Saba
Mistral · mistralai/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...
Saba ranks #129 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.40 blended per million tokens, it is cheaper than 71% of models with published API pricing. Its 32,768-token context window is 8.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 26214
Pricing
Output / 1M: 0.60
Blend / 1M: 0.40
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.40per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.40 |
| 10,000,000 | $4.00 |
| 100,000,000 | $40.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Mistral
- Mistral Nemo$0.02 / 1M
- Mistral Small 3$0.07 / 1M
- Ministral 3 3B 2512$0.10 / 1M
- Mistral Small 3.2 24B$0.14 / 1M
- Ministral 3 8B 2512$0.15 / 1M
Closest API price
- UnslopNemo 12B$0.40 / 1M
- Llama 3.1 70B Instruct$0.40 / 1M
- Cydonia 24B V4.1$0.40 / 1M
- Hy3 preview$0.39 / 1M
- Qwen2.5 72B Instruct$0.38 / 1M