{"result":{"document_type":"receipt","items":[{"description":"Chocolate (Ice)","quantity":1.0,"unit_price":24000.0,"total_price":24000.0},{"description":"Thai Tea (Ice)","quantity":1.0,"unit_price":24000.0,"total_price":24000.0},{"description":"Cleo Water","quantity":1.0,"unit_price":10000.0,"total_price":10000.0},{"description":"Es Batu","quantity":2.0,"unit_price":2000.0,"total_price":4000.0},{"description":"Nasi Goreng Sun Up","quantity":4.0,"unit_price":30000.0,"total_price":120000.0},{"description":"Chicken Nugget Platter","quantity":1.0,"unit_price":28000.0,"total_price":28000.0}],"subtotal":210000.0,"tax":21000.0,"total":231000.0,"notes":"DINE IN"},"document_info":{"size_mb":0.09,"pages":1,"approx_tokens":300}}
curl --location 'https://zylalabs.com/api/13136/receipt+and+invoice+ocr+api/26650/extract+receipt' \
--header 'Content-Type: application/json' \
--form 'image=@"FILE_PATH"'
注册后,每个开发者都会被分配一个个人 API 访问密钥,这是一个唯一的字母和数字组合,用于访问我们的 API 端点。要使用 Receipt and Invoice OCR API 进行身份验证,只需在 Authorization 标头中包含您的 bearer token。
| 标头 | 描述 |
|---|---|
授权
|
必需
应为 Bearer access_key. 订阅后,请查看上方的"您的 API 访问密钥"。
|
无长期承诺。随时升级、降级或取消。 免费试用包括最多 50 个请求。
(年度计费可节省 2 个月 🎉)
领先企业的信赖之选
This API extracts structured data from receipts and invoices. Upload a photo, scan, or PDF file, and receive a JSON response containing the vendor or merchant name, itemized line items with quantity and price, subtotal, tax, discount, total, dates, and payment method when available.
Supported input formats: JPEG, PNG, WEBP, HEIC/HEIF images, and multi-page PDF documents up to 25 pages.
Three endpoints are available: one optimized for retail receipts, one optimized for business invoices, and one that automatically detects which type of document was submitted.
Billing is based on document size — a single-page receipt and a multi-page invoice are billed differently based on the number of pages processed.
Each endpoint returns structured JSON data. The "Extract Receipt" endpoint provides vendor name, itemized line items (including quantity and price), subtotal, tax, total, notes, and document information such as size and page count.
Key fields in the response include "document_type," "items" (with "description," "quantity," "unit_price," and "total_price"), "subtotal," "tax," "total," "notes," and "document_info" (with "size_mb," "pages," and "approx_tokens").
The response data is organized in a JSON format with a "result" object containing the extracted data and a "document_info" object detailing the file's characteristics, such as size and number of pages.
The "Extract Receipt" endpoint provides information such as vendor name, itemized purchases, quantities, prices, subtotal, tax, total amount, notes, and document size and page count.
The endpoints accept image and PDF file uploads in formats like JPEG, PNG, WEBP, HEIC/HEIF, and multi-page PDFs. Users should ensure files are within the size limits for optimal processing.
Users can parse the JSON response to extract relevant fields for applications such as expense tracking, accounting, or inventory management. For example, the "items" array can be used to generate detailed purchase reports.
Data accuracy is maintained through advanced OCR technology that recognizes text and structures it into a usable format. Continuous improvements and updates to the OCR algorithms help enhance recognition capabilities.
Typical use cases include automating expense reporting, managing receipts for tax purposes, tracking business expenses, and integrating with accounting software to streamline financial processes.