# Paperclip Clean-Text Extraction

> Paperclip Clean-Text Extraction is a paid API for AI agents from 129-121-84-146.nip.io, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Fetches a URL and returns clean, AI-ready plain text (up to 4000 chars) stripped of HTML noise, for $0.01 USDC per call via x402.

## Facts

- Endpoint: POST https://129-121-84-146.nip.io/x402/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/paperclip-clean-text-extraction-d0e3e996
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__O8M8_Iu4tCWtkLPN4cYH

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 paperclip-clean-text-extraction-d0e3e996 -d '<json body>'
```

Example prompt: Can you pull the clean readable text from this article — https://example.com/some-article — so I can summarize it?

## When to prefer this

Choose this endpoint when you need fast, cheap ($0.01/call), AI-ready plain text from a public URL and don't need full DOM structure, structured data, or screenshots. Ideal for feeding article or documentation content directly to an LLM without preprocessing. Prefer alternatives if you need JavaScript rendering, structured data extraction, or full-page archiving.

## Known failure modes

- URL is unreachable or returns a non-200 status — ok field will be false and status reflects the HTTP error code
- Page is JavaScript-rendered and content cannot be extracted server-side — may return empty or minimal text
- URL points to a PDF or binary file — extraction may fail or return garbled text
- Payment not included or malformed — endpoint returns 402 Payment Required before processing
- Content exceeds 4000 characters — text is truncated to the limit

## How this service works

Pay-per-call URL to clean-text extraction for AI agents. $0.01 USDC on Base (eip155:8453) via x402.

## Output

A JSON object with fields: ok (boolean success flag), url (the fetched URL), title (page title), text (clean AI-ready plain text, max 4000 characters), status (HTTP status of the fetched page), and word_count (number of words in the extracted text).

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "type": "object",
  "required": [
   "ok",
   "url",
   "title",
   "text"
  ],
  "properties": {
   "ok": {
    "type": "boolean"
   },
   "url": {
    "type": "string"
   },
   "text": {
    "type": "string",
    "description": "Clean AI-ready text (max 4000 chars)"
   },
   "title": {
    "type": "string"
   },
   "status": {
    "type": "integer"
   },
   "word_count": {
    "type": "integer"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/paperclip-clean-text-extraction-d0e3e996/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 129-121-84-146.nip.io](https://www.zero.xyz/host/129-121-84-146.nip.io/llms.txt)