Mistral: Mixtral 8x22B Instruct
- by mistralai
- mistralai/mixtral-8x22b-instruct
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,...
What the numbers mean
- Context window65,536 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 49,000 words, or 98 pages.
- Max output52,428 tokens
- The longest single reply it can write: about 39,000 words.
- Input price$2 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$6 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext, file in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
- Knowledge cutoff2024-01-31
- The last date its training data covers. It does not know about anything after that unless you put it in the prompt.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltymax_tokenspresence_penalty