# Convert PDF to Word (.docx)

> Upload a PDF and download an editable Word (.docx) file: headings, paragraphs in reading order and real Word tables, with no text boxes.

Canonical: https://reducto.ai/tools/pdf-to-word  
Last updated: 2026-11-15  
For: Office teams, Editors, Anyone updating an old PDF

## Run it now (free, no API key, up to 5 pages)

Send a PDF, Word, PowerPoint, Excel or image (PNG, JPG, HEIC, TIFF, BMP, GIF) (max 10 MB, 5 pages) to `POST https://reducto.ai/api/tools/pdf-to-word` as multipart `file`, or JSON `{"url": "https://..."}`. The response has `result`, ready-to-save `output` (Word (.docx), Markdown (.md), JSON), `pages_processed` and `next`.

```bash
curl -s https://reducto.ai/api/tools/pdf-to-word \
  -F file=@conv-pdf-to-word.pdf

# or, for a file that is already online:
curl -s https://reducto.ai/api/tools/pdf-to-word \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/conv-pdf-to-word.pdf"}'
```

Higher volume needs a free API key (new accounts get 15,000 free credits). Agents can sign up over HTTP: https://reducto.ai/auth.md. Humans: https://studio.reducto.ai/?utm_source=free_tool&utm_medium=agent&utm_campaign=pdf-to-word&utm_content=api_response

Big file? Without a key the free run covers the first 5 pages and returns `partial: true` with a `signup_required` block. Your user signs up in under a minute (email, 6-digit code, name, terms: https://reducto.ai/auth.md); then repeat the same request with `Authorization: Bearer $REDUCTO_API_KEY` for the whole file on their 15,000 free credits. The same key works on the hosted MCP (https://mcp.reducto.ai/mcp) and the Reducto API.

## How to do it

1. Upload a PDF.
2. Reducto Parse reads the headings, paragraphs and tables.
3. The Reducto Office engine builds a .docx from them.
4. Download the Word file.

## How it works

Parses with r-1, then builds the .docx from the headings, paragraphs and tables with the Reducto Office engine.

| `settings.model` | `"r-1"` | Reads digital and scanned pages, including tables, in reading order. |
| `formatting.table_output_format` | `"html"` | Keeps table cells, so each table becomes a real Word table. |

### curl

```bash
# 1. Upload the file (or pass a public URL as "input" and skip this step)
curl -s https://platform.reducto.ai/upload \
  -H "Authorization: Bearer $REDUCTO_API_KEY" \
  -F file=@file.pdf
# => {"file_id": "reducto://..."}

# 2. Run parse
curl -s https://platform.reducto.ai/parse \
  -H "Authorization: Bearer $REDUCTO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": "reducto://FILE_ID",
  "settings": {
    "model": "r-1",
    "page_range": {
      "start": 1,
      "end": 5
    }
  },
  "formatting": {
    "table_output_format": "html"
  }
}'
```

### Python

```python
# pip install reductoai
from pathlib import Path
from reducto import Reducto

client = Reducto()  # reads REDUCTO_API_KEY

upload = client.upload(file=Path("file.pdf"))
result = client.parse.run(
    input=upload.file_id,
    settings={
        "model": "r-1",
        "page_range": {
            "start": 1,
            "end": 5,
        },
    },
    formatting={
        "table_output_format": "html",
    },
)
print(result)
```

### Node

```ts
// npm install reductoai
import fs from "fs";
import Reducto from "reductoai";

const client = new Reducto(); // reads REDUCTO_API_KEY

const upload = await client.upload({ file: fs.createReadStream("file.pdf") });
const result = await client.parse.run({
  input: upload.file_id,
  settings: {
    model: "r-1",
    page_range: {
      start: 1,
      end: 5,
    },
  },
  formatting: {
    table_output_format: "html",
  },
});
console.log(JSON.stringify(result, null, 2));
```

## What it handles

- **Real headings, lists and tables**: You get Word headings, bulleted and numbered lists and editable tables, not floating text boxes.
- **Scanned pages become editable text**: Scans are read with OCR first, so the Word file is text, not a picture.
- **Page furniture dropped**: Running headers, footers and page numbers are left out of the body text.

## FAQ

### Does it work on scanned PDFs?

Yes. See scanned PDF to Word: scanned pages are read with OCR first.

### Does the Word file look exactly like the PDF?

No: it keeps the structure (headings, paragraphs, tables) and uses Word's default styles, so it is easy to edit. Fonts, colours and page layout are not copied.

### Are images kept?

Not yet: figures are left out of the .docx. Text and tables are kept.

### Can I do this through the API?

Yes: call Parse with the settings shown below, then build the document from the blocks, or use the no-key endpoint for files.

### Is it free?

Yes. Short documents run free with no account, with a small daily limit per IP. For a longer file you get a free preview of the first pages, then enter your email to get the whole file on a free account (15,000 free credits).

Sample document (synthetic): https://reducto.ai/tools/samples/conv-pdf-to-word.pdf

## Related

- [Scanned PDF to Word](https://reducto.ai/tools/scanned-pdf-to-word)
- [PDF to HTML](https://reducto.ai/tools/pdf-to-html)
- [PDF to text](https://reducto.ai/tools/pdf-to-text)
- [All Word tools](https://reducto.ai/tools/word)
