Convert any PDF into structured JSON data with a single API call. Digital PDFs, scanned documents, multi-page contracts — send any PDF and get clean, typed JSON back. No templates, no training, no OCR pipelines to manage.
Upload a PDF and define the fields you need. The API reads every page, understands the document structure, and returns structured JSON matching your schema.
curl -X POST \
https://api-parse.conversiontools.io/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@contract.pdf" \
-F 'schema={
"parties": [{
"name": "string",
"role": "string"
}],
"effective_date": "string",
"termination_date": "string",
"payment_terms": "string",
"total_value": "number",
"clauses": [{
"title": "string",
"summary": "string"
}]
}'{
"status": "completed",
"pages": 12,
"data": {
"parties": [
{
"name": "Acme Corp",
"role": "Service Provider"
},
{
"name": "Globex Inc",
"role": "Client"
}
],
"effective_date": "2026-01-15",
"termination_date": "2027-01-14",
"payment_terms": "Net 30",
"total_value": 84000.00,
"clauses": [
{
"title": "Confidentiality",
"summary": "Both parties agree..."
}
]
}
}Three steps to go from a raw PDF to structured JSON. Works with any PDF — digital, scanned, single-page, or multi-page.
Send any PDF to the API endpoint — invoices, contracts, reports, forms, or scanned documents. Multi-page PDFs are processed automatically.
The API reads all pages, applies OCR for scanned content, understands the layout and context, and extracts the fields defined in your schema.
Receive clean, typed JSON matching your schema. Ready to store in a database, feed into a pipeline, or display in your application.
Built for developers who need reliable PDF to JSON conversion without the complexity of traditional OCR and PDF parsing libraries.
Automatically detects and applies OCR to scanned PDFs and image-based pages. Works with both digital and paper-origin PDFs without any configuration.
One endpoint, one API call. Send a PDF, get JSON back. No SDKs required — works with curl, Python, Node.js, or any HTTP client.
Processes all pages of a PDF document. Extracts data that spans across pages — line items, tables, and sections that continue on subsequent pages.
Define exactly which fields to extract with JSON schemas. Support for strings, numbers, dates, arrays, and nested objects. One schema works across different PDF layouts.
PDF files are processed and deleted automatically. No document data is stored after extraction. EU-hosted infrastructure with encrypted connections.
Most single-page PDFs are processed in seconds. Synchronous and asynchronous modes available depending on your document size and page count.
The same API works across all your PDF processing needs. Define a schema once, parse data from thousands of PDF documents.
Extract structured data from any document format — PDFs, images, and scanned files.
Extract vendor, amounts, line items, dates, and tax details from invoices automatically.
Parse store names, totals, items, and payment methods from receipts and POS printouts.
Extract fields from applications, surveys, tax forms, and government documents.
Common questions about the PDF parsing API.
Yes. Parse uses OCR to extract text from scanned PDFs and image-based documents. Whether your PDF was created digitally or scanned from paper, the API reads the content and returns structured JSON matching your schema.
The API processes all pages of a PDF document automatically. You can parse multi-page contracts, reports, or statements and extract data that spans across pages — such as line items that continue on the next page or summary sections at the end.
Parse supports PDFs in any language. The AI model understands multilingual documents and can extract fields regardless of the language used. This includes Latin, Cyrillic, CJK characters, Arabic, and other scripts.
Parse uses large language models that understand document context and layout, not simple text pattern matching. Accuracy depends on document quality, but most structured PDFs like invoices, receipts, and forms achieve high extraction rates. Scanned documents with clear text also perform well.
Yes. The free plan includes 100 pages per month with full API access, custom schemas, and OCR support. No credit card required to start. For higher volumes, the Pro plan supports 2,500 pages per month with priority processing.
Get your API key and parse your first PDF in minutes. 100 pages per month free — no credit card required.