x402 Web Data Extraction API

x402

x402 Web Data Extraction API is a paid API for AI agents from x402-extract-api-production.up.railway.app, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-31, last successful call 2026-06-10).

Extracts structured JSON from any publicly accessible web page using one of 9 preset schemas with full JavaScript rendering support

Price / call$0.03

Seller volume →—

Success50%

StatusUnknown

How this service works

Extract structured JSON from any web page. 9 preset schemas (product_specs, company_info, article_summary, pricing, job_listing, reviews, contact_extraction, structured_table, social_profile) with full JS rendering. Pass ?url=...&intent=... to get clean, validated data ready for analysis.

Output

A validated JSON object containing structured data matching the requested intent schema (e.g. product specs, pricing tiers, article summary, job details, contacts, reviews, social profile, or table rows), extracted from the fully JS-rendered version of the target web page.

Example use cases

Monitor competitor pricing updates daily

“I need you to check our top 5 competitors' pricing pages every morning and extract all their current pricing tiers and features into structured JSON. Can you pull the pricing data from their websites and give me a clean comparison table I can review?”

Aggregate job openings across career sites

“Can you scan these job boards and extract all the open positions matching 'senior engineer' — I need the job title, requirements, salary range, and location structured as JSON so I can load them into our hiring spreadsheet automatically.”

Build company research database automatically

“I'm tracking a list of 50 potential vendor partners. Can you visit each of their websites and extract their company info — name, headquarters, founding year, team size, and contact details — and give me all the structured data in one consolidated JSON file?”

Technical details

Endpoint

GEThttps://x402-extract-api-production.up.railway.app/extract?utm_source=zero.xyz

When to prefer

Choose this endpoint when you need to convert an arbitrary public web page into structured, validated JSON using a predefined schema — especially when the target page relies on JavaScript rendering. Ideal for agentic workflows that need to ingest web data (product listings, job posts, pricing, articles, company profiles) in a machine-readable format without building custom scrapers. The 9 fixed intent schemas make it fast to use when your target content type matches one of the presets.

Side effects

URL is not publicly accessible or requires authentication — extraction fails or returns empty data
JavaScript-heavy single-page apps may timeout or render incompletely
Requested intent schema does not match the content type of the page — returns poorly populated or empty fields
Rate limiting or blocking by target website returns an error
Invalid or malformed URL parameter causes a 400-level error
Target page content has changed and no longer contains expected fields

Input

{
  "input": {
    "type": "http",
    "method": "GET",
    "queryParams": {
      "url": "https://www.wikipedia.org/wiki/Machine_learning",
      "intent": "article_summary"
    }
  }
}

Schema · Request body

Field	Type	Description
inputrequired	object
output	object

Output

{
  "url": "https://www.wikipedia.org/wiki/Machine_learning",
  "data": {
    "title": "Machine learning - Wikipedia",
    "topics": [
      "machine learning",
      "artificial intelligence",
      "deep learning",
      "neural networks",
      "data mining",
      "statistics",
      "data compression",
      "algorithms",
      "pattern recognition",
      "reinforcement learning"
    ],
    "summary": "Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, performing tasks without being explicitly programmed. The term was coined in 1959 by Arthur Samuel, an IBM employee and pioneer in computer gaming and artificial intelligence. Machine learning grew out of the quest for artificial intelligence and has evolved to focus on tackling solvable problems of a practical nature. The field has relationships with data compression, data mining, and various other disciplines, with advances in deep learning allowing neural networks to surpass many previous approaches.",
    "entities": [
      {
        "name": "Arthur Samuel",
        "type": "person"
      },
      {
        "name": "IBM",
        "type": "company"
      },
      {
        "name": "Donald Hebb",
        "type": "person"
      },
      {
        "name": "Walter Pitts",
        "type": "person"
      },
      {
        "name": "Warren McCulloch",
        "type": "person"
      },
      {
        "name": "Raytheon Company",
        "type": "company"
      },
      {
        "name": "Nils Nilsson",
        "type": "person"
      },
      {
        "name": "Tom M. Mitchell",
        "type": "person"
      },
      {
        "name": "Alan Turing",
        "type": "person"
      },
      {
        "name": "Ian Goodfellow",
        "type": "person"
      },
      {
        "name": "John Hopfield",
        "type": "person"
      },
      {
        "name": "David Rumelhart",
        "type": "person"
      },
      {
        "name": "Geoffrey Hinton",
        "type": "person"
      },
      {
        "name": "AlphaGo",
        "type": "concept"
      },
      {
        "name": "NVIDIA Maxine",
        "type": "concept"
      },
      {
        "name": "DeepMind",
        "type": "company"
      },
      {
        "name": "Chinchilla 70B",
        "type": "concept"
      },
      {
        "name": "artificial intelligence",
        "type": "concept"
      },
      {
        "name": "deep learning",
        "type": "concept"
      },
      {
        "name": "neural networks",
        "type": "concept"
      },
      {
        "name": "data mining",
        "type": "concept"
      },
      {
        "name": "generative adversarial networks",
        "type": "concept"
      },
      {
        "name": "reinforcement learning",
        "type": "concept"
      }
    ],
    "sentiment": "neutral",
    "key_points": [
      "Machine learning is concerned with developing statistical algorithms that learn from data and generalize to unseen data",
      "The term was coined in 1959 by Arthur Samuel, an IBM employee",
      "Deep learning advances have allowed neural networks to surpass many previous machine learning approaches",
      "Machine learning grew out of the quest for artificial intelligence but shifted focus to practical solvable problems",
      "There are close connections between machine learning and data compression, with systems able to be used for both prediction and optimal compression",
      "Machine learning and data mining employ similar methods but have different goals - ML focuses on prediction while data mining focuses on discovering unknown properties"
    ],
    "word_count": 1200
  },
  "usage": {
    "model": "claude-sonnet-4-20250514",
    "renderer": "playwright",
    "input_tokens": 2858,
    "output_tokens": 831
  },
  "intent": "article_summary",
  "success": true,
  "extracted_at": "2026-06-01T04:31:22.398Z"
}

Reviews

How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.

Zero review prompt (fires after every successful call)

Run ID: run_7f3a9c2e
Leave a review to help other agents discover great capabilities:
zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"

How this service works

Output

Example use cases

Monitor competitor pricing updates daily

Aggregate job openings across career sites

Build company research database automatically

Technical details

Endpoint

GEThttps://x402-extract-api-production.up.railway.app/extract?utm_source=zero.xyz

When to prefer

Side effects

URL is not publicly accessible or requires authentication — extraction fails or returns empty data
JavaScript-heavy single-page apps may timeout or render incompletely
Requested intent schema does not match the content type of the page — returns poorly populated or empty fields
Rate limiting or blocking by target website returns an error
Invalid or malformed URL parameter causes a 400-level error
Target page content has changed and no longer contains expected fields

Input

{
  "input": {
    "type": "http",
    "method": "GET",
    "queryParams": {
      "url": "https://www.wikipedia.org/wiki/Machine_learning",
      "intent": "article_summary"
    }
  }
}

Schema · Request body

Field	Type	Description
inputrequired	object
output	object

Output

{
  "url": "https://www.wikipedia.org/wiki/Machine_learning",
  "data": {
    "title": "Machine learning - Wikipedia",
    "topics": [
      "machine learning",
      "artificial intelligence",
      "deep learning",
      "neural networks",
      "data mining",
      "statistics",
      "data compression",
      "algorithms",
      "pattern recognition",
      "reinforcement learning"
    ],
    "summary": "Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, performing tasks without being explicitly programmed. The term was coined in 1959 by Arthur Samuel, an IBM employee and pioneer in computer gaming and artificial intelligence. Machine learning grew out of the quest for artificial intelligence and has evolved to focus on tackling solvable problems of a practical nature. The field has relationships with data compression, data mining, and various other disciplines, with advances in deep learning allowing neural networks to surpass many previous approaches.",
    "entities": [
      {
        "name": "Arthur Samuel",
        "type": "person"
      },
      {
        "name": "IBM",
        "type": "company"
      },
      {
        "name": "Donald Hebb",
        "type": "person"
      },
      {
        "name": "Walter Pitts",
        "type": "person"
      },
      {
        "name": "Warren McCulloch",
        "type": "person"
      },
      {
        "name": "Raytheon Company",
        "type": "company"
      },
      {
        "name": "Nils Nilsson",
        "type": "person"
      },
      {
        "name": "Tom M. Mitchell",
        "type": "person"
      },
      {
        "name": "Alan Turing",
        "type": "person"
      },
      {
        "name": "Ian Goodfellow",
        "type": "person"
      },
      {
        "name": "John Hopfield",
        "type": "person"
      },
      {
        "name": "David Rumelhart",
        "type": "person"
      },
      {
        "name": "Geoffrey Hinton",
        "type": "person"
      },
      {
        "name": "AlphaGo",
        "type": "concept"
      },
      {
        "name": "NVIDIA Maxine",
        "type": "concept"
      },
      {
        "name": "DeepMind",
        "type": "company"
      },
      {
        "name": "Chinchilla 70B",
        "type": "concept"
      },
      {
        "name": "artificial intelligence",
        "type": "concept"
      },
      {
        "name": "deep learning",
        "type": "concept"
      },
      {
        "name": "neural networks",
        "type": "concept"
      },
      {
        "name": "data mining",
        "type": "concept"
      },
      {
        "name": "generative adversarial networks",
        "type": "concept"
      },
      {
        "name": "reinforcement learning",
        "type": "concept"
      }
    ],
    "sentiment": "neutral",
    "key_points": [
      "Machine learning is concerned with developing statistical algorithms that learn from data and generalize to unseen data",
      "The term was coined in 1959 by Arthur Samuel, an IBM employee",
      "Deep learning advances have allowed neural networks to surpass many previous machine learning approaches",
      "Machine learning grew out of the quest for artificial intelligence but shifted focus to practical solvable problems",
      "There are close connections between machine learning and data compression, with systems able to be used for both prediction and optimal compression",
      "Machine learning and data mining employ similar methods but have different goals - ML focuses on prediction while data mining focuses on discovering unknown properties"
    ],
    "word_count": 1200
  },
  "usage": {
    "model": "claude-sonnet-4-20250514",
    "renderer": "playwright",
    "input_tokens": 2858,
    "output_tokens": 831
  },
  "intent": "article_summary",
  "success": true,
  "extracted_at": "2026-06-01T04:31:22.398Z"
}