Atlas / Models / Mistral AI / Mistral: Saba

Mistral: Saba✓ Catalog verified

mistralai/mistral-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

Input price
$0.20 /1M
Output price
$0.60 /1M
Context
33K
Modalities
text
Released
Feb 17, 2025
Tool calling
✓ Yes
Atlas signal
76/100
01

Overview

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

Access: available through the official Mistral AI API. Context window: 33K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifiermistralai/mistral-saba
ProviderMistral AI
Model typeText LLM
Context window33K catalog
Input modalitiestext
Output modalitiestext
ReleasedFeb 17, 2025
TokenizerMistral
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "temperature": 0.3
}
03

Pricing

Live pricing components for mistralai/mistral-saba as published in the catalog.

$0.20
Input /1M
$0.60
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$2e-7$0.20 / 1MPer input token
Completion tokens$6e-7$0.60 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.22Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-Hosting✓ SupportedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Mistral: Saba
MMLU Signal (Reasoning)
74signal
Coding Signal (HumanEval proxy)
83signal
Math Signal (GSM8K proxy)
74signal
Science Signal (GPQA proxy)
74signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Mistral: Saba through an OpenAI-compatible client.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="mistralai/mistral-saba",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Mistral: Saba cost?

$0.20 per 1M input tokens and $0.60 per 1M output tokens on the official Mistral AI API.

What is the context window of Mistral: Saba?

Mistral: Saba supports up to 33K tokens of context.

Does Mistral: Saba support tool / function calling?

Yes, Mistral: Saba supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Mistral: Saba?

Use the official Mistral AI API with the model id `mistralai/mistral-saba`. See the Quick start section above for code examples.