Get started

If you already have an API key, run this command to extract content from a PDF:

curl -X POST https://api.nutrient.io/extraction/parse \
  -H "Authorization: Bearer your_api_key_goes_here" \
  -F "file=@document.pdf"

This sends a document to the Data Extraction API using the default settings (understand mode with spatial element output) and returns structured elements with bounding boxes and confidence scores.

Step-by-step setup

Follow these steps to create an account, get an API key, and run your first request.

1. Sign up

Go to the Nutrient dashboard(opens in a new tab) and create an account. If you already have a Nutrient DWS account, skip to step 2.

2. Get your API key

Open the API keys page(opens in a new tab) in the dashboard and copy a live API key. Live keys start with pdf_live_.

By default, a live key works with every DWS integration enabled for your account. Create a scoped live key when an integration requires restricted access.

3. Send your first request

Use the API key to extract content from a document. The examples below upload a local PDF and return structured spatial elements.

curl -X POST https://api.nutrient.io/extraction/parse \
  -H "Authorization: Bearer your_api_key_goes_here" \
  -F "file=@document.pdf" \
  -F 'instructions={"mode":"understand","output":{"format":"spatial"}}'

import requests

response = requests.post(
    "https://api.nutrient.io/extraction/parse",
    headers={"Authorization": "Bearer your_api_key_goes_here"},
    files={"file": open("document.pdf", "rb")},
    data={
        "instructions": '{"mode":"understand","output":{"format":"spatial"}}'
    },
)

print(response.json())

import fs from "node:fs";

const form = new FormData();
form.append("file", fs.createReadStream("document.pdf"));
form.append(
  "instructions",
  JSON.stringify({ mode: "understand", output: { format: "spatial" } }),
);

const response = await fetch("https://api.nutrient.io/extraction/parse", {
  method: "POST",
  headers: { Authorization: "Bearer your_api_key_goes_here" },
  body: form,
});

const result = await response.json();
console.log(result);

POST /extraction/parse HTTP/1.1
Host: api.nutrient.io
Authorization: Bearer your_api_key_goes_here
Content-Type: multipart/form-data; boundary=boundary

--boundary
Content-Disposition: form-data; name="file"; filename="document.pdf"
Content-Type: application/pdf

<binary PDF data>
--boundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json

{"mode":"understand","output":{"format":"spatial"}}
--boundary--

4. Review the response

The API returns a JSON response with extracted document elements:

{
  "status": 200,
  "requestId": "req_e5f6g7h8",
  "output": {
    "elements": [
      {
        "id": "a1b2c3d4-1111-4000-8000-000000000001",
        "type": "paragraph",
        "role": "Title",
        "text": "Quarterly Report",
        "confidence": 0.95,
        "readingOrder": 0,
        "bounds": { "x": 100, "y": 50, "width": 400, "height": 35 },
        "page": { "pageIndex": 0, "pageNumber": 1, "width": 1818, "height": 2422 }
      }
    ]
  },
  "metrics": {
    "processingTimeMs": 4200,
    "pagesProcessed": 1
  },
  "configuration": {
    "mode": "understand",
    "outputFormat": "spatial"
  }
}

Each element includes its type, text content, spatial coordinates (bounds), detection confidence, and page reference. Refer to extract document elements for the full element schema.

Next steps

• Extract document elements — Learn about all element types and spatial output options.
• Extract Markdown — Get whole-document Markdown instead of structured elements.
• Extract structured data — Map a document to your own JSON Schema with the extract endpoint.
• Classify documents — Score a document against your own labels and route it with the classify endpoint.
• Multilingual extraction — Process documents in other languages.
• API overview — Review request formats, authentication, and response structure.
• Interactive demos(opens in a new tab) — Browse open source browser demos showing grounded extraction across healthcare, legal, mortgage, and real estate documents.