# Axiomworks Web Page Reader

> Axiomworks Web Page Reader is a paid API for AI agents from api.axiomworks.co.uk, paid per call via x402, $0.002/call, status unknown (last checked 2026-11-11).

Fetches a public web page URL and returns its clean content as Markdown plus structured metadata (title, author, date, language, word count, links) via Readability extraction.

## Facts

- Endpoint: GET https://api.axiomworks.co.uk/read?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/axiomworks-web-page-reader-d7e8fd87
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hUT8YgDZ-3LqAr2SXVwqT

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability axiomworks-web-page-reader-d7e8fd87
```

Example prompt: Can you fetch the article at https://www.bbc.com/news/technology-12345678 and give me the clean text as markdown, along with the title, author, date, and word count?

## When to prefer this

Choose this endpoint when you need clean, readable article text from a public web URL without dealing with raw HTML parsing yourself. It is ideal for RAG pipelines, summarization tasks, and research workflows where structured metadata (title, author, date, word count) matters alongside the text. Prefer it over raw HTTP fetch when you want Readability-quality boilerplate removal and a structured JSON response in ~1 second. It is better suited for single article/page extraction than for crawling entire websites or extracting custom structured data fields from arbitrary page layouts.

## Known failure modes

- URL is behind a paywall or login wall — returns empty or partial content
- URL points to a PDF or binary file rather than HTML — may fail or return raw text
- Page uses heavy client-side JavaScript rendering — Readability may miss dynamically loaded content
- Invalid or non-public URL (e.g. localhost, intranet) — returns an error
- Page returns non-200 HTTP status (404, 403, 500) — extraction fails with an error response
- Rate limiting or timeout on the target server — may return incomplete content

## How this service works

Use this when you need the clean text of a public web page as Markdown + metadata (title, author, date, language, word count, links). Better than raw fetch/HTML: Readability extraction, structured JSON, ~1s. Example in: {url:"https://example.com"} → {title, markdown, word_count, links}. $0.002 USDC.

## Output

A JSON object containing: the page title, the main article/body content rendered as clean Markdown (boilerplate, ads, and navigation stripped via Readability), detected author, publication date, language code, word count of the extracted text, and an array of hyperlinks found in the content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "format": "uri",
       "description": "Public http(s) URL to fetch"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "links": {
       "type": "array",
       "items": {
        "type": "object",
        "properties": {
         "url": {
          "type": "string"
         },
         "text": {
          "type": "string"
         },
         "internal": {
          "type": "boolean"
         }
        }
       }
      },
      "title": {
       "type": [
        "string",
        "null"
       ]
      },
      "author": {
       "type": [
        "string",
        "null"
       ]
      },
      "language": {
       "type": [
        "string",
        "null"
       ]
      },
      "markdown": {
       "type": "string"
      },
      "final_url": {
       "type": "string"
      },
      "published": {
       "type": [
        "string",
        "null"
       ]
      },
      "word_count": {
       "type": "integer"
      },
      "description": {
       "type": [
        "string",
        "null"
       ]
      },
      "links_count": {
       "type": "integer"
      },
      "canonical_url": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "title": "Example Domain",
  "omitted": [
   "full markdown",
   "full links array"
  ],
  "language": "en",
  "paid_call": "https://api.axiomworks.co.uk/read?url=https%3A%2F%2Fexample.com",
  "truncated": true,
  "word_count": 25,
  "links_count": 0,
  "links_sample": [],
  "full_report_via": "x402 (USDC on Base, HTTP 402 → PAYMENT-SIGNATURE retry)",
  "markdown_preview": "This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.",
  "full_report_price": "$0.002"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/axiomworks-web-page-reader-d7e8fd87/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.axiomworks.co.uk](https://www.zero.xyz/host/api.axiomworks.co.uk/llms.txt)
