Mistral: Mistral Medium 3.1
- by mistralai
- mistralai/mistral-medium-3.1
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
What the numbers mean
- Context window131,072 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 98,000 words, or 197 pages.
- Max output104,857 tokens
- The longest single reply it can write: about 79,000 words.
- Input price$0.4 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$2 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, image, 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 cutoff2025-06-30
- 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_penaltyresponse_format