Mistral Releases Shieldstral: 3B Open-Weights Content Safety Model

sophiamyang · x · 2026-08-07

Mistral AI has introduced Shieldstral, a 3B parameter open-weights model designed for content safety.

A key feature of the model is its ability to be deployed on-device. Furthermore, developers can now define and customize the moderation policy simply by writing a single sentence, greatly simplifying the implementation of safety rules.

Original post →

More from Models

Models channel →