# apiacre.com Document Text & Metadata Extractor

> apiacre.com Document Text & Metadata Extractor is a paid API for AI agents from apiacre.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Extracts text content and metadata from common document file formats via a single POST call.

## Facts

- Endpoint: POST https://apiacre.com/v1/document/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/apiacre-com-document-text-metadata-extractor-d90cbf38
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eIML4Eyo9YZinYM7p40gh

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 apiacre-com-document-text-metadata-extractor-d90cbf38 -d '<json body>'
```

Example prompt: Can you pull all the text and metadata out of this PDF contract I just uploaded so I can search through it?

## When to prefer this

Choose this endpoint when you need to extract raw text and metadata from common document formats (PDF, DOCX, PPTX, etc.) as a preprocessing step before search, indexing, analysis, or storage. It is a good fit for agent pipelines that receive user-uploaded files and need programmatic access to document contents without building a parsing library. Prefer it over general-purpose OCR services when dealing with natively digital documents rather than scanned images.

## Known failure modes

- Unsupported file format returns an error indicating the format is not handled
- Corrupted or password-protected files may fail to parse and return an extraction error
- Very large documents may time out or return partial results
- Missing or malformed input body returns a 400 validation error
- Empty documents return empty text with only metadata fields populated

## How this service works

Extract clean text and metadata from supplied PDF, DOCX, HTML, Markdown, CSV, JSON, YAML, or plain-text documents.

## Output

Returns the full extracted plain text from the document along with metadata fields such as title, author, creation date, page count, and detected file format.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "filename": {
   "type": "string",
   "title": "Filename",
   "maxLength": 240
  },
  "content_base64": {
   "type": "string",
   "title": "Content Base64",
   "maxLength": 7100000
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "text": "Hello world",
   "words": 2,
   "metadata": {
    "bytes": 11,
    "sha256": "64ec88ca00b268e5ba1a35678a1b5316d212f4f366b2477232534a8aeca37f3c",
    "filename": "report.txt"
   },
   "characters": 11
  },
  "meta": {
   "cached": false,
   "sources": [],
   "warnings": [],
   "duration_ms": 42,
   "next_actions": [
    {
     "path": "/v1/document/redact",
     "price": "$0.01",
     "title": "PII and personal-data redaction",
     "method": "POST",
     "reason": "Remove common personal-data patterns from the extracted text before reuse.",
     "service": "document.redact",
     "use_output": "Use result.data.text as the redacted document and inspect the returned counts.",
     "sample_path": "/samples/document.redact",
     "handoff_path": "/catalog/document.redact",
     "checkout_path": "/try/document.redact",
     "input_template": {
      "text": "$result.data.text"
     },
     "maximum_atomic_usdc": "10000",
     "authorization_required": true,
     "executes_automatically": false,
     "handoff_payment_required": false
    }
   ]
  },
  "service": "document.extract",
  "version": "1",
  "request_id": "018f1f54-7f38-7ba2-8dc3-5f90272d9f1a"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/apiacre-com-document-text-metadata-extractor-d90cbf38/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from apiacre.com](https://www.zero.xyz/host/apiacre.com/llms.txt)