# apiacre.com Document Table Extractor

> apiacre.com Document Table Extractor is a paid API for AI agents from apiacre.com, paid per call via x402, $0.025/call, status unknown (last checked 2026-09-13).

Extracts structured rows from HTML, DOCX, or CSV documents and returns them as structured data

## Facts

- Endpoint: POST https://apiacre.com/v1/document/tables
- Price: $0.025/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-table-extractor-5659f814
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Zn0XhBhneMLAnxypV2Z3_

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-table-extractor-5659f814 -d '<json body>'
```

Example prompt: Can you extract all the structured table rows from this DOCX file I have — I need the data as clean, structured records so I can work with it programmatically.

## When to prefer this

Choose this endpoint when you need to extract tabular data from HTML, DOCX, or CSV documents and get back clean, structured rows. It is ideal for document automation pipelines where tables contain the key data of interest and you need row-level access without writing custom parsers. Prefer it over generic text extraction when the document's value is in its tabular structure.

## Known failure modes

- Unsupported file format returns an error — only HTML, DOCX, and CSV are accepted
- Malformed or corrupt documents may fail to parse and return a processing error
- Documents with no detectable table structure may return empty rows
- Very large documents may time out or exceed size limits
- Ambiguous merged cells or complex nested tables may produce incomplete or inaccurate row extraction

## How this service works

Extract structured table rows and columns from supplied HTML, DOCX, or CSV documents.

## Output

An array of structured rows parsed from the tables found in the input document, including column headers and cell values organized as structured records ready for downstream processing.

## 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": {
   "rows": [
    [
     "name",
     "score"
    ],
    [
     "Ada",
     "98"
    ]
   ],
   "warning": null,
   "metadata": {
    "bytes": 17,
    "sha256": "bae2475f86fa2343a9611424d3c2475e454b639c71da96a788602528e0937bea",
    "filename": "report.csv"
   },
   "rowCount": 2
  },
  "meta": {
   "cached": false,
   "sources": [],
   "warnings": [],
   "duration_ms": 42,
   "next_actions": []
  },
  "service": "document.tables",
  "version": "1",
  "request_id": "018f1f54-7f38-7ba2-8dc3-5f90272d9f1a"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/apiacre-com-document-table-extractor-5659f814/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)