Home › Providers › mistralai › Mistral: Mixtral 8x22B Instruct
Mistral: Mixtral 8x22B Instruct API Pricing
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?
- OpenAI: GPT-5.2 (batch) — $0.875 in / $7 out per 1M
- Magnum v4 72B — $2.5 in / $5 out per 1M
- Z.ai: GLM 5.2 — $0.0341 in / $7 out per 1M
- OpenAI: GPT-5.6 Terra Pro (batch) — $1 in / $6 out per 1M
- OpenAI: GPT-5.6 Terra (batch) — $1 in / $6 out per 1M
- Google: Gemini 3.1 Pro Preview (batch) — $1 in / $6 out per 1M
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 21, 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. 20 free models are listed on the free models page.
Provider: mistralai · Model ID: mistralai/mixtral-8x22b-instruct · Modality: text+file->text · Price snapshot October 21, 2026, refreshed daily. How we collect prices