AI Screenshot Analyzer 🎯

Capture screenshots of any URL and analyze them instantly with GPT-5-mini Vision. Zero storage - just the AI analysis results.

🚀 What it does

1. Captures a high-quality screenshot of any URL (websites, live streams, apps)
2. Analyzes the image with OpenAI's GPT-5-mini Vision (or GPT-4o)
3. Returns structured JSON analysis - no images stored, minimal costs

💡 Use Cases

Use Case	Description
🎮 Stream Ad Verification	Verify sponsor overlays on Twitch/Kick streams
🛡️ Content Monitoring	Check websites for policy violations
✅ Visual QA	Automated UI testing and regression detection
📊 Competitor Analysis	Analyze competitor landing pages
🔍 Accessibility Audits	Check visual accessibility compliance
📈 Social Media Monitoring	Track visual changes on social platforms

⚡ Why This Actor?

Traditional Approach	This Actor
Screenshot → Store → Download → AI	Screenshot → AI (direct)
Multiple API calls	Single API call
Storage costs	No storage
Slow	Fast (~30-60s)
~$0.02/run	~$0.008/run

📥 Input

Field	Type	Required	Default	Description
url	string	✅	-	URL to capture and analyze
openaiApiKey	string	✅	-	Your OpenAI API key
delay	integer	❌	8	Seconds to wait (use 10-15 for video)
prompt	string	❌	-	Custom analysis instructions
jsonOutput	boolean	❌	false	Request structured JSON response
model	string	❌	gpt-5-mini	OpenAI model (gpt-5-mini, gpt-4o-mini, gpt-4o)
viewportWidth	integer	❌	1920	Browser width (px)
viewportHeight	integer	❌	1080	Browser height (px)

📤 Output

{
  "url": "https://www.twitch.tv/shroud",
  "pageTitle": "shroud - Twitch",
  "capturedAt": "2026-01-07T12:00:00.000Z",
  "tokens": 1850,
  "analysis": {
    "detected": true,
    "sizeCompliant": true,
    "visibility": "CLEAR",
    "description": "Square sponsor overlay in bottom-right with brand logo and QR code"
  }
}

📋 Examples

Basic Website Analysis

{
  "url": "https://www.example.com",
  "openaiApiKey": "sk-...",
  "prompt": "Describe this website's layout and main content"
}

Stream Ad Verification

{
  "url": "https://www.twitch.tv/streamer_name",
  "openaiApiKey": "sk-...",
  "delay": 12,
  "jsonOutput": true,
  "prompt": "Look for sponsor/ad overlay. Return: {\"detected\": bool, \"sizeCompliant\": bool, \"visibility\": \"CLEAR\"/\"PARTIAL\"/\"BLOCKED\"/\"NONE\", \"description\": \"...\"}"
}

E-commerce Product Check

{
  "url": "https://shop.example.com/product/123",
  "openaiApiKey": "sk-...",
  "jsonOutput": true,
  "prompt": "Extract product info: {\"name\": \"\", \"price\": \"\", \"inStock\": bool, \"rating\": \"\"}"
}

💰 Pricing

Component	Cost
Apify compute (~60s)	~$0.005
GPT-5-mini tokens	~$0.002
Total per run	~$0.007-0.008

🔧 Optimizations

This actor is optimized for cost and speed:

• ✅ Playwright (lighter than Puppeteer)
• ✅ Single-process Chrome (40% less memory)
• ✅ JPEG compression (smaller images)
• ✅ Fast page load strategy
• ✅ Minimal dependencies
• ✅ 512MB memory allocation

📚 Tips

• Video content (Twitch, YouTube): Set delay to 10-15 seconds
• Static websites: 2-5 seconds delay is enough
• JSON output: Define your schema in the prompt for structured data
• Cost savings: Use GPT-5-mini (default) for best price/performance

🔗 Integration

Node.js / JavaScript

const response = await fetch(
  'https://api.apify.com/v2/acts/YOUR_USERNAME~ai-screenshot-analyzer/run-sync-get-dataset-items?token=YOUR_TOKEN',
  {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      url: 'https://example.com',
      openaiApiKey: 'sk-...',
      prompt: 'Describe this page',
    }),
  }
);
const [result] = await response.json();
console.log(result.analysis);

Python

import requests

response = requests.post(
    'https://api.apify.com/v2/acts/YOUR_USERNAME~ai-screenshot-analyzer/run-sync-get-dataset-items',
    params={'token': 'YOUR_TOKEN'},
    json={
        'url': 'https://example.com',
        'openaiApiKey': 'sk-...',
        'prompt': 'Describe this page',
    }
)
result = response.json()[0]
print(result['analysis'])

🤝 Support

• Issues: GitHub Issues
• Discord: Apify Discord

📄 License

MIT

---

Built with ❤️ for the Apify $1M Challenge