AIModelsTester
Mistral AItext->text

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 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)

Context Window

33K

Input Price

$0.2000/M tokens

Output Price

$0.6000/M tokens

Modality

text->text

Pricing Breakdown
Cost per million tokens for input and output
Input$0.2000/M tokens
Output$0.6000/M tokens

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.002600

Context Window Size
Maximum tokens the model can process in a single request
Context Window33K tokens
3% of 1M max

~25K

Words Equivalent

~16

Pages of Text

~328

Code Functions

Best Use Cases
What this model excels at
Data-analysisAnalytics

Related Categories:

Ready to Test Mistral: Saba?

Use our free AI Models Tester to compare Mistral: Saba with other models side-by-side using your own prompts. See real results instantly.