Invoice & Receipt Data Extraction API

When to use this API

This service converts financial documents into reviewable JSON including parties, identifiers, line items, totals, tax breakdown, confidence and validation signals. It is intended for accounting automation, reconciliation and document-driven finance workflows where extracted data is reviewed before downstream use.

• You need bookkeeping-ready structured output from invoices or receipts.
• You want validation feedback for incomplete or inconsistent financial fields.
• You need to feed extracted accounting data into ERP or automation systems.

Typical use cases

• AP automation and invoice ingestion.
• Expense receipt normalization.
• Financial data extraction for reconciliation workflows.

Billing and APIRAPTOR token model

Invoice & Receipt Extraction usage is metered per processed document page through the `invoice_receipt_page` service billing event.

• Tokens are the APIRAPTOR communication unit: 1 token = 100 subtokens.
• Trial availability, token amount and duration come from Billing configuration.
• All services are available from day one; Invoice & Receipt Extraction is not premium-gated per plan.
• This is service billing event metering, not ordinary API-call billing.

Extraction quality boundary

Extraction results are structured review inputs, not a guarantee of perfect accounting, tax or legal correctness.

• Quality depends on scan quality, layout, language, readability, OCR/text extraction quality, visible tax data and atypical invoice or receipt formats.
• Confidence, warnings, missing fields and validation checks should be read together before automation.
• The result does not replace an accountant, tax advisor, formal document validation or compliance review.

Sync and async usage

Sync and async requests use the same canonical invoice/receipt extraction POST endpoint.

• Sync uses POST /v1/invoice-receipt-extraction with mode=sync or the configured default mode.
• Async create uses POST /v1/invoice-receipt-extraction with mode=async.
• Job status uses GET /v1/invoice-receipt-extraction/jobs/{jobId}; file artifacts are returned as file_id values for authenticated API download and are deleted automatically no later than 48 hours after creation.