# Convert PDF to Markdown for LLMs and RAG

> Upload a PDF and get clean Markdown with headings, reading order and tables kept as Markdown tables, ready to chunk for an LLM or RAG index. This free tool runs Reducto Parse with the r-1 mini model. For more pages, the same call is one request to the Reducto API.

Canonical: https://reducto.ai/tools/pdf-to-markdown  
Last updated: 2026-11-15  
For: Developers building RAG, Analysts feeding reports to an LLM, Data and ML engineers

## 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-markdown` as multipart `file`, or JSON `{"url": "https://..."}`. The response has `result`, ready-to-save `output` (Markdown (.md), JSON), `pages_processed` and `next`.

```bash
curl -s https://reducto.ai/api/tools/pdf-to-markdown \
  -F file=@kestrel-10k-segment-table.pdf

# or, for a file that is already online:
curl -s https://reducto.ai/api/tools/pdf-to-markdown \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/kestrel-10k-segment-table.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-markdown&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, DOCX, PNG or JPG, or keep the sample.
2. Reducto Parse reads the layout, reading order and tables with the r-1 mini model.
3. Review the Markdown on the page. Tables stay as Markdown tables.
4. Download the .md file or copy it into your chunker or prompt.
5. For whole documents or batches, call the API with a free key using the snippet below.

## Reducto API call: `POST https://platform.reducto.ai/parse`

| Option | Value | Why |
| --- | --- | --- |
| `settings.model` | `"r-1-mini"` | Reducto's low-cost parse model, suited to high-volume Markdown conversion. |
| `formatting.table_output_format` | `"md"` | Tables come back as Markdown tables inside the Markdown text. |
| `settings.page_range` | `{ start: 1, end: 5 }` | The free tool reads at most 5 pages. |

### 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=@report.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-mini",
    "page_range": {
      "start": 1,
      "end": 5
    }
  },
  "formatting": {
    "table_output_format": "md"
  }
}'
```

### Python

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

client = Reducto()  # reads REDUCTO_API_KEY

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

Do this with the API: [Turn a Complex 10-K into Grounded RAG with r-1](https://reducto.ai/cookbooks/reducto-turn-a-complex-10-k-into-grounded-rag-with-r-1)

## What it handles

- **Tables stay tables**: Tables come out as Markdown or HTML tables, not lines of numbers.
- **Scanned pages too**: Pages without a text layer are read with OCR.
- **Two columns read in order**: Each column is read top to bottom.

## FAQ

### Is this PDF to Markdown converter free?

Yes. You can convert documents without an account. A small daily limit per IP applies. For longer documents or more runs, sign up for a free Reducto API key.

### Which model does it use?

Reducto Parse with settings.model set to r-1-mini. Reducto describes r-1 mini as its parse model for workloads where cost and speed matter most, priced at $1 per 1,000 pages on the API.

### Are tables kept?

Yes. Tables are returned as Markdown tables inside the Markdown output. Merged header cells are flattened into rows, so check wide tables before you index them.

### Does it work on scanned PDFs?

Yes. Parse reads the page image as well as any embedded text, so scanned pages convert too.

### Why Markdown for RAG?

Markdown keeps headings and tables as structure that chunkers and LLMs can use, while staying plain text. It is the format most RAG frameworks accept directly.

### Can I convert a long document?

Yes, up to 10 MB per file. For a long document you get a free preview of the first pages, then enter your email to convert the whole file on a free account (15,000 free credits). The API has no page cap; see the pricing page for plan details.

### Can an AI agent use this tool?

Yes. Agents can POST a file or a public URL to https://reducto.ai/api/tools/pdf-to-markdown without an API key and get the Markdown back as JSON.

### How do I get Markdown chunks instead of one file?

Use the Parse API, which returns content in chunks with block types and page numbers. The free tool joins the chunks into one Markdown file.

### Can I convert DOCX or images?

Yes. The tool accepts PDF, DOCX, PNG and JPG files.

Sample document (synthetic): https://reducto.ai/tools/samples/kestrel-10k-segment-table.pdf

## Related

- [All free tools](https://reducto.ai/tools)
- [Turn a complex 10-K into grounded RAG with r-1](https://reducto.ai/cookbooks/reducto-turn-a-complex-10-k-into-grounded-rag-with-r-1)
- [Best document parsers for RAG](https://reducto.ai/guides/best-document-parsers-rag)
- [PDF parser guide](https://reducto.ai/guides/pdf-parser)
- [r-1 mini announcement](https://reducto.ai/blog/reducto-r-1-mini-parse-model)
- [Reducto Parse](https://reducto.ai/parse)
