# Kenward Readable Extraction API

> Kenward Readable Extraction API is a paid API for AI agents from pay.kenwardai.my.id, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-19).

Fetches a public URL server-side, strips boilerplate/ads/nav, and returns clean LLM-ready text (title, headings, paragraphs, lists) for RAG ingestion or LLM prompts; supports batch mode for up to 5 URLs per call.

## Facts

- Endpoint: GET https://pay.kenwardai.my.id/v1/readable?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/kenward-readable-extraction-api-f56c2d70
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tLdGMJOLVqOSh3yaZORIO

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 kenward-readable-extraction-api-f56c2d70
```

Example prompt: Fetch this article URL and give me clean, readable text with the title, headings, and paragraphs stripped of ads and nav — I want to feed it into my RAG pipeline: https://example.com/some-article

## When to prefer this

Choose this endpoint when you need server-side, pay-per-call web content extraction with no API key or account setup, billed in USDC via x402. It is ideal for agents that need clean LLM-ready text from arbitrary public URLs on demand, especially for RAG ingestion or LLM context augmentation. Prefer it over browser-based scrapers when you want stripped, structured text (title + headings + paragraphs) rather than raw HTML, and when you need lightweight batch processing of up to 5 URLs in a single call.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — endpoint returns an error reason_code for that URL
- Page is JavaScript-rendered and server-side fetch cannot see content — returns empty or minimal extraction
- URL is paywalled or behind a login — extraction returns only the visible fragment
- Batch exceeds 5 URLs — request may be rejected or truncated
- Malformed or non-HTTP(S) URL — validation error returned
- Network timeout fetching the target URL — error reason_code returned

## How this service works

URL to clean LLM-ready text (readable extraction): fetched server-side, boilerplate/ads/nav stripped, returned as title + headings/paragraphs/lists plus the plain text - for RAG ingestion, LLM prompts and indexing. Batch mode: repeat urls= up to 5 times in one call.

## Output

A structured response per URL containing the extracted page title, headings, paragraphs, lists, and a single plain-text concatenation of all readable content — boilerplate, ads, and navigation removed. In batch mode, each URL gets its own result with an availability status and reason code.

## 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",
     "properties": {
      "url": {
       "type": "string",
       "description": "public http(s) page to convert into clean text"
      },
      "urls": {
       "type": "string",
       "description": "batch mode: repeat urls= up to 5 times in one call; each URL is answered separately with its own available/reason_code"
      }
     },
     "additionalProperties": false
    }
   },
   "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/kenward-readable-extraction-api-f56c2d70/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pay.kenwardai.my.id](https://www.zero.xyz/host/pay.kenwardai.my.id/llms.txt)