Shipping label OCR API
Read shipping labels from parcel photos into tracking number, carrier, sender and recipient addresses.
Result
Your Markdown or JSON shows up here.
What makes shipping labels hard to read
- Crumpled, curved or taped-over labels
- Barcodes and small print side by side
- Handwritten corrections on printed labels
What you can pull out
shipping-label fields
{
"carrier": "UPS",
"tracking_number": "1Z999AA10123456784",
"service": "Ground",
"sender": "Bloom Goods, 22 Market St, Seattle WA",
"recipient": "Ana Souza, 9 Pine Ave, Denver CO 80203",
"weight": "2.4 lb",
"ship_date": "2026-11-07"
}Best models for shipping labels
1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.
google/gemini-flash3 credits / page2Amazon TextractAWS OCR with form key-value pairs, tables and per-word confidence scores.aws/textract6 credits / page3GPTGeneral vision model. Good at messy scans and following extraction instructions.openai/gpt11 credits / pageCall it from your code
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-flash",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'