LLMCost
mistralai

Mistral: Mixtral 8x22B Instruct API Pricing

Mistral: Mixtral 8x22B Instruct costs $2.00 per 1M input tokens and $6.00 per 1M output tokens (cache reads: $0.200). Context window: 66K. Prices verified 2026-08-23 Β· source

Input / 1M tokens
$2.00
Output / 1M tokens
$6.00
Context window
66K
Max output
β€”

What would Mistral: Mixtral 8x22B Instruct cost you per month?

WorkloadRequests/moAvg tokens (in/out)Est. monthly cost
Light chatbot10,000800 / 400$40.00
Coding agent5,0008,000 / 2,000$140.00
RAG pipeline30,0004,000 / 500$330.00
Doc summarizer2,00020,000 / 1,000$92.00

Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.

About Mistral: 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,...

Compare Mistral: Mixtral 8x22B Instruct with

Official resources