All Models

Mistral Moderation 2 (March 2026), Mistral's API classifier that scores text or conversations across 11 categories, from hate and self-harm to PII, adds jailbreak detection and reads up to 128K tokens; it replaced the 2024 moderation model.

GPT-4o-based moderation model from September 2024 that flags harmful text and images across categories such as hate, violence and self-harm. Free to use and still the default snapshot behind omni-moderation-latest.