Mistral: Saba
- by mistralai
- mistralai/mistral-saba
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
What the numbers mean
- Context window32,768 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 25,000 words, or 49 pages.
- Max output26,214 tokens
- The longest single reply it can write: about 20,000 words.
- Input price$0.2 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$0.6 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 cutoff2024-09-30
- 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