AI-Invoice Parser in Make

What this module does

PDF4me AI-Invoice Parser extracts structured data from PDF or image invoices inside your Make scenario using AI — no template setup, no field coordinates, no rules to maintain. Supply a PDF, PNG, JPG, or JPEG and the module returns vendor details, line items, amounts, dates, taxes, currency, and payment terms as individually mappable fields. Ideal for accounts payable automation, expense management, financial reconciliation, and invoice digitization workflows that scale across hundreds of vendors and formats.

Authenticating Your API Request

Every PDF4me module in Make requires a valid Connection. Create or select one that holds your PDF4me API key so the scenario can authenticate AI invoice extraction requests securely.

Get your API Key

Important Facts You Should Not Miss

Supports PDF, PNG, JPG, and JPEG inputs

Map the invoice binary from Dropbox, Google Drive, email attachments, or HTTP modules directly into the Document field. Set the Invoice Name with the correct extension — PDF for digital invoices, PNG/JPG/JPEG for scanned or photographed invoices.

Confidence scores included in every output

Each extraction returns a confidence object with per-field scores (0–1). Use a Make Filter to route low-confidence results to a human review queue in Airtable or Slack instead of pushing them directly into accounting systems — eliminates costly downstream corrections.

Use Custom Field Keys for non-standard invoices

Add extra field names via Custom Field Keys to extract fields beyond the standard invoice schema — vendor_phone, tax_id, purchase_order_number, store_number. Each custom key returns as an individually mappable token in the Make output bundle.

Set File to Map, wire Invoice Name and Document from the prior module, and optionally add Custom Field Keys to extract fields beyond the standard invoice schema.

Parameters

Required: Connection, Invoice Name, and Document must always be provided. The matching input field (Binary Property, Base64 Content, or File URL) is required based on the chosen Input Data Type. Custom Field Keys are optional and can be added per scenario.

Parameter	Required	What it does	Example
Connection	Yes	PDF4me API connection. Click Add and paste your API key the first time. Reused automatically across all PDF4me modules in your scenarios.	My PDF4me connection
Input Data Type	Yes	How the invoice is supplied. Binary Data reads from a previous module (most common). Base64 String accepts encoded payload. URL downloads from a public link.	Binary Data
Input Binary Field	Conditional	Binary content of the invoice file. Required when Input Data Type is Binary Data. Wire from Dropbox, Google Drive, OneDrive Data field, or any HTTP/email module that returns file bytes.	1. Data
Base64 Invoice Content	Conditional	Base64-encoded invoice content. Required when Input Data Type is Base64 String. Useful when invoice arrives from a webhook or API call that delivers encoded content.	JVBERi0xLjQK...
Invoice URL	Conditional	Public URL to the invoice file. Required when Input Data Type is URL. The URL must not require authentication.	https://example.com/invoice.pdf
Invoice Name	Yes	Filename of the invoice with proper extension (.pdf, .png, .jpg, .jpeg). Used for format detection and AI processing optimization.	invoice.pdf
Custom Field Keys	No	Optional list of custom field keys to extract beyond the standard invoice schema. Each key returns as an individual mappable token in the output bundle.	["vendor_phone", "tax_id", "purchase_order_number"]

Output Fields

Field	Type	What it contains
invoiceNumber	String	Extracted invoice number or reference identifier (e.g. INV-2024-001).
vendorName	String	Complete name of vendor or supplier as printed on the invoice.
vendorAddress	String	Complete vendor address including street, city, state, and postal code.
vendorEmail	String	Vendor email address when present on the invoice.
vendorPhone	String	Vendor phone number when present on the invoice.
billToName	String	Name of the entity being billed (your company or end customer).
billToAddress	String	Complete billing address.
invoiceDate	String	Invoice issue date in ISO 8601 format (YYYY-MM-DD).
dueDate	String	Payment due date in ISO 8601 format.
subTotal	Number	Subtotal amount before taxes.
total	Number	Final total amount including all taxes and adjustments.
currency	String	Currency code in ISO 4217 format (USD, EUR, GBP, INR, CHF, etc.).
paymentTerms	String	Payment terms and conditions (e.g. Net 30, Due on receipt).
lineItems	Array	Array of line items with description, quantity, unitPrice, total, and HSN code when present.
cgst / sgst / igst	Number	Indian tax fields when present on the invoice — central, state, and integrated GST amounts.
confidence	Object	Per-field confidence scores (0–1). Use a Make Filter to route low-confidence extractions for human review.
jobId	String	PDF4me job identifier for audit trail and support tickets.
success	Boolean	True if the AI extraction completed successfully; false if it failed.
message	String	Human-readable status message confirming success or describing the error.

Quick Setup

1. Add PDF4me → AI-Invoice Parser to your Make scenario.
2. Select Connection (or click Add to create one with your PDF4me API key).
3. Under File, choose Map to reveal Invoice Name and Document fields.
4. Map Invoice Name to the filename of the source file (include .pdf, .png, .jpg, or .jpeg).
5. Map Document to the binary content from the source module — typically the Data field of Dropbox, Google Drive, OneDrive, or Gmail attachment modules.
6. Optionally add Custom Field Keys for fields beyond the standard invoice schema (e.g. purchase_order_number, tax_id, store_number).
7. Click Save and run the scenario. The output bundle exposes every extracted field — wire them into QuickBooks, Xero, Airtable, Google Sheets, Slack approval, or HTTP modules.

Workflow Examples

Workflow ExamplesCommon Make scenario patterns using AI-Invoice Parser.

Vendor email → AI-Invoice Parser → QuickBooks bill

1. Gmail triggers when an email arrives from a known vendor address with a PDF invoice attachment.
2. The attachment is passed to AI-Invoice Parser. The output bundle returns vendor name, invoice number, line items, total, currency, and payment terms.
3. A Make Filter checks confidence on the total field — extractions below 0.85 route to a Slack channel for human review.
4. High-confidence invoices are posted to QuickBooks as a new bill with vendor, due date, line items, and account mapping applied automatically.
5. An Airtable log record captures the invoice number, vendor, amount, status, and timestamp for audit reporting.

Dropbox watch folder → bulk parse → Google Sheets ledger

1. A Dropbox Watch Files trigger fires whenever a new invoice PDF is dropped into the accounting inbox folder.
2. AI-Invoice Parser extracts the full invoice payload. Custom Field Keys add purchase_order_number and department_code so cost allocation is captured per row.
3. A Google Sheets Add a Row module appends one normalized ledger row per invoice — vendor, total, currency, PO, department, due date.
4. A second module iterates over each lineItem and appends it to a separate Line Items sheet for spend analytics.
5. The invoice PDF is moved into a year-month subfolder for archive, keeping the inbox clean for the next run.

High-value invoice → AI parse → multi-step approval

1. A webhook receives invoices from an internal portal. The Document binary is passed to AI-Invoice Parser.
2. A Router branches on the extracted total amount. Invoices over $10,000 require CFO approval; over $1,000 require manager approval; under $1,000 auto-approve.
3. Each branch sends a Slack approval message containing vendor, total, line items, and a link to the original PDF.
4. When approval is received, the invoice posts to Xero as a bill with the correct GL account based on Custom Field Keys (department_code, project_code).
5. A final Airtable row records the approver, approval timestamp, and final disposition for compliance audit trails.

Frequently Asked Questions

What invoice fields does the AI-Invoice Parser extract?+

The module returns a complete structured set: invoiceNumber, vendorName, vendorAddress, vendorEmail, vendorPhone, billToName, billToAddress, invoiceDate, dueDate, subTotal, total, currency (ISO 4217), paymentTerms, and a lineItems array with description, quantity, unit price, total, and HSN code per row. Indian tax fields (cgst, sgst, igst) appear when present. Every field comes with a confidence score so you can decide which extractions to trust automatically and which to route for human review.

What file formats does AI-Invoice Parser support in Make?+

PDF, PNG, JPG, and JPEG. Digital PDFs (born-digital invoices generated by ERPs or invoicing software) deliver the highest extraction accuracy. Scanned PDFs and photographed invoices work too — PDF4me applies AI OCR before semantic extraction. Always set the Invoice Name with the correct file extension so the module detects the format properly and applies the right processing pipeline.

How do I extract fields that are not in the standard invoice schema?+

Use the Custom Field Keys parameter. Add keys such as purchase_order_number, store_number, department_code, vendor_tax_id, gst_number, or any other field your accounting workflow needs. Each custom key returned appears as an individually mappable token in the Make output bundle and can be wired directly into accounting, database, or ERP modules without any additional parsing.

How should I handle low-confidence extractions in production scenarios?+

The confidence object returns per-field scores from 0 to 1. Add a Make Filter immediately after the parser to route low-confidence invoices (e.g. total confidence below 0.85, or any critical field below 0.90) into a human review queue in Airtable, Slack, or a dedicated approval workflow. High-confidence results go straight to QuickBooks, Xero, NetSuite, or your ERP. This pattern eliminates costly downstream corrections while still scaling to thousands of invoices per month.

Can AI-Invoice Parser process invoices in different languages and currencies?+

Yes. The AI is trained on multilingual invoices and handles English, German, French, Spanish, Italian, Portuguese, Dutch, and other major business languages without any extra configuration. Currencies are returned in ISO 4217 format (USD, EUR, GBP, INR, CHF, JPY, etc.) so downstream conversion or reconciliation logic always has a normalized code regardless of the source invoice format.

Related Modules

AI-Process Order

Extract purchase order and sales order data — pair with AI-Invoice Parser for end-to-end procure-to-pay automation and three-way matching.

AI-Process Receipt

Parse retail and expense receipts — use alongside Invoice Parser for full accounts-payable and expense-management coverage.

AI-Process Bank Statement

Extract transactions and balances from bank statements — match invoice payments against bank entries for automated reconciliation.

Get Help

Make IntegrationGet your API KeyMake Documentation