API Documentation

Quick Start

Get your API key from the pricing page. All API requests must include your key in the Authorization header. Here is a minimal example to detect AI content in a piece of text:

curl -X POST https://api.aidetector.ac/v1/detect   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{"content": "Your text here", "type": "text"}'

Response:

{
  "id": "det_01HN3X5ZX8KXZG4WKPF6M7KQ2",
  "type": "text",
  "ai_probability": 0.87,
  "verdict": "likely_ai",
  "confidence": "high",
  "model_attribution": {
    "gpt4o": 0.62,
    "claude": 0.18,
    "gemini": 0.07
  },
  "signals": ["low_perplexity", "uniform_burstiness", "formulaic_transitions"],
  "processing_time_ms": 380,
  "content_hash": "sha256:8f14e45f..."
}

Authentication

All requests require a Bearer token in the Authorization header:

Authorization: Bearer YOUR_API_KEY

API keys are scoped to your account and carry all permissions assigned to your plan. Keep keys secure — do not commit them to version control. Rotate compromised keys immediately from your dashboard.

Endpoints

POST /v1/detect

The primary detection endpoint. Supports text, image URL, audio URL, and video URL inputs. Returns AI probability, verdict, model attribution, and detection signals.

POST /v1/detect/batch

Batch endpoint for processing up to 100 items per request. Available on Professional and Enterprise plans. Each item in the batch is processed independently.

{
  "items": [
    {"id": "item_1", "content": "First text to check", "type": "text"},
    {"id": "item_2", "content": "Second text to check", "type": "text"}
  ]
}

GET /v1/usage

Returns current period API usage statistics: calls made, calls remaining, reset timestamp, and per-key breakdown for multi-key accounts.

SDKs

Python

pip install aidetector-python

from aidetector import AIDetector

client = AIDetector(api_key="YOUR_API_KEY")

result = client.detect(
    content="Text to analyze",
    content_type="text"
)

print(f"AI probability: {result.ai_probability}")
print(f"Verdict: {result.verdict}")
print(f"Model attribution: {result.model_attribution}")

Node.js

npm install @aidetector/node

import AIDetector from '@aidetector/node';

const client = new AIDetector({ apiKey: 'YOUR_API_KEY' });

const result = await client.detect({
  content: 'Text to analyze',
  type: 'text',
});

console.log(result.aiProbability);
console.log(result.verdict);

Rate Limits

Rate limits apply per API key:

Rate limit responses return HTTP 429 with a Retry-After header indicating seconds until your rate limit window resets. Implement exponential backoff starting at the value of Retry-After.

Webhooks

Configure webhooks from your dashboard to receive real-time notifications when content is flagged above your configured threshold. Webhook payloads are signed with HMAC-SHA256 using your webhook secret.

// Verify webhook signature (Node.js)
const crypto = require('crypto');
const sig = req.headers['x-aidetector-signature'];
const expected = crypto
  .createHmac('sha256', webhookSecret)
  .update(rawBody)
  .digest('hex');
const isValid = crypto.timingSafeEqual(
  Buffer.from(sig), Buffer.from(expected)
);

Error Codes