Magistral Small

24B open-weight reasoning model (Apache 2.0) with transparent multilingual chain of thought: 70.7% on AIME 2024, 83.3% with majority voting.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

text, code

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.