Saba

About Saba

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)

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Mistral Model Lineup

Compare all models from Mistral to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Cydonia 24B V4.1

Thedrummer

Input: $0.30

Output: $0.50

Context: 131k

UnslopNemo 12B

Thedrummer

Input: $0.40

Output: $0.40

Context: 1.0M

Grok 3 Mini

xAI

Input: $0.30

Output: $0.50

Context: 131k

Grok 3 Mini Beta

xAI

Input: $0.30

Output: $0.50

Context: 131k

💡 Cheaper Alternatives

Same Brand (Mistral)

Cross Brand

🚀 Quick Start

Get started with Saba API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="mistralai/mistral-saba-2502",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision