# docpull.ai PDF to Markdown Extractor

> docpull.ai PDF to Markdown Extractor is a paid API for AI agents from docpull.ai, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-15).

Extracts text content from a PDF document at a given URL and returns it as Markdown, reporting page count and character count.

## Facts

- Endpoint: GET https://docpull.ai/extract
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/docpull-ai-a57a7fec
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WvIhqRBPyyUgE-53fpqZa

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 docpull-ai-a57a7fec
```

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

Choose this endpoint when you need to programmatically extract text from a PDF accessible via URL and want the output in Markdown format. Ideal for AI pipelines that need to ingest PDF documents as structured text. At $0.001 per page it is cost-effective for moderate document volumes. Prefer this over general-purpose scraping tools when the source is specifically a PDF file.

## Known failure modes

- PDF URL is inaccessible or returns non-PDF content — likely returns success:false
- PDF is password-protected or encrypted — extraction may fail or return empty markdown
- Very large PDFs may time out or return partial results
- Invalid or malformed URL input causes request failure
- Network errors fetching the remote PDF result in an error response

## How this service works

PDF to Markdown extraction API. POST {url} to extract any PDF. $0.001 per page.

## Output

Returns a JSON object with a success boolean, the full extracted content as a Markdown string, the number of pages processed, and the total character count of 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": [
      "GET"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "required": [
      "success",
      "pageCount",
      "charCount",
      "markdown"
     ],
     "properties": {
      "success": {
       "type": "boolean"
      },
      "markdown": {
       "type": "string"
      },
      "charCount": {
       "type": "number"
      },
      "pageCount": {
       "type": "number"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/docpull-ai-a57a7fec/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from docpull.ai](https://www.zero.xyz/host/docpull.ai/llms.txt)