# Mistral: Mixtral 8x22B Instruct API prices

Mistral: Mixtral 8x22B Instruct (mistral) — 66k context, 52k max output.
1 metered per-token offers from 2 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $2 | $6 | $0.2 | 66k |

## Summary

- Cheapest input: $2 per 1M tokens (Kilo Gateway)
- Cheapest output: $6 per 1M tokens (Kilo Gateway)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2024-04-17
- Inputs: pdf, text

HTML page: https://llmprice.gitlab.io/models/mistral-mixtral-8x22b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json