Mistral: Sabamistralai
Bottom Line
Mistral: Saba: $0.20/1M input, $0.60/1M output, 33K context, CPS grade B. 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...
API Pricing (per 1M tokens)
| Input | $0.20 |
| Output | $0.60 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.30 |
Specs & Performance
| Context Length | 33K |
| Max Output | 26K |
| Intelligence | 7 |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | B |
| Input / Output Modalities | text, file → text |
More from mistralai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Mistral: Saba API cost?
Mistral: Saba costs $0.20/1M input tokens and $0.60/1M output tokens. Blended cost at a 3:1 ratio is about $0.30/1M tokens.
What is the context window of Mistral: Saba?
Mistral: Saba supports a 33K token context window with up to 26K output tokens.
Is Mistral: Saba worth it?
Mistral: Saba has a CPS grade of B (score 57), intelligence index 7, coding index —. Use the compare page to benchmark against rivals.