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
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
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
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
Mistral: Mistral Medium 3.1 | Aug 13, 2025 | — | 262K |
Text input
Image input
Text output
|
★★ | ★★★★ | $$$$ |
Mistral: Codestral 2508 | Aug 01, 2025 | ~2.5B | 256K |
Text input
Text output
|
★★ | ★★ | $$$ |
Mistral: Devstral Medium | Jul 10, 2025 | — | 131K |
Text input
Text output
|
★★★ | ★★★★ | $$$ |
Mistral: Devstral Small 1.1 | Jul 10, 2025 | ~24B | 131K |
Text input
Text output
|
★★★ | ★★★★ | $$ |
Mistral: Mistral Small 3.2 24B | Jun 20, 2025 | 24B | 131K |
Text input
Image input
Text output
|
★★★★ | ★★★★ | $$ |
Mistral: Magistral Small 2506 | Jun 10, 2025 | ~24B | 40K |
Text input
Text output
|
★★ | ★★★ | $$$$ |
Mistral: Magistral Medium 2506 | Jun 07, 2025 | — | 40K |
Text input
Text output
|
★★★ | ★★★★ | $$$$$ |
Mistral: Devstral Small 2505 | May 21, 2025 | ~24B | 128K |
Text input
Text output
|
★★★★★ | ★★★★★ | $ |
Mistral: Mistral Medium 3 | May 07, 2025 | — | 131K |
Text input
Image input
Text output
|
★★★ | ★★★★★ | $$$$ |
Mistral: Mistral Small 3.1 24B | Mar 17, 2025 | 24B | 131K |
Text input
Image input
Text output
|
★★★★ | ★★★★ | $$ |
Mistral: Mistral Small 3 | Jan 30, 2025 | 24B | 32K |
Text input
Text output
|
★★★★★ | ★★★★★ | $ |
Mistral: Codestral 2501 | Jan 14, 2025 | ~2.5B | 262K |
Text input
Text output
|
★★★ | ★★★ | $$$ |
Mistral Large 2411 | Nov 18, 2024 | ~32B | 131K |
Text input
Text output
|
★★★ | ★★★★ | $$$$$ |
Mistral Large 2407 | Nov 18, 2024 | ~32B | 131K |
Text input
Text output
|
★★★★ | ★★★★ | $$$$ |
Mistral: Pixtral Large 2411 | Nov 18, 2024 | ~124B | 131K |
Text input
Image input
Text output
|
★★ | ★★★★ | $$$$$ |
Mistral: Ministral 3B | Oct 16, 2024 | 3B | 32K |
Text input
Text output
|
★★★★★ | ★★★ | $ |
Mistral: Ministral 8B | Oct 16, 2024 | 8B | 128K |
Text input
Text output
|
★★★ | ★★★ | $$ |
Mistral: Pixtral 12B | Sep 09, 2024 | 12B | 32K |
Text input
Image input
Text output
|
★★★★ | ★★ | $$ |
Mistral: Mistral Nemo | Jul 18, 2024 | ~12B | 131K |
Text input
Text output
|
★★★★ | ★★ | $ |
Mistral: Mistral 7B Instruct | May 26, 2024 | 7B | 32K |
Text input
Text output
|
★★★★★ | ★★ | $$ |
Mistral: Mistral 7B Instruct v0.3 | May 26, 2024 | 7B | 32K |
Text input
Text output
|
★★★★★ | ★★ | $$ |
Mistral: Mixtral 8x22B Instruct | Apr 16, 2024 | 22B | 65K |
Text input
Text output
|
★★★ | ★★ | $$$$ |
Mistral Large | Feb 25, 2024 | ~32B | 128K |
Text input
Text output
|
★★★★ | ★★★ | $$$$ |
Mistral Medium Unavailable | Jan 09, 2024 | — | 32K |
Text input
Text output
|
★★★★ | ★★★ | $$$$ |
Mistral Tiny | Jan 09, 2024 | ~7B | 32K |
Text input
Text output
|
★★★★ | ★★ | $$$ |
Mistral Small | Jan 09, 2024 | ~22B | 32K |
Text input
Text output
|
★★★★ | ★★ | $$$ |
Mistral: Mistral 7B Instruct v0.2 Unavailable | Dec 27, 2023 | 7B | 32K |
Text input
Text output
|
★★★★★ | ★★ | $$$ |
Mistral: Mixtral 8x7B Instruct | Dec 09, 2023 | 56B | 32K |
Text input
Text output
|
★★★★★ | ★★ | $$ |
Mistral: Mistral 7B Instruct v0.1 | Sep 27, 2023 | 7B | 2K |
Text input
Text output
|
★★★★ | ★★ | $$ |