Model comparison
Mistral Saba vs Mistral Small
Capability radar, value bars, and side-by-side posture.
Mistral Saba
Not scored
value score
Mistral Small
74
value score
Mistral Saba ctx
—
Mistral Small ctx
32K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Mistral Small74
Attribute tape
| Field | Mistral Saba | Mistral Small |
|---|---|---|
| Developer | Mistral AI | Mistral AI |
| Context | — | 32K |
| Modalities | Text, Code | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $0.1/1M in · $0.3/1M out |
| Value score | — | 74 |
| Summary | Mistral Saba is a 24B-parameter language model from Mistral AI, fine-tuned for Arabic and South Asian languages (including Tamil and Malayalam), designed for regional enterprise text generation and conversation with a 32k context window. It is positioned as a compact, single-GPU-deployable model intended to outperform larger general-purpose models on Middle Eastern and South Asian language tasks. | Fast Mistral small model. |