# AgentFeed Content Extraction API

> AgentFeed Content Extraction API is a paid API for AI agents from agentfeed.up.railway.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Extracts readable content from a webpage URL and returns it as markdown with metadata like word count and reading time

## Facts

- Endpoint: POST https://agentfeed.up.railway.app/api/v1/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/agentfeed-content-extraction-api-b4e31fe6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yjv2iSacICXFPgKMNKwkT

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 agentfeed-content-extraction-api-b4e31fe6 -d '<json body>'
```

Example prompt: Can you pull the readable content from https://example.com/some-article and give it to me as markdown so I can summarize it?

## When to prefer this

Use this endpoint when you need to extract clean, readable text content from a public webpage and want it returned as structured markdown with metadata. Prefer this over raw HTTP fetching when you need clean article-body extraction without boilerplate, navigation, or ads. Best suited for single-URL content extraction tasks where downstream summarization, analysis, or storage is needed.

## Known failure modes

- URL is unreachable or returns a non-200 status — extraction fails with an error response
- URL points to a non-HTML resource (PDF, image, binary) — markdown may be empty or malformed
- Payment not included or insufficient — 402 Payment Required response blocking access
- URL requires JavaScript rendering — static extraction may return incomplete content
- Paywalled or login-gated page — extracted content may be minimal or a login prompt
- Malformed URL input — validation error returned

## How this service works

Six payment-gated endpoints for AI agents: content extraction, price oracle, URL unfurling, web search, RSS parsing, and translation.

## Output

Returns a JSON object containing the original URL, page title, output format, the extracted page content as markdown, word count integer, and estimated reading time in minutes.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "The webpage URL to extract content from"
  },
  "format": {
   "type": "string",
   "description": "Output format for extracted content"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "title": {
   "type": "string"
  },
  "format": {
   "type": "string"
  },
  "markdown": {
   "type": "string"
  },
  "wordCount": {
   "type": "integer"
  },
  "readingTimeMinutes": {
   "type": "integer"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentfeed-content-extraction-api-b4e31fe6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentfeed.up.railway.app](https://www.zero.xyz/host/agentfeed.up.railway.app/llms.txt)