Saba: Pricing, Context Window & Benchmarks
by Mistral
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 datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post [here](https://mistral.ai/en/news/mistral-saba)
What you can do with Saba
Everyday Q&A and clear explanations
Writing help (emails, posts, summaries)
Idea generation and brainstorming
Learning support with step-by-step guidance
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Highlights
| Metric | Value |
|---|---|
| Provider | Mistral |
| Context Window | 32,768 tokens |
| Input Price | $0.00/1M tokens |
| Output Price | $0.00/1M tokens |
| Release Date | Feb 17, 2025 |
| Modalities | text |
| Capabilities | N/A |
Compare Saba to other models
See how it stacks up on price, quality, and overall performance.
Frequently asked questions
What is Saba good for?
Use Saba for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.
How much does Saba cost?
Pricing is based on usage. Current rates are $0.00/1M tokens for input and $0.00/1M tokens for output.
Can I try Saba for free?
Yes. You can start a chat instantly and test the model before deciding on a plan.
Does Saba support images or audio?
Saba focuses on text-based tasks.
Suggested comparisons
Similar models
Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.
Compare Models
Select a model to compare with Saba