Mixtral 8x22B Instruct
As of Nov 22, 2026, the cheapest Mixtral 8x22B Instruct API price is $2 per 1M input tokens (Kilo Gateway) and $6 per 1M output tokens (Kilo Gateway). Mixtral 8x22B Instruct is offered by 4 providers in the mixtral family, open weights.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| Kilo Gatewayopenmistralai/mixtral-8x22b-instruct | Cheapest$2 | Cheapest$6 | $0.2 | — | 66k | — |
| OpenRouteropenmistralai/mixtral-8x22b-instruct | $2 | $6 | $0.2 | — | 66k | — |
| AI/ML APIopenmistralai/mixtral-8x22b-instruct | $2.116 | $6.348 | $0.2116 | — | 66k | 30d agoout −23.1% |
| Prime Inferenceopenmistralai/mixtral-8x22b-instruct | $2.2 | $6.6 | — | — | 66k | — |
Mixtral 8x22B Instruct price history
Output price per 1M tokens since tracking began on Oct 13, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| AI/ML API | $2.7508 → $2.116 | $8.2524 → $6.348 | −23.1% |
Mixtral 8x22B Instruct pricing FAQ
What is the cheapest Mixtral 8x22B Instruct API?
As of Nov 22, 2026, Kilo Gateway has the lowest Mixtral 8x22B Instruct output price at $6 per 1M tokens, and Kilo Gateway has the lowest input price at $2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Mixtral 8x22B Instruct?
4 providers list Mixtral 8x22B Instruct on Sovyron; 4 of them sell it at a metered per-token price.
Is Mixtral 8x22B Instruct free?
No provider in the Sovyron catalog lists a free tier for Mixtral 8x22B Instruct.
What is the context window of Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct supports a 66k-token context window and up to 52k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—