# agentsvc.io PDF Text Extraction

> agentsvc.io PDF Text Extraction is a paid API for AI agents from agentsvc.io, paid per call via x402, $0.0055/call, status unknown (last checked 2026-10-10).

Extracts full text content and metadata from a base64-encoded PDF file, returning per-page text and document metadata.

## Facts

- Endpoint: POST https://agentsvc.io/api/v1/proxy/pdf-extract?utm_source=zero.xyz
- Price: $0.0055/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentsvc-io-pdf-text-extraction-b659ce08
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MxWZFeizfSKDb-1Is40Zc

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 agentsvc-io-pdf-text-extraction-b659ce08 -d '<json body>'
```

Example prompt: Can you pull out all the text from this PDF I'm uploading — it's about 12 pages long — and give me the content page by page along with whatever metadata like title and author you can find?

## When to prefer this

Choose this endpoint when you need to programmatically extract text and metadata from a PDF without setting up a local PDF parsing library or managing infrastructure. Ideal for agent workflows that receive PDFs as inputs and need their textual content for downstream analysis, summarization, or storage. At $0.004 per call with no API key required, it suits pay-per-use pipelines processing occasional or variable PDF volumes.

## Known failure modes

- PDF exceeds ~10 MB base64 size limit — server rejects or truncates input
- Malformed or corrupted base64 string — parsing error returned
- Scanned image-only PDFs with no embedded text layer — empty or near-empty text output
- Encrypted or password-protected PDFs — extraction fails or returns no content
- max_pages set too low — only partial document text returned

## How this service works

86 APIs for AI agents: web scraping and crawling to Markdown, AI summaries, data extraction and cited answers, screenshots and PDF, PDF, OCR and document conversion, news, paper and developer search and more, paid per call with USDC on Base, Solana, Polygon or Arbitrum via x402. No account, no API key, free sample on every service.

## Output

Returns a JSON object containing the full concatenated text of the PDF, an array of per-page objects each with page number, text, and character count, document metadata (title, author, creator), total page count, extraction timestamp, and original file size in bytes.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "max_pages": {
   "type": "integer",
   "default": 50,
   "description": "Maximum number of pages to extract. Default: 50. Use to limit processing time for large PDFs."
  },
  "pdf_base64": {
   "type": "string",
   "description": "Base64-encoded PDF file content. Decode a PDF file to base64 and pass it here. Max ~10 MB (unencoded)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "text": "Quarterly Financial Report Q1 2026\n\nExecutive Summary\nTotal revenue increased by 23% year-over-year...",
   "pages": [
    {
     "page": 1,
     "text": "Quarterly Financial Report Q1 2026\n\nExecutive Summary",
     "char_count": 54
    },
    {
     "page": 2,
     "text": "Table of Contents\n1. Revenue Overview\n2. Cost Analysis",
     "char_count": 58
    }
   ],
   "metadata": {
    "title": "Q1 2026 Financial Report",
    "author": "Finance Department",
    "creator": "Adobe Acrobat"
   },
   "page_count": 12,
   "extracted_at": "2026-04-10T14:00:00.000Z",
   "file_size_bytes": 245760
  },
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentsvc-io-pdf-text-extraction-b659ce08/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentsvc.io](https://www.zero.xyz/host/agentsvc.io/llms.txt)