Find a model

Search models and open their dedicated profile. Use the arrow keys to navigate and Enter to open.

Saba

Mistral · 1 configuration

Intelligence—
Input / 1M$0.20
Output / 1M$0.60
Context32.8K

Tariff: OpenRouter · Source: openrouter · USD per million tokens

Thinking configuration

What does more thinking buy you?

Compare this model’s measured thinking configurations.

◌

No pair of measurements available

Change the filters or pick another benchmark. Missing values are not estimated.

Selected: thinking default · Click a point to switch configuration

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...

This model is in the catalog but has no imported benchmarks. Capabilities are not estimated.

Specifications from the catalog

Inputtext, file
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output26.2K
Catalog listing date2025-02-17