Mistral Saba 2502
Review Mistral Saba 2502 on key metrics including price, context length, throughput, and model features.
AuthorMistralAI
Context Length32.8k
Supports Tools
Mistral Saba is a 24B-parameter language model specifically developed for the Middle East and South Asia. It delivers accurate and contextually relevant responses in multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. The model is trained on curated regional datasets and is optimized for multilingual and regional applications.
Activity
Last 14 daysPrompt
28Completion
3Total
31Startup
Startup
Latency (p50)-
Throughput (p50)-
Pricing
Input$0.10/M tokens
Output$0.30/M tokens
Features
Input Modalitiestext
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools