Mistral: Codestral 2508
- by mistralai
- mistralai/codestral-2508
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
What the numbers mean
- Context window256,000 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 190,000 words, or 384 pages.
- Max output204,800 tokens
- The longest single reply it can write: about 150,000 words.
- Input price$0.3 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$0.9 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 cutoff2025-03-31
- 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_tokensprediction