Enterprise DNAEnterprise DNA
Mistral logo

Models · Best cheap

Saba

by Mistral

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.

Our verdict

Not reviewed yet

We have not reviewed Saba yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

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.

Notes

Saba is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.200 per million tokens
Checked OpenRouter models API
Output price
$0.600 per million tokens
Checked OpenRouter models API
Latest version
mistralai/mistral-saba-2502
Checked OpenRouter models API
Tokens served on OpenRouter in a day
9.4M (for 10 Nov 2026)
Checked OpenRouter model activity (748 of 748 series)
Tool calls on OpenRouter in a day
169 (for 10 Nov 2026)
Checked OpenRouter model activity (748 of 748 series)
Artificial Analysis Intelligence Index
6.5
Checked Artificial Analysis via OpenRouter

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `mistralai/mistral-saba`.

  • openrouter · mistralai/mistral-saba · Docs

OpenRouter id: mistralai/mistral-saba

Price

What Saba costs, over time

Input price

$0.200 to $0.200

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.600 to $0.600

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Usage

How much Saba is used

Tokens served a day

889.4K to 9.4M

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Saba scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index6.5indexAs of 26 Oct 2026Artificial Analysis via OpenRouter

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

USAGE / OPENROUTER

How much Saba is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
30.1M ▲55.7%
Requests, last 7 days
38.6K
Tool calls, last 7 days
512
Price per million tokens
$0.2 in · $0.6 out
05M10M19 Sept: 889K tokens, 620 requests20 Sept: 673K tokens, 682 requests21 Sept: 812K tokens, 935 requests22 Sept: 2M tokens, 804 requests23 Sept: 1.3M tokens, 1.6K requests24 Sept: 783K tokens, 766 requests25 Sept: 1.3M tokens, 948 requests26 Sept: 327K tokens, 621 requests27 Sept: 581K tokens, 2.5K requests28 Sept: 681K tokens, 1.1K requests29 Sept: 1.5M tokens, 989 requests30 Sept: 846K tokens, 1.3K requests1 Oct: 4M tokens, 5.2K requests2 Oct: 5M tokens, 4.6K requests3 Oct: 4.7M tokens, 1.7K requests4 Oct: 2.1M tokens, 2K requests5 Oct: 3.2M tokens, 3.7K requests6 Oct: 1.2M tokens, 1.6K requests7 Oct: 1.4M tokens, 2K requests8 Oct: 1.3M tokens, 1.9K requests9 Oct: 785K tokens, 463 requests10 Oct: 523K tokens, 489 requests11 Oct: 358K tokens, 908 requests12 Oct: 607K tokens, 1.3K requests13 Oct: 510K tokens, 750 requests14 Oct: 675K tokens, 1.3K requests15 Oct: 308K tokens, 529 requests16 Oct: 962K tokens, 3.1K requests17 Oct: 542K tokens, 725 requests18 Oct: 1.6M tokens, 1.3K requests19 Oct: 526K tokens, 1K requests20 Oct: 331K tokens, 547 requests21 Oct: 951K tokens, 1.2K requests22 Oct: 1.2M tokens, 3.4K requests23 Oct: 919K tokens, 3.7K requests24 Oct: 1.7M tokens, 3.4K requests25 Oct: 1.4M tokens, 1.3K requests26 Oct: 852K tokens, 1.9K requests27 Oct: 670K tokens, 1.2K requests28 Oct: 674K tokens, 1K requests29 Oct: 1.6M tokens, 3.8K requests30 Oct: 1.8M tokens, 2.7K requests31 Oct: 728K tokens, 1.7K requests1 Nov: 2.1M tokens, 3.5K requests2 Nov: 6.9M tokens, 10.7K requests3 Nov: 5.6M tokens, 6.6K requests4 Nov: 4.1M tokens, 4.9K requests5 Nov: 6.6M tokens, 4.4K requests6 Nov: 5.9M tokens, 3.5K requests7 Nov: 1.6M tokens, 1.2K requests8 Nov: 881K tokens, 1.9K requests9 Nov: 1.6M tokens, 3.4K requests10 Nov: 9.4M tokens, 19.2K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Saba.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperMistral
Exact model identifiermistralai/mistral-saba
Inputtext, file
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
33K tokens
Knowledge cutoff
30 Sept 2024
Developer release date
Not established
First seen in the catalogue
17 Feb 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

mistralai/mistral-saba: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for first seen, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 6.5 (2026-10-26) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.