# PDF Text Extraction API (pay-per-call)

> PDF Text Extraction API (pay-per-call) is a paid API for AI agents from 194-28-85-99.sslip.io, paid per call via x402, $0.01/call, status down (last checked 2026-11-17).

Fetches a PDF from a public URL and returns its full text content, page by page, with title and pagination metadata.

## Facts

- Endpoint: GET https://194-28-85-99.sslip.io/api/v1/pdf?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: down
- Last checked: 2026-11-17
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pdf-text-extraction-api-pay-per-call-6a20a829
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RpZnF67etlIBO8wbQr3Z7

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 pdf-text-extraction-api-pay-per-call-6a20a829
```

Example prompt: Can you read the PDF at https://bitcoin.org/bitcoin.pdf and extract all 9 pages of text so I can review the full content?

## When to prefer this

Use this endpoint when you need to extract plain text from a publicly accessible PDF, especially for research papers, whitepapers, legal documents, or reports that your agent needs to read and process. Prefer this over general web-scraping endpoints when the target is specifically a PDF file. It handles page-by-page formatting, title extraction, and pagination metadata natively.

## Known failure modes

- Invalid or inaccessible PDF URL returns an error (non-200 HTTP from origin, auth-gated PDF)
- PDF exceeds max_pages or max_chars — response will be truncated (truncated: true)
- Corrupted or non-standard PDF format may fail to parse
- Payment not provided or invalid signature returns HTTP 402 with payment instructions
- Signature older than max_tx_age_seconds is rejected
- Very large PDFs with 300+ pages may hit limits

## How this service works

Crypto market data and web tools for autonomous agents: read web pages, PDFs and YouTube transcripts, check domains and tokens. Every `/api/v1/*` call is paid per call: **$0.003** for simple reads, **$0.005-$0.01** for aggregates, **$0.02-$0.03** for token risk checks and reports (USDC or USDT). Each route's price is in `x-payment-info`.

**x402 agents:** pay automatically. The 402 response carries a standard `PAYMENT-REQUIRED` header (x402 v2, USDC on Base or Solana, USDT on Solana); retry with `PAYMENT-SIGNATURE`.

**Manual (legacy) flow:** call the endpoint, read the HTTP 402 JSON (`pay_to`, `asset`, `price`), send the USDT transfer, then repeat the call with header `X-Payment-Tx: <signature>`. One signature pays for one call; signatures older than the `max_tx_age_seconds` value are rejected.

Machine-readable spec: `/openapi.json`. LLM summary: `/llms.txt`. MCP server: `POST /mcp`.

## Output

Returns a JSON object with the extracted text (formatted page by page), the document title, total pages in the PDF, number of pages actually read, and a truncated flag indicating whether the output was cut short due to max_chars or max_pages limits.

## 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": "http(s) URL of a PDF"
      },
      "max_chars": {
       "type": "integer",
       "maximum": 200000,
       "minimum": 500
      },
      "max_pages": {
       "type": "integer",
       "maximum": 300,
       "minimum": 1
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://bitcoin.org/bitcoin.pdf",
  "text": "--- page 1 ---\nBitcoin: A Peer-to-Peer Electronic Cash System...",
  "title": "Bitcoin: A Peer-to-Peer Electronic Cash System",
  "truncated": false,
  "pages_read": 9,
  "pages_total": 9
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pdf-text-extraction-api-pay-per-call-6a20a829/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 194-28-85-99.sslip.io](https://www.zero.xyz/host/194-28-85-99.sslip.io/llms.txt)
