Drop in a PDF, image, or DOCX — one file or a batch. Each upload can be up to ≤10MB and ≤15 pages.
PRODUCT
Everything you need to turn documents into data.
From a single upload to a typed JSON response — OCR plus leading LLMs handle the whole extraction pipeline, in the dashboard or over the API.
HOW IT WORKS
Upload. Extract. Export.
Extract from a single file or run a whole batch — the pipeline is the same either way.
Step 1
Upload
Step 2
Extract
OCR reads the page and an LLM maps it to structured fields for the document type you selected.
Step 3
Export
Get clean, typed JSON in the dashboard or via the API — and a signed webhook when the job finishes.
PROCESSING MODELS
Quality or speed, your call.
Pick the processing model per extraction — the highest-quality model for tricky documents, or the fastest model when throughput matters.
Claude Opus 4.8 is the default for the highest-quality extractions — dense layouts, messy scans, and documents where every field matters. Select it per request with model=claude-opus-4-8.
DOCUMENT TYPES
12 types, ready to extract.
Grouped into Identity, Financial, and Tax — all built in, all available on every plan.
IDENTITY
Driver's License
Name, address, license number, and expiry.
IDENTITY
Passport
MRZ fields, holder details, and document number.
FINANCIAL
Invoice
Line items, totals, tax, and vendor details.
FINANCIAL
Bank Statement
Balances, transactions, and account metadata.
FINANCIAL
Pay Stub
Gross, net, deductions, and pay period.
FINANCIAL
Purchase Receipt
Merchant, line items, tax, and total.
FINANCIAL
Utility Bill
Service address, billing period, and amount due.
TAX
W-2
Wages, withholdings, and employer information.
TAX
1040 · 1099-*
Individual returns and the 1099 family of information returns.
CUSTOM TYPES
Your documents, your fields.
Built-in types don't cover everything. Define custom document types with your own typed fields, and dOCR maps each upload to exactly the shape your systems expect.
EXTRACTION HISTORY
Nothing gets lost.
Every extraction is saved to your history. Browse past runs, open the returned JSON, and download results whenever you need them.
LIMITS & FORMATS
No surprises.
The formats we accept and the per-upload limits, listed up front.
| Supported | ||
|---|---|---|
| Formats & limits | File formats | PDF · JPG · JPEG · PNG · BMP · WebP · DOCX |
| Max file size | ≤10MB per upload | |
| Max pages | ≤15 pages per upload | |
| Batch | Single file or batch |
TEAM & SECURITY
Built for teams, secure by default.
CLERK ORGANIZATIONS
Team & access
Invite your team and manage roles through Clerk Organizations — shared history, keys, and billing.
HMAC · IP WHITELIST
Security & API
Signed webhooks, IP whitelisting, and scoped API keys. See it all on the Developers page →
Put your document pipeline on autopilot.
Start on the free plan — 50 pages/mo, no credit card required.
