# Mixtral 8x22B Instruct API pricing

No price from the maker itself is on record for Mixtral 8x22B Instruct. The lowest of 5 providers is Kilo Gateway: $2 per 1M input tokens and $6 per 1M output tokens (as of 2026-11-12). Context window: 65.5K tokens, up to 52.4K output tokens per request.

- Type: Text
- Context: 65.5K
- Max output: 52.4K
- Released: 2024-04-17
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Kilo Gateway](https://kilo.ai) | mistralai/mixtral-8x22b-instruct | $2 | $6 | $0.2 | Lowest |
| [NanoGPT](https://docs.nano-gpt.com) | mistralai/mixtral-8x22b-instruct-v0.1 | $2 | $6 | $0.2 |  |
| [OpenRouter](https://openrouter.ai/models) | mistralai/mixtral-8x22b-instruct | $2 | $6 | $0.2 |  |
| [AI/ML API](https://docs.aimlapi.com) | mistralai/mixtral-8x22b-instruct | $2.116 | $6.348 | $0.2116 |  |
| [Prime Inference](https://docs.primeintellect.ai/inference/overview) | mistralai/mixtral-8x22b-instruct | $2.2 | $6.6 | — |  |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/mistral/mixtral-8x22b-instruct/