# ClawFetch Document Parser

> ClawFetch Document Parser is a paid API for AI agents from api.clawfetch.ai, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Converts office documents (docx, pptx, xlsx, pdf, odt, epub, csv, rtf, and more) to clean GitHub-Flavored Markdown, preserving headings, tables, and lists.

## Facts

- Endpoint: POST https://api.clawfetch.ai/parse
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/clawfetch-document-parser-acaa9f80
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WL5lEHT0z7Xv5WvDz_sqw

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 clawfetch-document-parser-acaa9f80 -d '<json body>'
```

Example prompt: Can you convert this Word document to clean markdown? Here's the URL: https://example.com/reports/q3-report.docx

## When to prefer this

Choose this endpoint when you need fast, deterministic, structure-preserving conversion of standard office document formats (docx, xlsx, pptx, pdf with selectable text, odt, epub, csv, rtf) to clean markdown — especially when table and heading structure must be retained. It is not suitable for scanned PDFs needing OCR, image extraction, or formats outside the supported list. Prefer this over general-purpose web scrapers when the input is a document file rather than an HTML page.

## Known failure modes

- Scanned/image-only PDFs return empty or minimal markdown because no OCR is performed
- Unsupported file format returns an error; use the format override parameter if auto-detection fails
- Base64 payload exceeding ~15MB will be rejected
- Inaccessible or redirected document URL returns a fetch error
- CSV files without a filename hint may fail format detection since they lack a file signature

## How this service works

Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epub, csv, doc, ppt) to clean GitHub-Flavored Markdown. Pass a document URL or base64-encoded bytes. Deterministic local Rust converter (Firecrawl anydoc) — fast, typed structure preserved (headings, tables, lists), no OCR for scanned/image-only PDFs.

## Output

Returns GitHub-Flavored Markdown text of the parsed document, with structural elements like headings (# H1, ## H2), tables (pipe syntax), and lists (- item) faithfully preserved. Does not perform OCR, so scanned or image-only PDFs will not yield meaningful text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "URL of the document to download and parse. Provide either url or base64."
  },
  "base64": {
   "type": "string",
   "description": "Base64-encoded document bytes (max ~15MB). Provide either url or base64."
  },
  "format": {
   "type": "string",
   "description": "Optional explicit format override. One of: doc, docx, odt, pdf, ppt, pptx, rtf, epub, xlsx, ods, odp, csv"
  },
  "filename": {
   "type": "string",
   "description": "Optional filename hint (e.g. \"report.docx\") used for format detection when bytes carry no signature (csv)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/clawfetch-document-parser-acaa9f80/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.clawfetch.ai](https://www.zero.xyz/host/api.clawfetch.ai/llms.txt)