Endpoint

POST /v1/

Extract structured data from documents and images using AI-powered parsing.

Request Body

Parameter	Type	Required	Description
schema	object	Yes	JSON schema defining the data structure to extract
contents	array	Yes	Array of files to process

Contents Array

Each item in the contents array must contain:

Field	Type	Required	Description
filename	string	No	Optional filename
mimeType	string	Yes	MIME type of the file
data	string	Yes	Base64-encoded file data

Supported MIME Types

• image/jpeg - JPEG images
• image/png - PNG images
• image/webp - WebP images
• image/gif - GIF images
• application/pdf - PDF documents

Request Example

{
  "schema": {
    "type": "object",
    "properties": {
      "invoice_number": {
        "type": "string",
        "description": "Unique invoice identifier, often prefixed with 'INV-' or similar"
      },
      "total_amount": {
        "type": "number",
        "description": "Final amount due including all taxes and fees"
      },
      "date": {
        "type": "string",
        "description": "Invoice date in YYYY-MM-DD format"
      }
    }
  },
  "contents": [
    {
      "filename": "receipt.pdf",
      "mimeType": "application/pdf",
      "data": "JVBERi0xLjQKJcOkw7zDtsO..."
    }
  ]
}

Response

Returns extracted data as JSON matching your provided schema:

{
  "invoice_number": "INV-2024-001",
  "total_amount": 1250.5,
  "date": "2024-01-15"
}

Error Responses

Status Code	Description
400	Bad Request - Invalid request format
401	Unauthorized - Invalid or missing API key
500	Internal Server Error - Server processing error