# Convert PDF to JSON

> Upload a PDF and get JSON: every heading, paragraph and table as a block with its type, content, page number and bounding box, ready for an app, a database or an agent.

Canonical: https://reducto.ai/tools/pdf-to-json  
Last updated: 2026-11-15  
For: Developers, Data engineers, Agent builders

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

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

# or, for a file that is already online:
curl -s https://reducto.ai/api/tools/pdf-to-json \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/conv-pdf-to-json.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-json&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 splits it into typed blocks with their positions.
3. Preview the content on the page.
4. Download JSON.

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

| Option | Value | Why |
| --- | --- | --- |
| `settings.model` | `"r-1-mini"` | The fast Parse model: every block with its type, page and box. |

### 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-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("file.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("file.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

- **Every value has its location**: Each block carries its page and bounding box, so you can cite or highlight it.
- **Tables stay tables**: Tables keep their rows and columns.

## FAQ

### Does it work on scanned PDFs?

Yes. Scanned pages are read with OCR and return the same block structure.

### What does the JSON look like?

A list of blocks: { type, content, page, bbox: { left, top, width, height } }, with coordinates as fractions of the page.

### Can I extract specific fields instead?

Yes: for named fields like invoice number or total, use the Extract API with your own schema. See structured extraction with citations.

### 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-json.pdf

## Related

- [PDF to HTML](https://reducto.ai/tools/pdf-to-html)
- [Excel to JSON](https://reducto.ai/tools/xlsx-to-json)
- [PDF to text](https://reducto.ai/tools/pdf-to-text)
- [All free tools](https://reducto.ai/tools)
