Model prices / Mistral AI / Mixtral 8x22B Instruct
Mixtral 8x22B InstructOpen weights
Mistral AI · released 2024-04-17
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.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
KKilo GatewayLowestmistralai/ | $2 | $6 | $0.2 | Lowest | Official docs |
NNanoGPTmistralai/ | $2 | $6 | $0.2 | Official docs | |
 OpenRoutermistralai/ | $2 | $6 | $0.2 | Official docs | |
 AI/ML APImistralai/ | $2.116 | $6.348 | $0.2116 | Official docs | |
PPrime Inferencemistralai/ | $2.2 | $6.6 | — | Official docs |
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.
About
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Description from models.dev.
Specs
- Type
- Text
- Context
- 65.5K
- Max output
- 52.4K
- Input
- Text, PDF
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2024-01-31
- Open weights
- Yes
- Released
- 2024-04-17
Source
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.