REST API for Developers

Developer tools

AI Detector API

Integrate AI content detection into your application with a simple REST API. Detect ChatGPT, Claude, and Gemini content programmatically with the engine that scored 95.2% accuracy and 3.1% false positives in our April 2026 benchmark (500 texts).

Try It Online

<2s

avg response time

95.2%

accuracy, April 2026 benchmark

3.1%

false positives, same benchmark

Get started in minutes

A single POST request is all you need

request.py
import requests

response = requests.post(
    "https://api.aidetectors.io/v1/detect",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "text": "Your text to analyze...",
        "options": {
            "sentence_scores": True
        }
    }
)

result = response.json()
print(f"AI Probability: {result['ai_probability']}%")
print(f"Flagged sentences: {len([s for s in result['sentences'] if s['ai_score'] > 50])}")
response.json
{
  "ai_probability": 94.7,
  "human_probability": 5.3,
  "confidence": "high",
  "sentences": [
    { "text": "Your text...", "ai_score": 97.2 },
    { "text": "More text...", "ai_score": 91.1 }
  ],
  "word_count": 156,
  "processing_time_ms": 1240
}

Try the detection engine

This interactive demo uses the same engine behind the API. Paste any text to see results.

Sentence-level reportThird-party verified
1

Paste or upload your text

Try a sample
Your text isn't saved
0 / 500words
2

Detection details

AI models detected
ChatGPTGPT-4oClaudeGeminiLlama 3MistralGrok
What we check
  • Perplexity
    How predictable each word is
  • Burstiness
    Variation in sentence length
  • N-gram patterns
    Repeated phrase signatures
  • Stylometric fingerprint
    Author-level writing traits
Privacy-first scanning
We don't store or train on your text. Your scan history and shared reports keep only the score and a short preview.

Built for production

Enterprise-grade AI detection infrastructure you can rely on

Fast Response Times

Average response time under 2 seconds for texts up to 5,000 words. Built for production workloads.

Benchmark-tested engine

Same detection engine that powers aidetectors.io: 95.2% accuracy and 3.1% false positives in our April 2026 benchmark (500 texts). Detects ChatGPT, GPT-4, Claude, Gemini, LLaMA, and more.

Simple REST API

Clean JSON request/response format. Get started with a single POST request from any language with an HTTP client.

Hosted on a global edge network

Served from a global CDN with rate limits designed for production use.

Detailed Results

Overall AI probability and sentence-level scores in every response.

Privacy by default

Your text is encrypted in transit and is not used to train our models.

Simple, transparent pricing

Start free, scale as you grow

Starter

Free

100 requests/month

  • Overall AI probability score
  • Up to 1,000 words per request
  • Community support
  • API key dashboard
Most Popular

Developer

$29/month

5,000 requests/month

  • Sentence-level scores
  • Up to 5,000 words per request
  • Email support

Enterprise

Custom

Unlimited requests

  • Everything in Developer
  • Higher rate limits
  • Priority support

Frequently Asked Questions

How do I get an API key?

Sign up for a free account at aidetectors.io and navigate to your Account dashboard. Your API key is generated instantly and you can start making requests immediately. The free tier includes 100 requests per month.

What AI models can the API detect?

The API detects content from all major AI models including ChatGPT (GPT-3.5, GPT-4, GPT-4o), Claude, Google Gemini, Meta LLaMA and Mistral — the five model families in our April 2026 benchmark — as well as other popular language models.

What languages does the API support?

The API is built and benchmarked for English text. It will return a score for other languages, but we do not publish accuracy figures for them, so treat non-English results as lower-confidence.

What is the rate limit?

Rate limits depend on your plan: Free tier allows 10 requests per minute, Developer allows 60 requests per minute, and Enterprise plans have custom rate limits. All plans include burst allowances for occasional spikes.

Do you store the text I send to the API?

Text submitted via the API is processed to produce the response and is not used to train our models. See our privacy policy for retention details.

Can I use the API for commercial products?

Yes. All paid plans include commercial usage rights. You can integrate AI detection into your SaaS product, CMS, hiring platform, or any other application.

Explore more AI detection tools

Start building with AI detection today

Get your free API key and make your first detection request in under 5 minutes.