Skip to main content
This is a Unreal API+ only request
POST /moderate-text Detects inappropriate language, mass mentions, and more. Uses AI

​
Headers

NameValue
apikey28-Character API Key

​
Body

NameTypeDescription
textstringThe text to moderate

​
Response

{
  "safe": false,
  "results": {
    "aiFlags": [
      { "category": "toxicity", "confidence": 0.96 },
      { "category": "obscene", "confidence": 0.93 },
      { "category": "insult", "confidence": 0.91 }
    ],
    "issuesFound": [
      "AI flagged \"toxicity\" (96%)",
      "AI flagged \"obscene\" (93%)",
      "AI flagged \"insult\" (91%)"
    ]
  }
}