# Make a scanned PDF searchable (OCR)

> Upload a scanned PDF or photo and get back a searchable PDF with an OCR text layer, so Ctrl+F, copy and document search work, plus the recognized text as Markdown. The tool runs Reducto Parse with r-1 and settings.embed_pdf_metadata turned on, free. For whole archives, the same call is one request to the Reducto API.

Canonical: https://reducto.ai/tools/ocr-scanned-pdf  
Last updated: 2026-11-15  
For: Operations and records teams, Paralegals, Accountants with scanned files, Developers building document search

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

```bash
curl -s https://reducto.ai/api/tools/ocr-scanned-pdf \
  -F file=@marrowfield-scanned-policy-memo.pdf

# or, for a file that is already online:
curl -s https://reducto.ai/api/tools/ocr-scanned-pdf \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/marrowfield-scanned-policy-memo.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=ocr-scanned-pdf&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 scanned PDF, PNG or JPG, or keep the sample.
2. Reducto Parse with r-1 reads every page image and recognizes the text, tables and layout.
3. With embed_pdf_metadata on, Reducto writes that text into a copy of your PDF as an invisible layer.
4. Check the Markdown preview on the page.
5. Download the searchable PDF and use Ctrl+F, select or copy as with any text PDF.

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

| Option | Value | Why |
| --- | --- | --- |
| `settings.model` | `"r-1"` | Reads the page image, so scans, rotated pages and photos work. |
| `settings.embed_pdf_metadata` | `true` | Returns pdf_url, a copy of the document with the recognized text embedded as a searchable layer. |
| `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=@scan.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",
    "embed_pdf_metadata": true,
    "page_range": {
      "start": 1,
      "end": 5
    }
  }
}'
```

### Python

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

client = Reducto()  # reads REDUCTO_API_KEY

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

## What it handles

- **Scans that look like text**: Image-only pages are read with OCR, so you can search and copy them.
- **Text and file**: You get the text in reading order, and the file stays the same.

## FAQ

### What does the searchable PDF look like?

The same as your scan. The recognized text sits in an invisible layer under the page image, so you can search, select and copy it.

### How do I check it worked?

Open the downloaded PDF and press Ctrl+F (Cmd+F on a Mac). Search for a word you can see on the page.

### Is the download link permanent?

No. The searchable PDF comes from a temporary link that expires. Download the file when the result appears.

### Does it work on photos and rotated scans?

Yes. Parse reads the page image, so phone photos and slightly rotated scans work. Upload images as PNG or JPG.

### Does it keep tables?

The Markdown preview keeps tables as tables. In the searchable PDF the text layer sits where the text appears on the page.

### What about handwriting?

Parse reads handwriting, but accuracy depends on legibility. Check the result before you rely on it.

### 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).

### Is there an API for this?

Yes. The snippet on this page is the exact Parse request. The response has the text in result.chunks and the searchable PDF link in pdf_url.

### Can I OCR many files at once?

Yes, with the API: send one Parse request per file. The free tool is for one file at a time.

Sample document (synthetic): https://reducto.ai/tools/samples/marrowfield-scanned-policy-memo.pdf

## Related

- [PDF to Markdown for LLMs](https://reducto.ai/tools/pdf-to-markdown)
- [Image to text](https://reducto.ai/tools/image-to-text)
- [Scanned PDF to text](https://reducto.ai/tools/scanned-pdf-to-text)
- [All OCR tools](https://reducto.ai/tools/ocr)
- [Fill a scanned PDF form](https://reducto.ai/cookbooks/fill-scanned-pdf-form)
- [r-1 announcement](https://reducto.ai/blog/parse-r-1-model)
- [Reducto Parse](https://reducto.ai/parse)
