v1

latestOpenAPI 3.1.0MIT2026-07-132429592.7 MB
Moderations

Classifies if text and/or image inputs are potentially harmful. Learn more in the [moderation guide](/docs/guides/moderation).

post/moderations

Request body

Example request

{
  "input": "I want to kill them."
}

Response

OK

idstring required

The unique identifier for the moderation request.

modelstring required

The model used to generate the moderation results.