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

Mixtral 8x22B costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.

How much does Mixtral 8x22B cost per request?

A typical request of 800 input and 200 output tokens costs about $0.0028 on Mixtral 8x22B.

Mixtral 8x22B is more expensive than Mixtral 8x7B on input tokens, by about 186%.

No cache discount is documented for Mixtral 8x22B on the provider's pricing page.

Mistral AI

Verified against Mistral AI’s pricing page on 2026-07-02.

Legacy

Specs

Pricing (per 1M tokens)

Capabilities

mixture-of-experts

Estimated monthly cost on three common usage shapes

Workload	Est. monthly cost
Chatbot 800 input / 200 output tokens per request, 100,000 requests/month	$280.00
RAG pipeline 6,000 input / 700 output tokens per request, 30,000 requests/month	$486.00
Batch summarization 20,000 input / 1,500 output tokens per request, 5,000 requests/month	$245.00

Workload

Est. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$280.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$486.00

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$245.00

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

How much does Mixtral 8x22B cost per 1M tokens?: Mixtral 8x22B costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.
How much does Mixtral 8x22B cost per request?: A typical request of 800 input and 200 output tokens costs about $0.0028 on Mixtral 8x22B.
Is Mixtral 8x22B cheaper than Mixtral 8x7B?: Mixtral 8x22B is more expensive than Mixtral 8x7B on input tokens, by about 186%.
Does Mixtral 8x22B have cache pricing?: No cache discount is documented for Mixtral 8x22B on the provider's pricing page.

Provider

Related models

Comparisons