Mistral
Saba
Released 2025-02-17 · Knowledge up to 2024-09-30
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...
You send / 1M
$0.200
tokens in
It replies / 1M
$0.600
tokens out
Memory
33K
tokens it can read at once
Typical request
$0.0006
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Mistral | $0.200 | $0.600 | 100% | Read |
| Mistral | $0.220 | $0.660 | n/a | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, file
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 26K tokens
- Repeated text is billed at $0.020 per 1M (prompt caching)
- Intelligence score: 6.5 / 100 (Artificial Analysis)
Similar models
- Command R (08-2024)Cohere · $0.150 in / $0.600 out per 1M
- Gemma 2 27BGoogle · $0.650 in / $0.650 out per 1M
- ReMM SLERP 13BUndi95 · $0.350 in / $0.650 out per 1M
- Qwen3 235B A22B Instruct 2507Qwen · $0.090 in / $0.550 out per 1M
- Hermes 3 70B InstructNousresearch · $0.700 in / $0.700 out per 1M
- Cydonia 24B V4.1Thedrummer · $0.300 in / $0.500 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models