Mistral: Saba

Text input Text output
Author's Description

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)

Key Specifications
Cost
$$
Context
32K
Parameters
24B (Rumoured)
Released
Feb 17, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Tool Choice Top P Temperature Seed Tools Structured Outputs Response Format Frequency Penalty Max Tokens
Features

This model supports the following features:

Tools Structured Outputs Response Format
Performance Summary

Mistral Saba, a 24B-parameter model designed for the Middle East and South Asia, consistently performs among the fastest models, ranking in the 81st percentile across six benchmarks. It also offers competitive pricing, typically providing cost-effective solutions in the 69th percentile. Notably, Mistral Saba demonstrates exceptional reliability, achieving a perfect 100th percentile across all benchmarks, indicating minimal technical failures and consistent response delivery. In terms of benchmark performance, Mistral Saba shows strong capabilities in specific areas. It achieved perfect accuracy in Ethics, making it the most accurate model at its price point and among models of comparable speed. Its General Knowledge and Email Classification scores were also very high at 97.8% and 98.0% accuracy respectively, indicating robust understanding and classification abilities. While its Instruction Following accuracy was solid at 63.0%, its performance in Coding (79.0%) and Reasoning (60.0%) was more moderate, placing it in the mid-range for these categories. A key strength lies in its high accuracy for ethical considerations and general knowledge, coupled with its outstanding reliability and efficient speed. Its primary area for potential improvement appears to be in complex reasoning tasks and comprehensive coding knowledge.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $0.6

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mistral
Mistral | mistralai/mistral-saba-2502 32K $0.2 / 1M tokens $0.6 / 1M tokens
Groq
Groq | mistralai/mistral-saba-2502 32K $0.2 / 1M tokens $0.6 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by mistralai