# Vennatta Document Extraction

> Vennatta Document Extraction is a paid API for AI agents from vennatta-core.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-23).

Extracts structured text, summaries, or metadata from a document provided as raw text or a public URL

## Facts

- Endpoint: POST https://vennatta-core.onrender.com/api/v1/extract-document?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vennatta-document-extraction-0482100d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_a_yoKASJ8sIo9PMeqikjF

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 vennatta-document-extraction-0482100d -d '<json body>'
```

Example prompt: Can you extract a summary from this public document — https://example.com/annual-report-2024.pdf — and pull out the key metadata like title and author?

## When to prefer this

Use this endpoint when you need to extract or summarize content from a document given either a public URL or raw text, and want a choice between full text, summary, or metadata output modes. Prefer this over generic scraping tools when the input is a document (PDF, report, article) rather than an arbitrary webpage, and when structured extraction modes (full/summary/metadata) are needed rather than raw HTML scraping.

## Known failure modes

- Document URL is not publicly accessible or returns a non-200 HTTP status — extraction fails with an access error
- Document text exceeds the 2,000,000 character limit — request is rejected
- Neither document_url nor document_text is provided — request fails with a missing input error
- Document format is unsupported or unreadable — extraction returns empty or partial results
- Network timeout when fetching a remote URL — extraction fails with a fetch error

## How this service works

Extract structured text, summaries, or metadata from supplied document text or a public HTTPS document URL.

## Output

Returns structured output depending on the extraction_mode: 'full' returns the complete extracted text of the document, 'summary' returns a condensed narrative summary, and 'metadata' returns key document attributes such as title, author, date, and other identifiable properties. Input can be either a public HTTP(S) URL pointing to a document or raw document text up to 2 million characters.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "document_url": {
   "type": "string",
   "format": "uri",
   "description": "Public HTTPS document URL."
  },
  "document_text": {
   "type": "string",
   "maxLength": 2000000,
   "description": "Text to extract or summarize."
  },
  "extraction_mode": {
   "enum": [
    "full",
    "summary",
    "metadata"
   ],
   "type": "string",
   "default": "full",
   "description": "Requested extraction mode."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vennatta-document-extraction-0482100d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from vennatta-core.onrender.com](https://www.zero.xyz/host/vennatta-core.onrender.com/llms.txt)