Mistral AI · all models ›

MSabaAPI

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.

33KContext window · tokens
$0.2Input price · per M tokens
$0.6Output price · per M tokens
Mistral AIProvider

Prices update automatically — checked daily against provider list prices.

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Saba, measured by Artificial Analysis. Higher is better.

Intelligence index6.2
GPQA42.4%
MMLU-Pro61.1%
Humanity's Last Exam4.3%
SciCode24.1%
MATH-50067.7%
AIME13%
vs. models measured heretop 94%
Scores higher than 6% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.2 per 1M tokens (median of 21) — this one costs $0.3.
Cheaper and better on this index: GLM 5.3 Flash · GPT-5.6 Luna (batch) · DeepSeek V4 Flash 0731 and 50 more
Benchmark data by Artificial Analysis

About this model

Saba is a commercial AI model by Mistral AI. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is Saba?

Saba is an AI language model from Mistral AI. It is a proprietary model, available through an API. It scores 6.2 on the Artificial Analysis intelligence index.

Is Saba free?

Saba is not free: it costs $0.2 per million input tokens and $0.6 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is Saba good at?

Independent benchmarks from Artificial Analysis give it GPQA 42.4%, MMLU-Pro 61.1%, Humanity's Last Exam 4.3%, SciCode 24.1%, MATH-500 67.7%, AIME 13%.

Related models

Mistral Medium 3.5Mistral AIMistral LargeMistral AIMistral Large 2407Mistral AIMistral Medium 3.1Mistral AIMistral Medium 3Mistral AIMistral Large 3 2512Mistral AI