AI model · Mistral
Saba
Model ID: mistralai/mistral-saba
- Input
- $0.20 per 1M tokens
- Output
- $0.60 per 1M tokens
- Context
- 33K tokens at once
- Max output
- 26K tokens per reply
- Released
- 17 Feb 2025 Mistral
What it can do
- NoReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text, file; gives text.
How its listing describes it
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...
Sources
- Mistral: Saba on OpenRouter — read 2 Oct 2026