Extract data from a document
Upload a document (PDF, image, Word, PowerPoint, Excel, CSV, TXT, RTF, ODT, HTML, or EML) and extract structured data using a template. Each extraction costs 1 credit.
The template defines the fields to extract. You must create a template first from the dashboard before using this endpoint.
Note: You can provide either a file (upload) or file_url (URL to document). At least one is required.
Authorization
ApiKeyAuth x-api-key<token>
Your ParserBee API key. Generate one from Settings in your dashboard. The key starts with pk_.
In: header
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl -X POST "https://example.com/api/v1/extract" \ -H "Content-Type: application/json" \ -d '{ "template_id": "abc123def456" }'{ "success": true, "request_id": "req_abc123", "data": { "invoice_number": "INV-2026-001", "total_amount": 1500, "vendor_name": "Acme Corp" }, "credits_remaining": 449, "processing_time_ms": 2400, "usage": { "pages_processed": 1, "doc_size_bytes": 204800 }}{ "error": "File is required", "code": "MISSING_FILE"}{ "error": "Invalid API key", "code": "INVALID_API_KEY"}{ "error": "Insufficient credits. Please purchase more credits.", "code": "INSUFFICIENT_CREDITS", "credits_remaining": 0}{ "error": "No active subscription. Please subscribe to use this API.", "code": "SUBSCRIPTION_INACTIVE"}{ "error": "Template not found or you don't have access to it", "code": "TEMPLATE_NOT_FOUND"}{ "error": "Failed to process document", "code": "PROCESSING_FAILED"}