Send a PDF or a scan and get JSON, Markdown and CSV back, with tables, form fields and reading order intact.
Page one rendered with every block outlined, next to the JSON your code receives.
Headings, paragraphs, tables and totals detected
| 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 |
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
Engineers call the API from their own code. Operations teams use the same engine in the web app, without writing a line.
A REST endpoint, typed JSON and SDKs that fit into the pipeline you already run.
Upload documents in the browser, define the fields you need once and export clean tables.
Merged cells, multi line rows and tables that continue on the next page come back as rows and columns, ready for PDF table extraction or PDF to CSV.
Form fields return as label and value pairs, checkboxes as true or false. Applications and claims land in your database as records. Included on Scale and Enterprise.
Pages without a text layer go through OCR automatically and return the same structure as digital PDFs. See the OCR API.
Define fields once (invoice_number, total, due_date) and every document returns exactly those keys with a confidence score and source page. See PDF data extraction.
Markdown with headings kept, split into chunks by section, each with page numbers, section path and bounding box. See PDF parsing for RAG.
Large files run as jobs. A signed webhook tells your service the moment the result is ready.
Send up to 500 files in one job and collect every result through one job id.
A file or a URL arrives through the API or the web app.
Pages without a text layer are read as images.
Columns, headings and reading order are detected.
Rows, columns and merged cells are rebuilt.
Your fields are filled with values and confidence.
JSON, Markdown and CSV are written together.
Your endpoint receives a signed notice.
Move the sliders to see which plan covers your volume and what one page costs in it.
The calculation uses PdfParse prices only, with yearly billing selected by default.
Documents carry customer data, so retention, access and audit are part of the product, not an add-on.
A clerk keying one invoice takes minutes. PdfParse returns it in seconds, at a published price per page on every plan.
Read about security
Most teams start with a PDF library, an OCR engine or a person retyping values. This is what each one gives you on a real document.
| What you need | PdfParse | Open source PDF library | Plain OCR engine | Manual keying |
|---|---|---|---|---|
| Tables with merged cells | Rows, columns and spans rebuilt | Ruled tables only, spans fixed by hand | Lines of text, no table structure | Retyped cell by cell |
| Scanned pages | OCR, then the same layout and table detection | A separate OCR step to wire in | Text only, no layout | Read by eye |
| Your own fields | Schemas return exactly your keys | Custom code for every layout | Custom code for every layout | A spreadsheet template |
| Chunks for RAG | Section path, pages and bounding boxes | Your own splitter | Not included | Not included |
| Webhooks and batch jobs | Signed webhooks, up to 500 files per job | Your own queue and retries | Your own queue and retries | Not included |
| Confidence scores | On every block and field | Not included | Per word only | Depends on the reviewer |
| Time to first result | One API call, under ten minutes from signup | Days of tuning per layout | Hours, then cleanup code | Minutes per page, on every page |
For a solo developer taking a project to production.
For a product team with one document pipeline.
For a company running several pipelines.
For regulated or high volume companies.
| Plan | Yearly, per month | Monthly | Pages per month |
|---|---|---|---|
| Starter | $24 | $49 | 2,000 |
| Growth | $74 | $149 | 7,000 |
| Scale | $249 | $499 | 24,000 |
| Enterprise | $749 | $1,499 | 72,000 |
See every limit on the PDF extraction API pricing page.
Scanned pages go through OCR and then the same layout and table detection as digital PDFs. Every block and every schema field carries a confidence score, so your code can send low confidence values to a person for review.
Yes. Tables return as rows and columns with merged cells resolved, in JSON and as a separate CSV per table. A table that continues on the next page is joined into one.
Files are kept for the retention period of your plan: 7 days on Starter, a period you choose up to 30 days on Growth. Scale and Enterprise can switch on zero retention mode. Files are never used to train models. Files in the website demo are parsed in your browser and never uploaded.
One page of a PDF or one image file counts as one page. Pages count as usage in the billing period, so deleting a document does not return them.
Parsing pauses and the app shows an Upgrade button. Nothing is charged automatically. If you upgrade, the difference is charged right away and the new limit applies at once.
There are official SDKs for Python and Node.js. Any other language works through the REST API with a single multipart request.
Yes. From the Growth plan you create extraction schemas with field names, types and descriptions, and every document returns exactly those keys.
Yes. You cancel in billing settings. Renewal stops and access runs to the end of the period you paid for. Payments are final, as described in the refund policy.
Drop a file and see page one as JSON, Markdown and CSV in seconds.
Parse your first PDFParse every page, download results and get your API key.
Already have an account? Sign in
By creating an account you accept the terms and the privacy policy.