PDF ANALYSIS API

Turn PDFs into structured JSON

The PDF analysis API for developers. POST a file or share a link. Define the fields you need, get vendor, totals, and line items back as JSON, no matter the layout.

No credit card required. 50 free credits to start.
POST /v1/pdf
{ "vendor": "Acme Supplies", "invoice_number": "INV-2044", "total": 84.20, "due_date": "2026-08-01" }
200 OK · 1.8s

HOW IT WORKS

PDF in, JSON out. Three steps.

01

Define your schema

List the fields you want back, like vendor, invoice number, total, or line items. You choose them, the API fills them in, regardless of layout.

02

Send the PDF

POST a file directly, or generate a shareable link. Users upload from any browser, no app needed.

03

Get your JSON

A webhook fires the moment analysis finishes, with every field you defined already filled in.

ONE SCHEMA ENGINE

What you can pull out of a PDF

Define the fields you need. The API returns exactly those, structured as JSON, regardless of the document's layout.

UNIFIED SCHEMA

Define your fields once. Extract them from every document.

{ vendor: string, total: number, line_items: array }
KV
Key-value fields

Vendor names, dates, totals, account numbers, anything labeled.

TBL
Tables

Line items, billing breakdowns, schedules, with full row and column structure.

FRM
Form fields

Filled or empty, checkboxes, radio buttons, signatures.

TXT
Body text

Paragraphs, clauses, sections, with semantic grouping.

#
Numbers

Totals, taxes, percentages, with currency and unit detection.

LYT
Layout

Page number, region on the page, document structure.

SIG
Signatures

Presence detection, signer name extraction.

+
Custom fields

Define a field, get it back.

USE CASES

What teams build with the PDF analysis API

Invoice processing

Vendors send invoices in 50 different layouts. Extract vendor, invoice number, totals, and line items.

{ vendor: "Acme Supplies", total: 1284.50 }
Expense reports

Employees upload receipts via the link. Extract merchant, date, amount, category. No manual entry.

{ merchant: "Delta Air Lines", amount: 342.00 }
Insurance claims

Claim forms and policy documents. Extract policy number, claim amount, incident date.

{ policy_number: "PL-88213", claim_amount: 4500 }
Medical records

Patient charts and lab results. Extract patient ID, diagnosis codes, medications.

{ patient_id: "P-2291", diagnosis_code: "J45.909" }
Bank statements

Reconciliation in seconds. Extract account number, period, opening and closing balance.

{ account_number: "****4471", closing_balance: 8213.44 }
AI agents with reading

Let users share a document instead of pasting text. No PDF infrastructure to manage.

{ document_type: "contract", key_terms: 6 }

PRICING

Start free. Scale when you need to.

Pay as you go
50 credits free
then $1 per 10 credits
  • 1 credit per document
  • Files auto-delete after 1 hour
  • Up to 3 assistants for different extraction tasks
  • Custom fields on every request
  • Shareable links, up to 10 files each
Start free
Pro
$149/mo
2,000 credits included
  • Everything in Pay as you go
  • Shared workspace for up to 3 teammates
  • Unlimited assistants
  • Fine-tune extraction with your own data
  • Custom branding on shareable links
  • Unlimited document length
Start free
Enterprise
Custom
for teams with scale or compliance needs
  • On-premise deployment
  • Custom-trained extraction models
  • Volume discounts
  • Priority support
Contact sales

FAQ

Questions, answered

How is this different from an OCR API?

OCR gives you raw text. We give you structured data. Define a schema and the API returns the vendor, totals, and line items you need, not just a wall of extracted characters.

What kinds of PDFs do you support?

Scanned documents, native text PDFs, fillable forms, and mixed documents with both. One extractor handles all of them without template setup.

Can you extract tables?

Yes. Line items, billing breakdowns, and schedules come back with full row and column structure, not flattened text.

Can you detect signatures?

Yes. Add a signature_present field to your schema, and the API can also extract the signer name where legible.

How long does extraction take?

Most documents process in 1 to 3 seconds per page. The webhook fires the moment processing completes.

How accurate is the extraction?

Most customers see 95 to 100 percent accuracy on well-defined fields. Every field includes a confidence score, so you can auto-accept high-confidence results.

Start analyzing PDFs today

50 free credits. No credit card required.

Start free