Moderation API

Check if text contains harmful content with multi-category compliance detection.

Endpoint

http
POST https://api.tk-novalink.com/v1/moderations

Request Example

bash
curl -X POST "https://api.tk-novalink.com/v1/moderations" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-moderation-latest",
    "input": "I want to kill them."
  }'

Detection Categories

The Moderation API can detect the following categories:

CategoryDescription
hateHateful content
hate/threateningHateful content with threats
harassmentHarassment
self-harmSelf-harm
sexualSexual content
violenceViolence