The Profanity API

The Profanity API is a context-aware moderation tool for developers who need to filter user-generated content in chat apps, forums, games, and social platforms. It intelligently distinguishes between playful banter and actual abuse by combining the speed of Regex with the nuanced understanding of an LLM (Large Language Model), only using AI where necessary to ensure low latency and cost-effective moderation. Developers can integrate it within minutes using a single configurable endpoint, benefiting from transparent, explainable responses.