ProductModeration API
OpenAI Moderation API
A content moderation API provided by OpenAI, implemented as a text classification model independent of the main language model. It detects multiple categories of harmful content, including hate speech, self-harm, and illegal activities, and operates decoupled from the primary language model.
Timeline (last 90 days)
Aug 30
OpenAI's Moderation API and Meta's Llama Guard series are guardrails based on classification models, using specially trained small models to perform safety classification of content.
Unverified60%