Data extraction software for the documents your team handles
PdfParse is one parser for every PDF and scan your product or team receives. The same API call returns JSON, Markdown and CSV, and a schema turns any document type into the fields you choose. Here is what teams parse with it.
Start with a document you already have
Drop any PDF, PNG or JPG and see page 1 as JSON, Markdown and CSV, with the rendered page showing every detected block.
What one call returns
Page one rendered with every block outlined, next to the JSON your code receives.
- Reading text layer
- Detecting layout
- Extracting tables
- Building JSON
Headings, paragraphs, tables and totals detected
Portsmouth, NH 03801
| Description | Qty | Unit | Amount |
|---|---|---|---|
| Oak countertop, 2.4 m | 2 | 640.00 | 1,280.00 |
| Cabinet doors, shaker | 12 | 85.00 | 1,020.00 |
| On site fitting | 1 | 450.00 | 450.00 |
Quote the invoice number with your transfer.
Goods remain ours until paid in full.
Pages 2 and later are parsed after you create an account.
{ "document": { "pages": 2, "parsed_pages": 1, "language": "en" }, "pages": [ { "number": 1, "blocks": [ { "type": "heading", "text": "Invoice", "bbox": [48, 52, 132, 84] }, { "type": "paragraph", "text": "Harbor Street Joinery, 14 Dock Lane, Portsmouth" }, { "type": "key_value", "pairs": { "Invoice no.": "INV-2026-0418", "Issued": "Oct 14, 2026", "Due": "Nov 13, 2026" } }, { "type": "table", "columns": ["Description", "Qty", "Unit", "Amount"], "rows": [ ["Oak countertop, 2.4 m", 2, 640.00, 1280.00], ["Cabinet doors, shaker", 12, 85.00, 1020.00], ["On site fitting", 1, 450.00, 450.00] ] }, { "type": "total", "label": "Total due", "value": 2983.75, "currency": "USD", "confidence": 0.98 } ] } ], "fields": { "invoice_number": { "value": "INV-2026-0418", "confidence": 0.99, "page": 1 }, "total": { "value": 2983.75, "confidence": 0.98, "page": 1 }, "due_date": { "value": "2026-11-13", "confidence": 0.97, "page": 1 } } }
Downloads from the demo include a watermark field and cover page one only.
Page one is parsed in your browser, so your file never reaches our servers.
One demo per day from this network. Create an account to parse more pages.
$ curl https://api.pdfparse.ai/v1/parse \ -H "Authorization: Bearer $PDFPARSE_API_KEY" \ -F file[email protected] \ -F outputs=json,markdown,csv
Invoices and supplier bills
Accounts payable teams pull the vendor, dates, totals, tax and every line item from invoices in any layout, including line item tables that continue on the next page. One schema covers every supplier. Read more about invoice OCR software.
Receipts and expense documents
Expense apps send phone photos and PDF receipts and get the merchant, date, payment method, tax, tip and total back while the employee is still on the screen. See the receipt OCR API.
Bank and broker statements
Fintech onboarding, lending and accounting products read transaction tables, balances and holdings from statements of many institutions. Multi page tables are joined, merged cells stay in place, and each table comes back as CSV and as rows in JSON. Statements are one document type among many, handled with the same PDF table extraction engine.
PDF forms and applications
Onboarding packs, account applications, claim forms and questionnaires arrive fillable, flattened or scanned. PdfParse returns each field and checkbox as a typed value with its page. Learn how to extract data from PDF form fields.
Contracts and agreements
Legal and procurement teams track parties, effective dates, terms, renewal notice periods, fees and named clauses across their whole repository, with a page reference for every value. Read about contract data extraction.
Research papers and technical reports
Two column layouts, footnotes, figures and tables in papers break simple text extraction. PdfParse keeps the reading order and headings, so the output reads in the right sequence. Teams use PDF to Markdown to feed papers into search, summaries and literature reviews.
Insurance claims and supporting documents
Claims arrive as a mix of forms, photos of receipts, repair estimates and letters. One call per file returns the text, the tables and the fields your claims system needs, with OCR on every scanned page. See the OCR API for scanned input.
Knowledge bases for RAG
AI engineers build assistants over manuals, policies and internal documents. PdfParse returns chunks split by section, each with page range, section path and bounding box, so answers can cite the exact page. Read about PDF parsing for RAG pipelines.
Two ways to use the same engine
Developers call the REST API or the Python and Node SDK, receive results in the same response or by webhook, and run backlogs as batch jobs of up to 500 files per job. Operations teams use the web app without code. They upload files, pick a schema and export CSV for their spreadsheet or system of record.
- JSON, Markdown and CSV from one call
- Tables with merged cells and multi page tables
- Form fields and checkboxes
- OCR for scanned PDFs, PNG, JPG and TIFF
- Custom extraction schemas with typed fields
- RAG chunks with page, section path and bounding boxes
What a page costs on each plan
Every plan is a monthly or yearly subscription, and yearly billing saves 50%. A page is one page of a PDF or one image file.
| Plan | Yearly billing | Monthly billing | Pages per month |
|---|---|---|---|
| Starter | $24 per month | $49 per month | 2,000 |
| Growth | $74 per month | $149 per month | 7,000 |
| Scale | $249 per month | $499 per month | 24,000 |
| Enterprise | $749 per month | $1,499 per month | 72,000 |
Custom schemas, webhooks and batch jobs start on Growth. Form field and checkbox detection and zero retention mode are part of Scale. See PDF extraction API pricing for the full comparison.
Built for documents that carry sensitive data
Files travel over TLS and are encrypted at rest. Retention follows your plan, from 7 days on Starter to zero retention mode on Scale and Enterprise, and files are never used to train models. Read how secure document processing works at PdfParse.
Start from the reference
Every use case on this page uses the same endpoint, POST /v1/parse, with a schema id or an inline schema. The document parsing API reference lists every option, response field and webhook event.
Parse the documents your team handles
Create an account, take an API key and send your first document, or upload a folder in the web app.