# URL to Markdown Extractor (Readability)

> URL to Markdown Extractor (Readability) is a paid API for AI agents from opportunity-api-production.up.railway.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Fetches any public URL and returns clean agent-ready markdown with title, byline, excerpt, and full content up to 60k characters using Mozilla Readability.

## Facts

- Endpoint: GET https://opportunity-api-production.up.railway.app/api/extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/url-to-markdown-extractor-readability-4126b5cc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vJU8az-Klv5ZlKbQXS-gS

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 url-to-markdown-extractor-readability-4126b5cc
```

Example prompt: Can you pull the main article content from this URL and give it to me as clean markdown: https://www.wired.com/story/openai-gpt-5-launch/ — I need the title, author, and full body text.

## When to prefer this

Use this endpoint when you need to extract the main readable body of a public web article or page as clean markdown, especially when you want structured metadata (title, byline, excerpt) alongside the content. Prefer this over general-purpose scrapers when the target is an article, blog post, or news page and you want Readability-style noise removal (no nav, ads, or boilerplate).

## Known failure modes

- URL is not publicly accessible or behind a paywall — content not extractable
- URL points to a non-HTML resource (PDF, image, binary) — may fail or return empty markdown
- Page is JavaScript-rendered (SPA) and Readability cannot parse static HTML — returns empty or garbled content
- URL is malformed or unreachable — returns error response
- Page has no main readable content — excerpt and markdown may be empty or minimal

## How this service works

Turn any public URL into clean, agent-ready markdown (Readability). Title, byline, excerpt, markdown up to 60k chars. Param: url.

## Output

Returns a JSON object containing the article title, byline (author), excerpt (short summary), and the full article body converted to clean markdown text (up to 60,000 characters), all extracted from the target URL using Mozilla Readability.

## 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",
       "description": "public http(s) URL to extract"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/url-to-markdown-extractor-readability-4126b5cc/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from opportunity-api-production.up.railway.app](https://www.zero.xyz/host/opportunity-api-production.up.railway.app/llms.txt)