# AgentIndex x402 PDF Reader

> AgentIndex x402 PDF Reader is a paid API for AI agents from x402.agentindex.world, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-16).

Converts a PDF file (by URL or base64) into Markdown text with metadata, billed at $0.05 USDC per call via x402

## Facts

- Endpoint: POST https://x402.agentindex.world/pdf
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentindex-x402-pdf-reader-cd73af26
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bF17Ejsq6nIuSwftR2UuP

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 agentindex-x402-pdf-reader-cd73af26 -d '<json body>'
```

Example prompt: Can you extract the text from this PDF and give it to me as markdown? Here's the URL: https://example.com/report.pdf

## When to prefer this

Use this endpoint when you need to extract the full text content of a PDF — whether hosted at a public URL or available as a base64-encoded blob — and want the result as Markdown with document metadata (title, author, page count). Prefer this over generic web-read endpoints when the source is definitively a PDF. It is particularly well-suited for AI pipelines that need to ingest document content for downstream summarization, fact-checking, or analysis, and where micropayment via x402/USDC on Base is acceptable.

## Known failure modes

- PDF URL is not publicly accessible or returns a non-200 status — endpoint will fail to fetch the document
- Providing both url and pdf_base64 simultaneously — only one should be supplied
- Malformed or password-protected PDFs may result in empty or partial extraction
- Very large PDFs may time out or produce truncated results
- Non-PDF URLs passed as url will result in parsing errors

## How this service works

Process the files and content an agent gives you. Nothing else. A pay-per-call kit for AI agents in USDC on Base (x402/MPP): pdf, web-read, extract, summarize, and the free detect-language entry point - see GET /capabilities. Plus two tools outside the kit: translate and jobs.

## Output

A JSON object containing: 'markdown' (the full document text converted to Markdown), 'metadata' (title, author, date, page count), and 'token_count' (number of tokens in the extracted content).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public HTTPS URL of a PDF file. Provide this or pdf_base64, not both."
  },
  "pdf_base64": {
   "type": "string",
   "description": "Base64-encoded PDF file content. Provide this or url, not both."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "markdown": "Universal Declaration of Human Rights \nPreamble \nWhereas recognition of the inherent dignity and of the equal and inalienable \nrights of all members of the human family is the foundation of freedom, justice \nand peace in the world, ...",
  "metadata": {
   "date": "2001-09-10T01:04:58-17:00",
   "pages": 8,
   "title": null,
   "author": "lindner"
  },
  "token_count": 2330
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentindex-x402-pdf-reader-cd73af26/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.agentindex.world](https://www.zero.xyz/host/x402.agentindex.world/llms.txt)