Mistral: Saba

Mistral: Saba

mistralai · Released Feb 17, 2025
Intelligence #329 / 620
29.5 our score
AA Index #307 / 395
6.4 Artificial Analysis
Input Price #281 / 620
$0.200 per 1M tokens
Output Price #278 / 620
$0.600 per 1M tokens
Context #431 / 620
32,768 tokens

Analysis Summary

Mistral Saba is a smaller model from Mistral AI offering tool use and function calling at a low price of $0.20 input and $0.60 output per million tokens, though its 32K context window is modest by current standards.

Benchmark results place its reasoning and knowledge coverage well behind current mid-tier models, making it suitable mainly for simple, well-defined tasks such as short-form drafting or basic classification rather than complex analysis or coding.

Its low cost is attractive for lightweight automation, but businesses needing dependable reasoning should look elsewhere in Mistral's lineup.

Assessed July 25, 2026

Editorial notes

Mistral Saba is a compact, affordable model with tool use support but limited reasoning depth and a small 32K context window.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Mistral Saba is a compact, affordable model with tool use support but limited reasoning depth and a small 32K context window.

#329 of 620 overall

Benchmark scores

GPQA Diamond 42.4%
HLE 4.1%
MMLU Pro 61.1%
MATH 500 67.7%
AIME 13%
SciCode 24.1%

Magenta = intelligence Ā· Ink = technical/agentic Ā· Cyan = content & long-context Ā· Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

6.4 Intelligence Index

How Mistral: Saba compares

Mistral: Saba ranks #307 of 395 AI models we track for overall intelligence. Its 33K-token context window is larger than 30% of the models we list. At $0.20 per million input tokens it is cheaper than 55% of comparable models.

Position in the field
Intelligence: smarter than 47% of models #329
Price: cheaper than 55% of models #281
Context: larger than 30% of models #431
worst in fieldmedianbest in field
Price vs frontier peers Ā· $ per 1M tokens
Mistral: Saba $0.20 in $0.60 out
Anthropic: Claude Fable 5 $10.00 in $50.00 out
Anthropic: Claude Opus 4.8 $5.00 in $25.00 out
Claude Opus 5 $5.00 in $25.00 out

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

Context window vs peers Ā· tokens

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

Intelligence1.7Technical0Value7.5Content3.5
Performance profile

Strongest on value. The pulled-in technical corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

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

Full calculator with 620 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.