Identify potentially dangerous or harmful content including self-harm, violence, threats, sexual content, hate speech, and substance abuse references.
Endpoint
Request Body
Response
Categories Detected
Category
Description
self_harm
Self-injury or suicidal content
violence
Violent threats or graphic content
sexual_content
Age-inappropriate sexual material
hate_speech
Discrimination or targeted harassment
substance_abuse
Drug or alcohol abuse promotion
eating_disorder
Pro-ED content or unhealthy behaviors
exploitation
Child exploitation or CSAM