document

PDF
JSON
Converter

Extract structured key-value pairs, tables, and form fields from PDF documents. Uses layout analysis and LLM extraction to produce clean JSON output, even from complex forms and invoices.

Max file size: 200 MB

Estimated: 2-15 sec per page

1 input formats

How It Works

Upload a PDF or provide a URL.

Layout analysis identifies form fields, tables, and key-value regions.

An LLM extracts values and maps them to a structured schema.

Tables are converted to row/column JSON arrays.

The complete structured output is returned as JSON.

Code Examples

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

result = client.convert(
    source="https://example.com/invoice.pdf",
    from_format="pdf",
    to_format="structured-data",
    options={
        "target_schema": {
            "vendor_name": "string",
            "invoice_date": "date",
            "total_amount": "number",
            "line_items": [{"description": "string", "amount": "number"}]
        }
    }
)

print(result.data)

Use Cases

Extract invoice line items and totals automatically

Parse insurance claims and medical forms

Digitize government and tax forms into databases

Convert product spec sheets into structured catalogs

Supported Input Formats

PDF

Quick Info

Categorydocument

Max File Size200 MB

Est. Time2-15 sec per page

Extractordocument-descriptor

Try This Conversion

Get started with the Mixpeek API and convert your first file in minutes.

Frequently Asked Questions

Related Converters

PDF

Text

PDF to Text

Extract clean, structured text from PDF documents including scanned pages, multi-column layouts, headers/footers, and tables. Combines traditional parsing with OCR and layout analysis for maximum accuracy.

PDF

Embeddings

PDF to Embeddings

Convert PDF documents into semantic vector embeddings for search, retrieval, and RAG applications. Pages are chunked intelligently by sections and paragraphs, then embedded using text or multimodal models.

PDF

Markdown

PDF to Markdown

Convert PDF documents to clean Markdown format, preserving headings, lists, tables, links, and emphasis. Ideal for migrating content into wikis, CMS platforms, and documentation systems.

HTML

JSON

HTML to Structured Data

Extract structured data from web pages using a combination of CSS/XPath selectors and LLM-based extraction. Captures product details, article metadata, contact information, and custom schemas from any website.

Ready to convert pdf to json?

Start using the Mixpeek PDF to Structured Data in minutes. Sign up for a free API key and follow the documentation to get started.

PDFJSONConverter