output
$6
per 1M tokens
Cached input
$0.2
per 1M tokens
Context window
65K
65,536 tokens
Blended (80/20)
$2.8
per 1M tokens

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,...

How much does Mistral: Mixtral 8x22B Instruct cost for a real workload?

At 10M input + 2M output tokens per month, Mistral: Mixtral 8x22B Instruct costs about $32 ($20 input + $12 output). Try your own volumes in the cost calculator.

What are cheaper alternatives to Mistral: Mixtral 8x22B Instruct?

Where to run Mistral: Mixtral 8x22B Instruct

AI/ML API: one API key for 400+ models, including most models tracked here · Novita AI: pay-as-you-go APIs for open models (DeepSeek, Qwen, Llama and more) plus GPU cloud. Prices there follow each platform's own catalog and can differ from the list prices tracked here.

Run it on AI/ML API →Run it on Novita AI →

Disclosure: links to these platforms may be affiliate links — if you sign up or buy through them, LLMPrices may earn a commission at no extra cost to you.

Compare Mistral: Mixtral 8x22B Instruct with other models

Mistral: Mixtral 8x22B Instruct vs Mistral: Mistral NemoMistral: Mixtral 8x22B Instruct vs Mistral: Mistral Small 3Mistral: Mixtral 8x22B Instruct vs Mistral: Ministral 3 8B 2512 (batch)Mistral: Mixtral 8x22B Instruct vs Mistral: Ministral 3 3B 2512Mistral: Mixtral 8x22B Instruct vs Mistral: Ministral 3 8B 2512Mistral: Mixtral 8x22B Instruct vs Mistral: Mistral Small 3.2 24B

Frequently asked questions

How much does Mistral: Mixtral 8x22B Instruct cost?

Mistral: Mixtral 8x22B Instruct costs $2 per 1M input tokens and $6 per 1M output tokens (list price, snapshot October 22, 2026). At 10M input + 2M output tokens per month that is about $32.

What is the context window of Mistral: Mixtral 8x22B Instruct?

Mistral: Mixtral 8x22B Instruct has a context window of 65,536 tokens and can return up to 52,428 output tokens per response.

What are cheaper alternatives to Mistral: Mixtral 8x22B Instruct?

Cheaper models include OpenAI: GPT-5.2 (batch) ($0.875 in / $7 out), Magnum v4 72B ($2.5 in / $5 out), Z.ai: GLM 5.2 ($0.0341 in / $7 out). See the full list on this page.

Is Mistral: Mixtral 8x22B Instruct free to use?

No. Mistral: Mixtral 8x22B Instruct is a paid model at $2 input / $6 output per 1M tokens. 21 free models are listed on the free models page.

Provider: mistralai · Model ID: mistralai/mixtral-8x22b-instruct · Modality: text+file->text · Price snapshot October 22, 2026, refreshed daily. How we collect prices