Mistral: Mixtral 8x22B Instructmistralai
Mistral: Mixtral 8x22B Instruct: $2.00/1M input, $6.00/1M output, 66K context. Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
API Pricing (per 1M tokens)
| Input | $2.00 |
| Output | $6.00 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $3.00 |
Specs & Performance
| Context Length | 66K |
| Max Output | 52K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text, file → text |
More from mistralai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Mistral: Mixtral 8x22B Instruct API cost?
Mistral: Mixtral 8x22B Instruct costs $2.00/1M input tokens and $6.00/1M output tokens. Blended cost at a 3:1 ratio is about $3.00/1M tokens.
What is the context window of Mistral: Mixtral 8x22B Instruct?
Mistral: Mixtral 8x22B Instruct supports a 66K token context window with up to 52K output tokens.
Is Mistral: Mixtral 8x22B Instruct worth it?
Mistral: Mixtral 8x22B Instruct has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.