Mistral: Saba
Mistral Saba is a lightweight, affordable model with tool use support, but its limited benchmark scores and small context window make it suitable only for simple, cost-sensitive tasks rather than complex business applications.
Assessment date: April 4, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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..
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Mistral |
Benchmark Scores
Intelligence
Benchmark data from Artificial Analysis and Hugging Face
How does Mistral: Saba stack up?
Compare side-by-side with other efficient models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.20 | $0.000200 |
| Output | $0.60 | $0.000600 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
