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 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)

Input Cost
$0.20
per 1M tokens
Output Cost
$0.60
per 1M tokens
Context Window
32,768
tokens
Compare vs GPT-4o
Developer ID: mistralai/mistral-saba

Related Models

mistralai
$2.00/1M

Mistral Large 2407

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a ...

📝 131,072 ctx Compare →
mistralai
$0.10/1M

Mistral: Devstral Small 1.1

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering ...

📝 131,072 ctx Compare →
mistralai
$0.06/1M

Mistral: Mistral Small 3.2 24B

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimiz...

📝 131,072 ctx Compare →