MMistral · Released Feb 17, 2025
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...
- Released
- Feb 17 2025
- Context window
- 33K 26K out
- Input / 1M tokens
- $0.20
- Output / 1M tokens
- $0.60
Where to run it
Providers
Cheapest: Mistral at $0.20 / $0.60 per 1M input / output tokens — 9% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Mistralzdr | $0.20 | $0.60 | $0.02 | 33K | 26K | 100%24h | Cheapest |
| Mistral | $0.20 | $0.60 | $0.02 | 33K | 26K | 100%24h | Cheapest |
| Mistraleu | $0.22 | $0.66 | $0.022 | 33K | 26K | — | +10% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Saba. Scores appear here automatically once it does.
Specs
Details
- Model ID
mistralai/mistral-saba- Developer
- Mistral
- Release date
- Feb 17, 2025 ·
- Context window
- 32,768 tokens
- Max output
- 26,214 tokens
- API price
- $0.20 / $0.60 per 1M input / output tokens
- Providers
- 1
- Input types
- text, file
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.