Mistral: Saba
Mistral AI • LLM#462 of 579 in intelligence
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...
Specifications
Context Window
33K tokens
Input Price/1M
$0.20
#326 of 714
Output Price/1M
$0.60
Parameters
—
Max Output
26K tokens
Cost per Task
20.7
AA Score / US$ · higher = better
Benchmarks
Mistral: Saba results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SciCode | 24.0 | 100.0 | — |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 61.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MATH-500 | 67.7 | 100.0 | Artificial Analysis official API |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 6.2 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU Pro | 61.1 | 100.0 | Artificial Analysis official API |
| GPQA Diamond | 42.0 | 100.0 | Artificial Analysis official API |
| HLE | 4.0 | 100.0 | — |
Information
- Release date
- February 17, 2025
- Tool Calling
- ✅ Supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: Mistral: Saba
What is Mistral: Saba?
Mistral: Saba is an AI model developed by Mistral AI, classified as a large language model (LLM). It focuses on text processing and natural language generation. As an open source model, it is available for download, customization, and on-premises deployment. With a context window of 33K tokens, it is suitable for processing medium-sized documents like articles, reports, and code sections.
Pricing & Costs in 2026
Mistral: Saba is usage-based, priced at $0.2/1M input tokens and $0.6/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Benchmarks & Performance
Mistral: Saba was evaluated on 7 different benchmarks, covering categories like Coding, Knowledge, Math, overall, Reasoning. Results show moderate performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Mistral: Saba is suitable for a wide range of AI applications: automation with tool calling (API integration, databases, external systems), high-volume chatbots and automated support, text generation, summarization, translation, and general assistance.
Comparison with Alternatives
In the 2026 AI model ecosystem, Mistral: Saba competes directly with similarly capable models. Mistral AI competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is 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...
How much does Mistral: Saba cost?
Mistral: Saba costs $0.2/1M input tokens and $0.6/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does Mistral: Saba compare with other models?
In available benchmarks, Mistral: Saba scored: SciCode: 24/100, MMLU-Pro: 61/100, MATH-500: 67.7/100. See the full table above for a detailed comparison.
Is Mistral: Saba open source?
Yes, Mistral: Saba is an open source model. You can deploy it on-premises, customize it via fine-tuning, and maintain full control over your data. Check the official repository for the specific license.
What is Mistral: Saba best for?
Mistral: Saba excels at general-purpose language tasks. It supports tool calling for API integrations and automation.
Last updated: September 01, 2026 • View methodology →