Mistral's Shieldstral: a 3B open model that moderates by reading your policy
Mistral released Shieldstral 1.0, a 3-billion-parameter open-weights safety classifier (Apache 2.0) that judges text and images against a moderation policy written in plain language at inference time, returning calibrated probability scores instead of fixed categories. Mistral says it matches or beats open guard models up to seven times its size and runs on a single 16 GB GPU.
Why it mattersEvery app hosting user content needs a filter, and most either rent one from a big provider or bolt on rigid category lists. A small, free, policy-adaptive moderator lowers the cost of doing safety properly — and lets each platform define 'safe' in its own words.
Read in the app — free, in 9 languages
Related stories
Reflection will hand out a 501-billion-parameter model for free.2026-10-06Microsoft's new transcriber starts writing before you finish speaking.
2026-10-05An American lab is about to give away a China-class open model.
2026-10-05A video site now gives away the best-scoring open translation model.
2026-10-05Half the people on a short video call thought the AI was human.
2026-10-04