The Profanity API

The Profanity API is a developer tool designed to intelligently filter harmful, profane, or abusive content from user-submitted text. Unlike basic word filters, it uses a layered approach combining fast word list checks, custom logic, and a large language model (LLM) that only activates for ambiguous cases (reducing false positives, missed evasions, and unnecessary costs). This is ideal for apps, games, or chat platforms needing nuanced, context-aware moderation for live user interactions.