Detectify Content Moderation API

Welcome to the Detectify Content Moderation API—a powerful, real-time service that scans multilingual text for 11 policy-sensitive categories. Built for simplicity and speed, Detectify helps you enforce community guidelines, detect policy violations, and maintain a safe environment for users worldwide.

Overview

The Detectify API allows you to moderate any user-submitted text with a single POST request. It returns a structured JSON response with per-category flags, confidence scores, human-readable reasons, and an overall risk summary—across multiple languages.

Features

• Multilingual Support: Analyze text in various languages for broader platform coverage.
• Multi-Category Detection: Spam, NSFW, Hate Speech, Harassment, Violence, Self-Harm, CSAM, Extremism, Misinformation, PII, and Obfuscation.
• Human-Readable Reasons: Each flagged category includes a concise rationale.
• Overall Risk Summary: flaggedAny, highestScore, topCategory, and overallScore for quick assessment.
• Zero Setup: Simple HTTP endpoint—no client libraries required.

API Endpoint

Content Moderation

• Method: POST
• Endpoint: /detect
• Description: Submit any text (up to 10,000 characters) in any supported language. Receive a JSON response detailing content violations and risk scoring.

Example Request & Response

Request

curl --request POST \
  --url https://detectify-ai-based-moderation-spam-nsfw-more.p.rapidapi.com/detect \
  --header "Content-Type: application/json" \
  --header "X-RapidAPI-Key: YOUR_RAPIDAPI_KEY" \
  --header "X-RapidAPI-Host: detectify-ai-based-moderation-spam-nsfw-more.p.rapidapi.com" \
  --data '{
    "text": "P1ng m3 0n wha55app 9So2E4SSo2"
  }'

Response

{
  "results": {
    "spam":        { "flagged": true,  "score": 0.95, "reason": "Contains elements resembling spam or phishing attempts." },
    "nsfw":        { "flagged": false, "score": 0.0,  "reason": "No NSFW content detected." },
    "hateSpeech":  { "flagged": false, "score": 0.0,  "reason": "No hate speech detected." },
    "harassment":  { "flagged": false, "score": 0.0,  "reason": "No harassment content detected." },
    "violence":    { "flagged": false, "score": 0.0,  "reason": "No violence detected." },
    "selfHarm":    { "flagged": false, "score": 0.0,  "reason": "No self-harm content detected." },
    "csam":        { "flagged": false, "score": 0.0,  "reason": "No CSAM detected." },
    "extremism":   { "flagged": false, "score": 0.0,  "reason": "No extremism detected." },
    "misinformation": { "flagged": false, "score": 0.0, "reason": "No misinformation detected." },
    "pii":         { "flagged": true,  "score": 0.85, "reason": "Contains potential personally identifiable information." },
    "obfuscation": { "flagged": true,  "score": 0.90, "reason": "Text includes obfuscated characters." }
  },
  "summary": {
    "flaggedAny":   true,
    "highestScore": 0.95,
    "topCategory":  "spam",
    "overallScore": 0.64
  }
}

Usage

1. Subscribe to Detectify on RapidAPI.
2. Include your RapidAPI key and host in request headers.
3. Send your text payload (in any supported language) to /detect.
4. Parse the JSON response to automate moderation workflows.

Keep your platform safe, compliant, and user-friendly—automate multilingual content moderation with one simple endpoint.