API Endpoint

POST Comment Moderation API

/api/v1/ai/comment-moderate

Moderate social media comments to detect spam, abuse, harassment, toxicity, sexual content, or promotional spam without over-classifying customer criticism.

Request Body Parameters

Field	Type	Required	Description
`comment`	string	Required	The social media comment text (Max: 5,000 characters).
`language`	string	Optional	Optional comment language identifier.
`platform`	string	Optional	Optional social media platform name.
`context`	string	Optional	Optional contextual details to aid analysis.
`model`	string	Optional	Optional AI model to use.

Example Request (Spam Detect)

This example demonstrates how to check a suspicious promotional link comment on YouTube.

JSON Request

{
  "comment": "Buy cheap followers now at http://fakefollowers.com !!! FAST DELIVERY!",
  "platform": "YouTube"
}

cURL

curl -X POST https://rsflowhub.com/api/v1/ai/comment-moderate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "comment": "Buy cheap followers now at http://fakefollowers.com !!! FAST DELIVERY!",
    "platform": "YouTube"
  }'

Example Response

The response highlights safety assessment, categories flagged, severity, and suggested moderation action.

JSON Response

{
  "success": true,
  "data": {
    "result": {
      "is_safe": false,
      "categories": [
        "spam",
        "promotional"
      ],
      "severity": "high",
      "recommended_action": "flag",
      "reason": "Comment contains suspicious promotional URLs attempting to sell fake engagement services.",
      "confidence": 0.99
    }
  },
  "meta": {
    "credits_used": 1,
    "credits_remaining": 996
  }
}

API Request Example

Use the cURL snippet below to test the endpoint.