Turn any document into
structured JSON
The simplest way to get clean JSON from invoices, receipts, contracts, PDFs and images.
No regex. No training data. Ready to use instantly.
From document to structured data in seconds
Define your template
Set the fields you want once. It applies to every document of that type.
Send your documents
Upload files or use the API to process at scale.
Get clean JSON
Structured data, ready to use in your app.
|Template Wizard
Create a template in seconds,
not hours
Parselyze extracts exactly the fields you define, no more, no less. Define your schema once from a sample document, then reuse it on every similar document you process.
- Upload any document (PDF, image, or scan)
- Fields detected automatically from your document
- Review, confirm and save your template
invoice.pdf
Invoice • 6 fields detected
Template Flexibility
Your JSON structure, your rules
From invoices to medical records: any document type, any JSON structure, defined by you field by field.
Accounting & Finance
Automate invoice processing, reconciliation and financial reporting by extracting structured data from any financial document.
String · Number · Date · Boolean · Object · Array, all supported
Features
Accurate extraction, built for production
High-fidelity field detection, flexible schemas, dev-first API. No fragile scripts, no maintenance.
Extraction That Fits Your Data Model
Define exactly what to extract: strings, numbers, dates, arrays, nested objects. Your JSON comes out the way your app expects it, field by field.
Learn moreBuilt for Production Scale
Batch multiple documents per call, process ZIP archives, and submit async jobs. Get notified via webhook when results are ready. No polling needed.
Learn moreFull Job Visibility
Track every extraction job in real time. Inspect outputs, spot failures, and reprocess in one click. Full history at your fingertips.
Learn moreReady-Made Templates
Start immediately with templates for invoices, receipts, IDs, contracts and more. Use them as-is or customize every field in minutes.
Learn moreTest Before You Go Live
Run your template against real documents before deploying. See exactly what gets extracted, field by field, and iterate until it's perfect.
Learn morePrivacy by Design
Enterprise-grade security. Your documents are processed, not stored. Never used for training or any other purpose.
One API call.
Structured data back.
A clean REST API. Send a document, get structured JSON back in the shape your app expects.
Template-based extraction
Create your template once in the UI, call it from the API anytime
Multiple formats
Supports PDF, JPG, PNG, and ZIP, all processed the same way
Predictable output
JSON that matches your schema exactly, every time
// npm install parselyze
import { Parselyze } from "parselyze";
const parselyze = new Parselyze("plz_xxxxxxxx...xxxxxx");
(async function () {
console.log("Start parsing document...");
const result = await parselyze.documents.parse({
files: ["./invoice.pdf"],
templateId: "",
});
console.log("Parsing complete:", result);
})();
Plug Parselyze into your existing infrastructure.
Whether you rely on REST API calls, event-driven webhooks, or no-code automation tools, Parselyze fits seamlessly into the workflows you already run.
Parselyzecurl -X POST https://api.parselyze.com/v1/documents/parse/async \
-H "x-api-key: plz_xxxxxxxx...xxxxxx" \
-F "file=@invoice.pdf" \
-F "template_id=tpl_invoice_default"Call the REST API directly
One endpoint, a document, an API key. Get structured JSON out. Works from any language or framework.
Use Parselyze in automation workflows
Parselyze is natively available on Zapier. For Make, n8n, and Power Automate: just add an HTTP step, point it at the API, and pipe the JSON wherever you need it.
{
"eventType": "document.completed",
"jobId": "job_abc123",
"status": "completed",
"result": {
"invoice": {
"invoice_number": "INV-2026-0042",
"total_amount": 1490.00,
"due_date": "2026-04-10"
}
}
}React to events with webhooks
Subscribe to document events and trigger actions in your backend as soon as parsing completes.
Automate document parsing with Zapier
Connect Parselyze to 6,000+ apps: Google Drive, Gmail, Slack, Airtable and more.
Pricing
Start free. Scale as you grow.
Only pay for what you process. No upfront commitment.
Perfect for getting started
- 50 pages / month
- Template testing
- Process one document at a time
- Email support
Starter
Ideal for small teams
- 400 pages / month
- Quota-free testing
- Email support
- Process multiple documents at once
Pro
Best for growing businesses
- 1,500 pages / month
- Additional pages billed automatically
- Quota-free testing
- Priority support
- Process multiple documents at once
Business
For high-volume teams
- 5,000 pages / month
- Additional pages billed automatically
- Quota-free testing
- Priority support
- Process multiple documents at once
Only pay for what you use. Additional pages are billed automatically in simple blocks.
Need more? View detailed pricing
Why Parselyze
Built out of frustration, not a trend
Whether you're automating an invoice workflow, processing hundreds of contracts, or building a product that handles user documents, extracting structured data from files is always harder than it should be.
FAQ
Questions? We've got answers.
Most developers are extracting data within 10 minutes. Pick a template, send a test document, get JSON back. No complex setup or training required.
We support PDFs, images (JPG, PNG, WEBP, TIFF, BMP), and ZIP files. Our AI handles varying layouts automatically - no need to provide training examples or worry about document variations.
Absolutely not. Your documents are processed for extraction only and are never used to train our models. We don't store, analyze, or repurpose your data in any way.
Built by developers who understand that "good enough" isn't good enough. Our parsing engine is designed for production workloads where accuracy matters.
Choose from our ready-made templates or create unlimited custom templates with our visual builder. You define exactly what gets extracted - we handle the complex parsing logic.
Really. 50 pages/month free forever. No credit card to start. Scale up when you're ready, scale down anytime.
Enterprise-grade security from day one. HTTPS everywhere, isolated processing, and we never store your documents unless you specifically request it. Your data is never used for training our AI models or any other purpose.
Absolutely. The free tier includes full API access and all features. Test your real documents with your real use cases before upgrading.
You can send multiple documents per API request. Processing typically takes seconds depending on document complexity and size.
You do. Your templates are private to your account. We never share, analyze, or use your templates for any other purpose.
Have more questions? Contact our support team
Document in. JSON out.
Build your template once, call the API, get clean structured data every time. No regex, no fragile parsers, no maintenance.
No credit card required · 50 pages/month free