The Moderation API analyzes text inputs to detect violations of OpenAI's safety policies. It is designed for developers who need to filter user-generated content before it reaches their applications.
No migration guide is currently listed for this service.
Significant foreign legal exposure risk
Strong EU ownership and control
More dimensions coming soon
Verification date unknown. This assessment needs review.
A score is an assessment of recorded facts. Missing evidence and unresolved ownership can affect the result.
Statement 17/03/2026, confidence 90%.
R11 audit correction. Moderation API documentation describing categories like hate, hate/threatening, and illicit/violent, and input types supported.