LLM Reference

Mistral Saba Models by MistralAI

1 model2025Up to 32k ctx

Last refreshed 2026-05-05. Next refresh: weekly.

Details

ResearcherMistralAI
Models1
Released2025
Max context32k

Capabilities

JSON / Tool useAll models
Structured OutputsAll models

Links

Website

About

Mistral AI's specialized family for Arabic and Middle Eastern languages.

Decision facts

Best fit
JSON / Tool usestructured outputs
Capability starting point
Mistral Saba with 32k context and JSON / Tool use and structured outputs
Lowest tracked input
Not tracked
Closest related family
Ministral

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

1 in view

Use when the workload needs 32k context, 24B parameters, and JSON / Tool use.

2025-0232k context24B parametersJSON / Tool use

Release Timeline

1 release group
2025-02
1 current
Mistral Saba
32k context24B parametersJSON / Tool use
Current

Specifications(1 models)

Mistral Saba model specifications comparison
ModelReleasedContextParametersJSON / Tool useStructured Outputs
Mistral Saba2025-0232k24BYesYes