# Axiomworks Document-to-Markdown Converter

> Axiomworks Document-to-Markdown Converter is a paid API for AI agents from api.axiomworks.co.uk, paid per call via x402, $0.03/call, status down (last checked 2026-11-17).

Converts publicly accessible PDF, DOCX, HTML, or plain-text documents to clean Markdown or plain text, returning detected format, content, page count, and word count.

## Facts

- Endpoint: GET https://api.axiomworks.co.uk/convert?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: down
- Last checked: 2026-11-17
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/axiomworks-document-to-markdown-converter-edbf06c8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Nuf4eEjg8iDUxy474g1VU

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 axiomworks-document-to-markdown-converter-edbf06c8
```

Example prompt: Can you fetch the PDF at https://example.com/report.pdf and convert it to markdown so I can feed it into my RAG pipeline?

## When to prefer this

Use this endpoint when you need clean, structured text from a remote PDF, DOCX, HTML, or plain-text document and the source is publicly accessible via URL. It is ideal for RAG ingestion, summarization preprocessing, and LLM context preparation. Prefer this over general web-scraping endpoints when the source is a document file rather than a webpage, and over OCR services when the document has embedded selectable text.

## Known failure modes

- URL is not publicly accessible or returns 4xx/5xx — conversion fails with an error
- Document format is not supported (e.g. XLSX, PPT) — returns format error
- PDF is scanned/image-only with no embedded text — output will be empty or minimal
- Document is too large or takes too long to fetch — may timeout
- Malformed URL input — returns validation error

## How this service works

Convert a public document URL (PDF, DOCX, HTML, text) into clean markdown or plain text. PDF via unpdf/PDF.js; DOCX via mammoth; HTML via Readability+Turndown.

## Output

Returns a JSON object containing: detected_format (e.g. 'pdf', 'docx'), the converted content in the requested format (markdown or plain text), pages (page count), and word_count. The markdown output preserves headings and structure where possible.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "format": "uri",
       "description": "Public URL of a PDF, DOCX, HTML or text document"
      },
      "format": {
       "enum": [
        "markdown",
        "text"
       ],
       "type": "string",
       "description": "Output format (default markdown)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "text": {
       "type": "string"
      },
      "pages": {
       "type": "integer"
      },
      "title": {
       "type": [
        "string",
        "null"
       ]
      },
      "markdown": {
       "type": "string"
      },
      "final_url": {
       "type": "string"
      },
      "truncated": {
       "type": "boolean"
      },
      "word_count": {
       "type": "integer"
      },
      "detected_format": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://raw.githubusercontent.com/mozilla/pdf.js/master/web/compressed.tracemonkey-pldi-09.pdf",
  "pages": 14,
  "title": null,
  "omitted": [
   "full markdown/text body"
  ],
  "paid_call": "https://api.axiomworks.co.uk/convert?url=https%3A%2F%2Fraw.githubusercontent.com%2Fmozilla%2Fpdf.js%2Fmaster%2Fweb%2Fcompressed.tracemonkey-pldi-09.pdf",
  "truncated": true,
  "word_count": 13409,
  "text_preview": "Trace-based Just-in-Time Type Specialization for Dynamic\nLanguages\nAndreas Gal∗+, Brendan Eich∗, Mike Shaver∗, David Anderson∗, David Mandelin∗,\nMohammad R. Hag",
  "detected_format": "pdf",
  "full_report_via": "x402 (USDC on Base, HTTP 402 → PAYMENT-SIGNATURE retry)",
  "full_report_price": "$0.03",
  "preview_remaining": 7
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/axiomworks-document-to-markdown-converter-edbf06c8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.axiomworks.co.uk](https://www.zero.xyz/host/api.axiomworks.co.uk/llms.txt)
