# Read URL as Clean Text for RAG

> Read URL as Clean Text for RAG is a paid API for AI agents from klane402.deanhiki.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-31).

Fetches a public web page and returns its title, description, plain text (up to 20k chars), and links in a clean format suitable for RAG pipelines.

## Facts

- Endpoint: GET https://klane402.deanhiki.workers.dev/api/read-url?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/read-url-as-clean-text-for-rag-991c9123
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wBPjFLxCr7rfwAixgVrxV

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 read-url-as-clean-text-for-rag-991c9123
```

Example prompt: Can you fetch the content of https://en.wikipedia.org/wiki/Retrieval-augmented_generation as clean text so I can use it in my RAG pipeline — I need the title, description, body text, and any links on the page.

## When to prefer this

Choose this endpoint when you need raw, clean text from a URL for downstream processing such as embedding, RAG ingestion, or analysis — and you do NOT need an AI-generated summary (use the sibling summary endpoint for that). Best for pipelines where you want the full page content and links without any interpretation, at low cost ($0.005/call).

## Known failure modes

- URL is not publicly accessible or behind authentication — returns error or empty content
- Page uses heavy JavaScript rendering — may return incomplete or no text
- URL is malformed or missing — returns validation error
- Page returns non-200 status (e.g. 404, 403) — propagated as error
- Text exceeds 20k chars — truncated to limit silently

## How this service works

Read a public web page as clean text for RAG: returns {title, description, text (<=20k chars), links}. Query: url. $0.005 per URL.

## Output

A JSON object containing the page's title (string), meta description (string), cleaned plain text body of up to 20,000 characters, and an array of links found on the page.

## 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"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "This domain is for use in illustrative examples...",
  "title": "Example Domain"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/read-url-as-clean-text-for-rag-991c9123/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from klane402.deanhiki.workers.dev](https://www.zero.xyz/host/klane402.deanhiki.workers.dev/llms.txt)