Mistral: Saba

mistralai · Released Feb 17, 2025
DFO score #658 / 749
6.0 leaderboard score
Speed
56 tok/s · best OpenRouter provider
Input Price #360 / 749
$0.200 per 1M tokens
Output Price #353 / 749
$0.600 per 1M tokens
Context #563 / 749
32,768 tokens

Analysis Summary

Mistral Saba is a text-and-file model with tool use and function calling, a 32K context window, and low listed prices. Its supplied reasoning benchmark results are limited, and no coding or instruction-following measurements are provided. The available evidence points to a budget-oriented option rather than a model for demanding reasoning or complex coding tasks.

Its pricing may suit basic, high-volume text or tool-connected workloads if quality is adequate. The relatively short context is a constraint for lengthy documents or codebases, and the benchmark results do not establish reliable performance for client-facing analysis. Test outputs for accuracy and instruction compliance before automating routine tasks.

A small pilot is reasonable where cost matters and requests are bounded. Keep a stronger model in the workflow for complex content, long inputs, and work requiring careful reasoning.

Assessed September 23, 2026

Editorial notes

Mistral Saba has tool and function calling at low listed prices, but its measured reasoning results are limited and its 32K context window narrows its fit for document-heavy work.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

Mistral Saba has tool and function calling at low listed prices, but its measured reasoning results are limited and its 32K context window narrows its fit for document-heavy work.

#658 of 749 overall Down 66 this week

Benchmarks

Intelligence Index 4.1 #355 of 454 · Artificial Analysis
Coding Index Not published yet Artificial Analysis
Agentic Index Not published yet Artificial Analysis
Creative Writing Not rated Arena rating
Instruction Following Not rated Arena rating
GPQA Diamond 42.4%
HLE 4.1%
MMLU Pro 61.1%
MATH 500 67.7%
AIME 13%
SciCode 24.1%

Artificial Analysis data refreshed Nov 16, 2026. Arena ratings from the Nov 9, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.

Artificial Analysis has not published coding or agentic results for Mistral: Saba yet. Until it does, the model sits below tested models on the Coding and AI Agents lists.

Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.

How Mistral: Saba compares

Mistral: Saba ranks #355 of 454 AI models we track for overall intelligence. Its 33K-token context window is larger than 25% of the models we list. At $0.20 per million input tokens it is cheaper than 52% of comparable models.

Position in the field
DFO score: ahead of 13% of models #649
Price: cheaper than 52% of models #360
Context: larger than 25% of models #563
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Mistral: Saba $0.20 in $0.60 out
Anthropic: Claude Fable 5.2 $8.00 in $40.00 out
Google: Gemini 4 Carbon $2.00 in $10.00 out
Google: Gemini 4 Argon $2.00 in $10.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.20 $0.000200
Output $0.60 $0.000600

What would Mistral: Saba cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

$1.15/mo Mistral: Saba $0.0004 per request
$63.36/mo Anthropic: Claude Fable 5.2 $0.02 per request
$15.84/mo Google: Gemini 4 Carbon · best value $0.0053 per request

Full calculator with 749 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save Mistral: Saba for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About 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..

Frequently asked questions about Mistral: Saba

How much does Mistral: Saba cost?

Mistral: Saba costs $0.20 per million input tokens and $0.60 per million output tokens.

What is the context window of Mistral: Saba?

Mistral: Saba has a context window of 32,768 tokens (33K).

What can Mistral: Saba do?

Mistral: Saba supports tool use and function calling.

Who created Mistral: Saba?

Mistral: Saba is developed by Mistral and was released on February 17, 2025.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.