# Ai Screenshot Analyzer (`globose_jump/ai-screenshot-analyzer`) Actor

Transform any URL into actionable insights with AI-powered visual analysis. Capture, analyze, and extract structured data in a single API call. Zero storage overhead. Built for ad verification, compliance monitoring, and automated visual QA at scale.

- **URL**: https://apify.com/globose\_jump/ai-screenshot-analyzer.md
- **Developed by:** [Jordan](https://apify.com/globose_jump) (community)
- **Categories:** AI, Automation, Developer tools
- **Stats:** 4 total users, 3 monthly users, 0.0% runs succeeded, 1 bookmarks
- **User rating**: 3.00 out of 5 stars

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## 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

```json
{
  "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

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

#### Stream Ad Verification

```json
{
  "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

```json
{
  "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

```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

```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](https://github.com/your-repo/issues)
- Discord: [Apify Discord](https://discord.gg/apify)

### 📄 License

MIT

***

Built with ❤️ for the [Apify $1M Challenge](https://apify.com/challenge)

# Actor input Schema

## `url` (type: `string`):

URL to capture and analyze

## `openaiApiKey` (type: `string`):

Your OpenAI API key

## `delay` (type: `integer`):

Wait time before capture. Use 8-15s for video, 2-5s for static sites.

## `prompt` (type: `string`):

Instructions for the AI

## `jsonOutput` (type: `boolean`):

Request structured JSON response

## `viewportWidth` (type: `integer`):

Viewport width (px)

## `viewportHeight` (type: `integer`):

Viewport height (px)

## `model` (type: `string`):

OpenAI model to use

## Actor input object example

```json
{
  "url": "https://www.twitch.tv/shroud",
  "delay": 8,
  "prompt": "Analyze this screenshot and describe what you see.",
  "jsonOutput": false,
  "viewportWidth": 1920,
  "viewportHeight": 1080,
  "model": "gpt-5-mini"
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "url": "https://www.twitch.tv/shroud",
    "prompt": "Analyze this screenshot and describe what you see."
};

// Run the Actor and wait for it to finish
const run = await client.actor("globose_jump/ai-screenshot-analyzer").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "url": "https://www.twitch.tv/shroud",
    "prompt": "Analyze this screenshot and describe what you see.",
}

# Run the Actor and wait for it to finish
run = client.actor("globose_jump/ai-screenshot-analyzer").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "url": "https://www.twitch.tv/shroud",
  "prompt": "Analyze this screenshot and describe what you see."
}' |
apify call globose_jump/ai-screenshot-analyzer --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,globose_jump/ai-screenshot-analyzer"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/4KkDRgptXUzBehgiQ/builds/ul96AyJq8DF8W8YTz/openapi.json