Mistral ships Shieldstral, a 3B guard model with runtime policy controls
The Apache 2.0 release evaluates text and images against plain-language policies, giving developers a compact moderation layer they can operate themselves.
By Ryan Merket · Published · Updated
Primary source: Mistral Blog
Why it matters
Mistral is extending its open-model strategy into the safety layer, where policy control, inference cost and data privacy increasingly shape which AI stacks enterprises adopt.
Mistral AI cofounders Arthur Mensch, Guillaume Lample and Timothee Lacroix released Shieldstral on August 4th, giving developers a 3-billion-parameter model that evaluates text and images against moderation policies written in plain English at inference time.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.