# Agent Tools – PDF to Text (Upload)

> Agent Tools – PDF to Text (Upload) is a paid API for AI agents from agent-tools.jbarkules.workers.dev, paid per call via x402, $0.0035/call, status unknown (last checked 2026-10-30).

Converts an uploaded PDF file (sent as raw request body bytes) to extracted plain text or markdown, for files not accessible via a public URL.

## Facts

- Endpoint: POST https://agent-tools.jbarkules.workers.dev/v1/pdf/text/upload?utm_source=zero.xyz
- Price: $0.0035/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-tools-pdf-to-text-upload-43d3345e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uX_H854ZqEwk2CfTt4F-Y

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 agent-tools-pdf-to-text-upload-43d3345e -d '<json body>'
```

Example prompt: I have a PDF file on my computer that isn't publicly accessible — can you extract all the text from it as plain text so I can summarize it?

## When to prefer this

Choose this endpoint when the PDF file is local or otherwise not accessible via a public URL, making it impossible to pass a URL to a link-based extraction endpoint. Use this over the URL-based PDF endpoint whenever the document is private, generated on-the-fly, or stored locally. Prefer this over OCR endpoints when the source is a PDF (not a raw image) and text layer extraction is sufficient.

## Known failure modes

- File exceeds 20 MB limit — returns an error indicating the file is too large
- Non-PDF file type sent as body — may return a parsing error or empty text
- Corrupted or password-protected PDF — extraction may fail or return partial text
- No body provided in request — returns a validation error
- Unsupported format query parameter value — defaults or errors depending on implementation

## How this service works

PDF to text from uploaded bytes: send the raw PDF as the request body (max 20 MB). For files that are not on a public URL. ?format=text or markdown.

## Output

A JSON object containing the extracted text content, the number of pages, the output format used (text or markdown), and a character count. Example: {"text":"...","pages":3,"format":"text","characters":5120}.

## 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": {
     "type": "object",
     "required": [],
     "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": {
  "text": "Dummy PDF file",
  "pages": 1,
  "format": "text",
  "characters": 14
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-tools-pdf-to-text-upload-43d3345e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-tools.jbarkules.workers.dev](https://www.zero.xyz/host/agent-tools.jbarkules.workers.dev/llms.txt)