# GeekVault PDF Metadata Extractor

> GeekVault PDF Metadata Extractor is a paid API for AI agents from api.geekvault.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-29).

Extracts metadata fields (author, title, creation date, etc.) from a PDF file, returning them as key-value pairs.

## Facts

- Endpoint: POST https://api.geekvault.dev/docs-tools/v1/pdf-metadata?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/geekvault-pdf-metadata-extractor-96946e87
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EEAb_hm6FBiuR2Tek6oTi

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 geekvault-pdf-metadata-extractor-96946e87 -d '<json body>'
```

Example prompt: Can you pull out the metadata from this PDF file — things like the author, title, creation date, and any other document properties embedded in it?

## When to prefer this

Choose this endpoint when you need lightweight, fast extraction of PDF document metadata (author, title, dates, producer) without full text extraction or content parsing. Ideal for cataloging, auditing, or provenance checks where document properties rather than content are the goal. Prefer this over full PDF-to-text pipelines when you only need the header/info fields. Payment is per-call via USDC on Base with no API key setup required.

## Known failure modes

- Malformed or corrupted PDF returns an error — the file must be a valid PDF
- Empty or missing 'file' field in the request body results in a 400-level error
- Non-PDF binary data (e.g. a DOCX or image) may return empty fields or an error
- Very large PDF files may time out or be rejected depending on size limits
- Payment failure via x402 (insufficient USDC balance) blocks the request before processing

## How this service works

Network, docs, image, web, and dev utility tools paid per call via x402. No signup, no API keys, no subscriptions — just USDC on Base.

## Output

Returns a JSON object with a 'fields' property containing key-value pairs of all metadata embedded in the PDF, such as Title, Author, Subject, Creator, Producer, CreationDate, and ModDate, all as string values.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "file"
 ],
 "properties": {
  "file": {
   "type": "array"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "fields"
 ],
 "properties": {
  "fields": {
   "type": "object",
   "propertyNames": {
    "type": "string"
   },
   "additionalProperties": {
    "type": "string"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/geekvault-pdf-metadata-extractor-96946e87/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.geekvault.dev](https://www.zero.xyz/host/api.geekvault.dev/llms.txt)