Vision›OCR Extract
API Key not detected. Please configure to use debug features.
General Scenario
*Input Image

Supported formats: JPG / JPEG, PNG, BMP

Size limit: ≤ 10MB

General Extraction
Task Info
Trace ID-
Status-
Extraction Result
Result will show here
Guide
This is a synchronous API: upload an image and a prompt to get the extraction result immediately.
Write a precise prompt and specify the output format (e.g., JSON) for structured parsing.
API Reference
CURL
curl -X POST "https://maas-api.hivoice.cn/v1/ocr/image/extract" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=u1-ocr-extract" \
  -F "scene=general" \
  -F "prompt=Your task is to extract information from the image above and structure it into JSON.
Strictly follow this schema for extraction (if a field does not exist, return an empty string): {\"invoiceNumber\":\"\",\"issueDate\":\"\",\"items\":[{\"itemName\":\"\",\"unitPrice\":\"\",\"quantity\":\"\",\"totalAmount\":\"\"}]}
Please output JSON only. All values must be strings. Do not provide any explanation." \
  -F "image=@/path/to/image.png"