LLM Reference

Mistral Saba

Released
2025-02-01
Last refreshed
2026-05-05
Status
Researched 45d ago
ProprietaryCommercial use with conditionsAgentsClassificationJSON / Tool use

Mistral Saba has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Use it for

  • Teams evaluating agents, classification, and json / tool use
  • Workloads that can use a 32k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Teams that need a tracked hosted API route today
Specifications
Released
2025-02-01
Context
32k
Parameters
24B
Architecture
Decoder Only
Knowledge cutoff
2024-09
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use with conditions
Training
pretrained
Created by

Enterprise AI solutions for trust and transparency.

Paris, France
Founded 2023
Website
Pricing

No tracked provider token pricing is available yet.

About

Mistral Saba is a 24B-parameter model by Mistral AI designed for the Middle East and South Asia. It delivers accurate Arabic, Farsi, Urdu, Hindi, and related languages at 32K context.

Mistral Saba is a proprietary model. The structured metadata tracks a 32k-token context window, function calling, tool use, and structured outputs. No headline benchmark score is tracked for Mistral Saba yet.

Top use-case fit: coding, agents, and build tasks

Agents

Included by capability and metadata signals in the decision map.

Classification

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

Function CallingTool UseStructured Outputs

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.