API Endpoint

POST Content Moderation & Spam API

/api/v1/ai/spam-detection

Analyze text to detect spam, promotional abuse, toxicity, and PII, keeping your platform safe from malicious actors.

Request Body Parameters

Field	Type	Required	Description
`text`	string	Required	The raw text content to analyze (Max: 5,000 characters).
`content_type`	string	Optional	Context of where the text came from (e.g., "blog_comment", "email", "product_review"). Helps the AI understand the expected format.
`strictness`	string	Optional	Filter strictness: "low", "medium", or "high". Default is "medium".
`detect_toxicity`	boolean	Optional	Optional. Set to true to analyze the text for hate speech, harassment, and severe profanity.
`detect_pii`	boolean	Optional	Optional. Set to true to detect Personal Identifiable Information (emails, phone numbers, SSNs).
`return_sanitized`	boolean	Optional	Optional. Set to true to receive a redacted version of the text where malicious links, profanity, and PII are replaced with "[REMOVED]".
`model`	string	Optional	Optional AI model to use.

Example Request (Full Moderation)

In this example, we test a highly abusive comment and request all advanced moderation features, including sanitization.

JSON Request

{
  "text": "You guys are idiots! Call me at 555-019-2831 or visit my crypto scam site http://bit.ly/scam-link to win free money.",
  "content_type": "blog_comment",
  "strictness": "high",
  "detect_toxicity": true,
  "detect_pii": true,
  "return_sanitized": true
}

cURL

curl -X POST https://rsflowhub.com/api/v1/ai/spam-detection \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "You guys are idiots! Call me at 555-019-2831 or visit my crypto scam site http://bit.ly/scam-link to win free money.",
    "content_type": "blog_comment",
    "strictness": "high",
    "detect_toxicity": true,
    "detect_pii": true,
    "return_sanitized": true
  }'

Example Response

The API processes the text and returns a comprehensive moderation report, including the safely redacted text.

JSON Response

{
  "success": true,
  "data": {
    "result": {
      "is_spam": true,
      "spam_score": 0.98,
      "spam_category": "promotional",
      "reason": "Contains a suspicious shortlink and unsolicited promotional language.",
      "is_toxic": true,
      "toxicity_score": 0.85,
      "contains_pii": true,
      "pii_types": ["phone_number"],
      "sanitized_text": "You guys are [REMOVED]! Call me at [REMOVED] or visit my crypto scam site [REMOVED] to win free money."
    }
  },
  "meta": {
    "credits_used": 2,
    "credits_remaining": 991
  }
}

API Request Example

Use the cURL snippet below to test the endpoint.