Skip to main content
AI Choice Engine
← All open-weight guides

Mistral · open weights

Shieldstral

A smaller policy-adaptive safety model designed to sit around a generation system rather than replace it.

Organisation
Mistral
Weights published
Licence
Apache 2.0
Size
3B classifier
Modalities
textimage
Comparison catalog
Not in the priced catalog yet

Practical fit

Useful for moderation, routing, and safety layers where a compact model can reduce latency and cost.

Deployment note

Evaluate false positives and policy fit on your own content; a classifier is not a complete safety programme.

Where to go next

Other open-weight releases