Home / Models / Mistral AI / Mixtral 8x22B Instruct

Mixtral 8x22B Instruct pricing and routing profile

Mixtral 8x22B Instruct from Mistral AI lists at $2.00 per million input tokens and $6.00 per million output tokens, with a 65,536-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$2.00
Output, per 1M tokens$6.00
Cached input, per 1M$0.20
Context window66K
Confidence signalNot exposed

Tool callingStructured output

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$1.26
Chat reply (2,000 in, 400 out)$6.40
Retrieval-augmented answer (8,000 in, 500 out)$19.00

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Mixtral 8x22B Instruct. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Mixtral 8x22B Instruct that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Grok 4.7$1.60 / $4.8020%
Qwen3.7 Max$1.48 / $4.4226%
GLM 5.1$1.40 / $4.4029%
Grok 4.3$1.25 / $2.5045%
Grok 4.20 Multi-Agent$1.25 / $2.5045%
Grok 4.20$1.25 / $2.5045%

Questions

How much does Mixtral 8x22B Instruct cost?

Mixtral 8x22B Instruct lists at $2.00 per million input tokens and $6.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $6.40 per 1,000 requests.

What is the context window of Mixtral 8x22B Instruct?

65,536 tokens.

Can a cheaper model replace Mixtral 8x22B Instruct?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Mixtral 8x22B Instruct on one half of your requests and make at most three answers worse on the other.