SF·SIX / MODEL PROFILE
Mistral Saba
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...
Mistral Saba costs $0.20 per 1M input tokens and $0.60 per 1M output tokens at the standard tier, the lowest default-region price among the 1 provider SF·SIX tracks, from Mistral AI. Cached input reads cost $0.02 per 1M tokens. Updated ; prices checked .
- Developer
- Mistral AI
- Input modalities
- text, file
- Output modalities
- text
- Context tokens
- 32,768
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.20 input / $0.60 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| Mistral AIOpenRouter | $0.20 | $0.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Mistral AIOpenRouter · Zero data retention | $0.20 | $0.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Mistral AIOpenRouter · EU region | $0.22 | $0.66 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.