Mistral Saba Models by MistralAI
1 model2025Up to 32k ctx
Capabilities
Function CallingAll models
Tool UseAll models
Structured OutputsAll models
Links
WebsiteAbout
Mistral AI's specialized family for Arabic and Middle Eastern languages.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view
Mistral SabaCurrent
Use when the workload needs 32k context, 24B parameters, and tool use.
2025-0232k context24B parameterstool use
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral Saba | Use when the workload needs 32k context, 24B parameters, and tool use. | 2025-02 | 32k context24B parameterstool use | Current |
Release Timeline
1 release group2025-02
1 current
Mistral Saba
Current32k context24B parameterstool use
Specifications(1 models)
| Model | Released | Context | Parameters | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|
| Mistral Saba | 2025-02 | 32k | 24B | Yes | Yes | Yes |
Frequently Asked Questions
- What is Mistral Saba used for?
- Mistral Saba is used for agent workflows and tool use and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does Mistral Saba compare to Ministral?
- Mistral Saba by MistralAI is strongest where you need agent workflows and tool use, while Ministral by MistralAI is the closest related family to check for vision and multimodal work. Mistral Saba has 1 listed variant and reaches up to 32k context, while Ministral reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
- Which Mistral Saba model should I use?
- If price is the main constraint, use the pricing table first because Mistral Saba does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Mistral Saba with 32k context and tool use, function calling, and structured outputs.
