Tell DoXroute what fields matter to you. Drop invoices, customs forms, or scanned receipts. Receive clean, typed JSON — same shape, every time, any language.
Free tier · no credit card · deploy on your own servers if you want
Classification, extraction, splitting, review — the full pipeline runs without writing a single rule.
Write "I need vendor, date, line items and total from my invoices." DoXroute builds the full extraction template for you.
Invoices, packing lists, bills of lading, purchase orders, customs declarations — seven schemas tuned for international trade.
Don't know what the document is? Neither did we. The classifier reads the first page and picks the right schema before extraction starts.
Select up to 50 files, hit upload. A progress bar tracks each one. Download all results when the batch finishes.
Got a 40-page PDF with three invoices and a packing list glued together? DoXroute splits it at the seams and processes each part alone.
Click any extracted value to see where it came from in the original document. Bounding boxes overlay the PDF page.
One API key authenticates everything. Fourteen endpoints cover extraction, batching, splitting, schema management and job polling. Async workers keep the queue moving.
# Extract structured data from a document curl -X POST https://doxroute.xdinamic.com/api/v1/extract \ -H "X-API-Key: YOUR_KEY" \ -F "file=@invoice.pdf" \ -F "doc_type=invoice" # Poll for results curl https://doxroute.xdinamic.com/api/v1/jobs/{job_id} \ -H "X-API-Key: YOUR_KEY"
The same endpoint handles a single invoice or a morning's worth of customs paperwork. Batch mode tracks each file independently.
Send a plain-text description to /extractors, get back a reusable schema ID. Use it on every future upload without re-describing.
Extraction runs on Anthropic. If that's unreachable, the request silently reroutes through OpenRouter. You never see the switch.
The cloud API and the self-hosted Docker stack share the same codebase. Migrate without changing a single integration line.
| Feature | DoXroute | DocuPipe | Textract | GPT-4 |
|---|---|---|---|---|
| Structured extraction | ✓ | ✓ | ✓ | ✓ |
| Custom schema (NL) | ✓ | ✓ | — | — |
| Batch upload | ✓ | ✓ | ✓ | — |
| Document splitting | ✓ | ✓ | — | — |
| Visual review + bbox | ✓ | ✓ | — | — |
| Equations → LaTeX | ✓ | — | — | — |
| Native Office files | ✓ | — | — | ✓ |
| Self-hosted / on-prem | ✓ | — | — | — |
| Open pricing | ✓ | ✓ | ✓ | ✓ |
Upload it, pick a schema, get JSON back. The whole loop takes less time than reading this sentence twice.