mistral-saba

completions

On:mistralaiopenrouter

mistral-saba

completions

Published by: mistralaiProviders:

mistralai openrouter

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)

Provider	Input	Output
mistralai	$0.2 / 1M tokens	$0.6 / 1M tokens
openrouter	$0.2 / 1M tokens	$0.6 / 1M tokens

Released

Feb 17, 2025

Knowledge

Aug 21, 2024

Context

32768

Input

$0.2 / 1M tokens

Output

$0.6 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
mistralai	32768 tokens	$0.2 / 1M tokens	$0.6 / 1M tokens	text	text	Apache-2.0
openrouter	32768 tokens	$0.2 / 1M tokens	$0.6 / 1M tokens	text	text

Released Feb 17, 2025Knowledge Cutoff: Aug 21, 2024

Access mistral-saba through LangDB AI Gateway

Recommended

Integrate with mistralai's mistral-saba and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Available from 2 providers

Provider:

Benchmark Results for mistral-saba

Category Performance Scores:

Academia: Score 31.00 (Top 69% - Rank #239)
Marketing: Score 48.39 (Top 36% - Rank #125)
Science: Score 45.42 (Top 73% - Rank #252)
Writing: Score 44.09 (Top 45% - Rank #156)

Overall Performance: 42.22354166666667 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	13.00	Top 60%	Mathematics
AAII	19.60	Top 68%	General
GPQA	42.40	Top 69%	STEM (Physics, Chemistry, Biology)
HLE	4.10	Top 75%	General Knowledge
MATH-500	67.70	Top 68%	Mathematics
MMLU-Pro	61.10	Top 71%	General Knowledge
SciCode	24.10	Top 60%	Scientific

GPQA Score: 42.40 - Graduate-level reasoning benchmark

Model Comparison:

Provider: mistralai

Model Type: completions

Context Size: 32768 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

13.0

Mathematics

AAII

19.6

General

GPQA

42.4

STEM (Physics, Chemistry, Biology)

HLE

4.1

General Knowledge

MATH-500

67.7

Mathematics

MMLU-Pro

61.1

General Knowledge

SciCode

24.1

Scientific

Metric	AIME	AAII	GPQA	HLE	MATH-500	MMLU-Pro	SciCode
Score	13.0	19.6	42.4	4.1	67.7	61.1	24.1

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for mistral-saba

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="mistral-saba",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "mistral-saba",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-saba",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: mistral-saba

Provider: mistralai

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from mistralai

mistral-saba

mistral-saba

Access mistral-saba through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2501

codestral-2501

mistral-saba by mistralai - AI Model Details, Pricing, and Performance Metrics

mistral-saba

mistral-saba

Access mistral-saba through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2501

codestral-2501