Mistral: Saba
Mistral Saba is a lightweight, affordable model with modest benchmark performance and a limited 32K context window, best suited to simple text tasks where cost is the primary concern. Its capabilities are fairly limited compared to more competitive offerings in the current market.
Assessment date: March 14, 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
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 datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Mistral |
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.20 | $0.000200 |
| Output | $0.60 | $0.000600 |
External Resources
Data sourced from OpenRouter API, Artificial Analysis and Hugging Face Open LLM Leaderboard. Scores are editorially curated by our team.
Last updated: March 15, 2026 7:52 pm