How much does Saba cost on Zeplik?

Input tokens cost 2.4 credits per million and output tokens 7.2 credits per million (1 credit = $0.10; the raw provider rates are $0.20 and $0.60 per million). New accounts start with free credits.

How long can a conversation with Saba be?

Saba has a 33K-token context window (32,768 tokens), which covers the conversation plus any documents you attach.

Does Saba support images and tools?

Saba is text-only and supports tool calling.

Saba

Open weightTools

Mistral · Released February 2025 · Knowledge cutoff September 2024

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.

It belongs to Mistral's catalog, which spans Medium and Large (capability), Small and Ministral (efficiency) and dedicated code and audio models, all with European data-residency roots.

Facts and pricing

Provider: Mistral
Context window: 33K tokens
Input price: 2.4 credits / 1M tokens ($0.20 raw)
Output price: 7.2 credits / 1M tokens ($0.60 raw)
Vision (image input): No
Tool calling: Yes
Extended reasoning: No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.

Try Saba now

Or open Zeplik with Saba already selected

What Saba is best for

Everyday chat and drafting on an open-weight model with transparent lineage
Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Example prompts

Prompts that suit a open weight model like Saba:

Draft a project update from these rough notes
Explain how HTTPS works to a curious teenager
Turn this list of features into a changelog entry
Brainstorm objections to this proposal and how to answer them

Mistral family

Model	Context	Input cr/M	Output cr/M	Released
Mistral Large 4	1.0M	8.4	25.2	October 2026
Mistral Medium 3.5	262K	18.0	90.0	April 2026
Mistral Medium 3.5 (batch)	262K	9.0	45.0	April 2026
Mistral Small 4	262K	1.8	7.2	March 2026
Devstral 2 2512	262K	4.8	24.0	December 2025
Ministral 3 14B 2512	262K	2.4	2.4	December 2025
Ministral 3 8B 2512	262K	1.8	1.8	December 2025
Ministral 3 3B 2512	131K	1.2	1.2	December 2025
Mistral Large 3 2512	262K	6.0	18.0	December 2025
Voxtral Small 24B 2507	33K	1.2	3.6	October 2025

All 21 Mistral models

Model comparisons

Frequently asked questions

What is Saba?: Saba is an AI model 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 efficient performance.
How much does Saba cost on Zeplik?: Input tokens cost 2.4 credits per million and output tokens 7.2 credits per million (1 credit = $0.10; the raw provider rates are $0.20 and $0.60 per million). New accounts start with free credits.
How long can a conversation with Saba be?: Saba has a 33K-token context window (32,768 tokens), which covers the conversation plus any documents you attach.
Does Saba support images and tools?: Saba is text-only and supports tool calling.

Related models

Mistral Large 4Open weight

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

1.0M ctx25.2 cr/M outOctober 2026

Mistral Medium 3.5Frontier

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

262K ctx90.0 cr/M outApril 2026

Mistral Medium 3.5 (batch)Open weight

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

262K ctx45.0 cr/M outApril 2026

Mistral Small 4Fast and light

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.

262K ctx7.2 cr/M outMarch 2026

Devstral 2 2512Coding

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.

262K ctx24.0 cr/M outDecember 2025

Ministral 3 14B 2512Fast and light

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.

262K ctx2.4 cr/M outDecember 2025