DocParse turns PDFs, images, and DOCX files into clean JSON. Define the fields you need, upload the file, get structured data back—in any language, no templates required.
{
"vendor": "Acme Supply Co.",
"invoice_no": "INV-20294",
"bill_to": "Northwind Logistics",
"date": "2026-04-14",
"line_items": [
{ "Steel pallet", 12, 840.00 },
{ "Strapping", 4, 162.00 }
],
"total": 1842.50,
"currency": "USD"
}Tell DocParse which fields you need. It reads the document and returns them as clean JSON—ready for your database, webhook, or Zap.
{
"vendor": "Acme Supply Co.",
"invoice_no": "INV-20294",
"bill_to": "Northwind Logistics",
"date": "2026-04-14",
"total": "$1,842.50"
}From extraction and classification to validation, human review, and automatic delivery — here’s the full surface area that’s live in production today.
Define the fields you need, upload PDFs / images / DOCX, and receive structured JSON. Built-in templates for invoices, receipts, contracts, resumes, bank checks, business cards, bills of lading, and emails — plus custom fields for anything else.
Sort incoming documents into categories you define. Pair it with an extraction so DocParse classifies first, then pulls the right fields for each category.
Toggles for tables, charts, checkboxes, handwriting, multi-page, split-PDF, and specific pages — pick what matches your input for richer, more accurate output.
Attach business rules that run after every document: totals must equal line items, fields can be required, values must match a pattern or sit in an approved list, dates can't be in the future. Anything that fails is flagged instead of passing through silently.
One place that collects every document needing a human — across all extractions — with the exact validation issues inline. Reviewers correct or confirm and the item clears automatically.
Every extraction gets its own forwarding address. Email or forward documents and the attachments are imported, extracted, and validated automatically. Turn it on per extraction and rotate the address any time.
Send extracted data where it needs to go automatically — a webhook, an automation tool, or your own system — as JSON or CSV, the moment a document is processed or after a reviewer confirms it. Every delivery is HMAC-signed and logged.
A live trust dashboard: straight-through-processing rate, exception rate, validation pass rate, average processing time, per-extraction breakdown, and the rules that fail most often.
Bearer-token auth with revocable, SHA-256-hashed API keys. Outbound webhooks signed with HMAC-SHA256 per the Standard Webhooks spec, with replay protection and per-endpoint delivery logs.
Triggers when an extraction completes, actions to upload files or create extractions on the fly. Wire DocParse into Gmail, Drive, Slack, Sheets, and 6,000+ other apps without writing code.
Pages used, documents classified, document-type breakdown, extractions pie chart, language distribution, and estimated time and cost savings — all in one view, refreshed live.
Pay-as-you-go packages or monthly subscriptions in either currency. Hosted customer portal for invoices, payment methods, and subscription changes. Powered by Dodo Payments as merchant of record.
We're a people-first product. We prioritise real human support over AI-agent replies, any time you need us. That's our promise — and our edge. So let's skip the funnels and just talk.
Just email us directly — or log in to the app for our WhatsApp & phone numbers. A founder will answer, not a ticket queue.
Co-founder
Co-founder
Prefer to call or WhatsApp the founders? Log in to the app and you'll find our direct numbers on the Talk to us page.
Want the product tailored to how your team works — a new field type, a different export, a workflow that's uniquely yours? We'd love to build it for you. Don't worry, we've got you.
Got feedback, want a product demo, or need a custom feature? Reach out — we'd be genuinely happy to help, and we'll prioritise it as fast as we can. People over everything is what we're built on.
PDFs, JPGs, PNGs, WEBP, and DOCX—up to 25 MB per file. Scans, photos, and digitally generated documents all go through the same pipeline.
You decide what to pull out: vendor names, totals, dates, line items, anything. DocParse fills your schema in seconds—no templates, no training, no fine-tuning.
DocParse reads layouts it has never seen before. You don't train it. You don't template it. You give it a document and tell it which fields you want.
Plain HTTP. Bearer-token auth with revocable keys. Signed outbound webhooks for async pipelines, and a native Zapier app so non-developers can ship too.
# 1. Create an extraction with the fields you want
curl https://api.docparse.io/api/v1/createExtraction \
-H "Authorization: Bearer $DOCPARSE_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Invoices",
"template": "invoice",
"fields": [
{ "name": "vendor", "type": "string" },
{ "name": "total", "type": "number" },
{ "name": "due_date", "type": "date" }
]
}'
# 2. Upload a file to it
curl https://api.docparse.io/api/v1/uploadFiles \
-H "Authorization: Bearer $DOCPARSE_KEY" \
-F "extractionId=ext_..." \
-F "files=@invoice.pdf"Your documents stay yours. TLS everywhere, hashed API keys, signed webhooks, and a processing pipeline that never retains your data for model training.
100 free pages on signup. No credit card. Pay in USD or INR when you need more.