Prepare supplier bills for AP review as invoices arrive
For Accounts payable teams preparing supplier bills
Replace an unstructured invoice attachment with the fields your payable intake process expects. Start with supplier identity, invoice references and amounts, then pass the checked result to your accounting workflow.
25 free credits/month · No card needed
See the workflow and review checks{
"supplier_name": "Example Supply Co. — synthetic",
"invoice_number": "DEMO-INV-0048",
"invoice_date": "2026-08-01",
"due_date": "2026-08-31",
"currency_code": "USD",
"line_items": [
{
"description": "Example packing cartons",
"quantity": 100,
"unit_price": 2.5,
"line_total": 250
}
],
"invoice_total": 250
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A supplier sends an invoice that must be entered and routed to the right approver before the next payment run.
Supplier layouts vary, totals may include shipping or tax and an invoice can repeat a purchase order number in several places. Re-entering the header and line items consumes attention that AP needs for exceptions. A schema captures the requested facts in a consistent shape without assigning ledger codes or authorizing payment.
Start with the documents you already collect
- Supplier invoice PDFs
- Scanned paper invoices
- Credit memos using a separately evaluated schema
PDF, JPEG, PNG, TIFF, or WEBP. Send one file per extraction call; create separate schemas when the document types need different fields.
Define the fields
Open the starter schema. Edit field descriptions, mark the values your process requires, and save it in your account.
Extract at intake
Send the document and saved schema slug to
POST /api/v1/extract, or collect the file through a branded upload site.Hand off reviewed data
Your accounting integration resolves the vendor, checks duplicates and validates totals. AP applies coding and approval rules before creating or posting a bill in its own system.
A schema shaped around the next step.
Start with these fields, then adjust them to match your documents and destination system. The example above shows the data object you are asking Dokyumi to extract.
Download editable starter schemaStarter fields are optional until you choose which are required. Nested line items need a defined structure if you want validation of their individual values.
| Field | Type | What to capture |
|---|---|---|
supplier_name | string | Supplier printed on the invoice, before vendor-master matching. |
invoice_number | string | Preserve letters, leading zeros and punctuation. |
invoice_date | date | Printed invoice issue date. |
due_date | date | Printed due date; do not infer from ambiguous terms. |
currency_code | string | Explicit invoice currency when available. |
line_items | array | Description, quantity, unit price and line total for each visible item. |
invoice_total | currency | Total amount printed as due on this invoice. |
Give exceptions a clear path to review.
Dokyumi returns a model-reported confidence map, validation details, and a completed or review status for produced results. Check required fields and your business rules before passing data onward.
A completed extraction describes the extraction result. Your application and reviewers own matching, approvals, routing, and updates to other systems.
Read the response contractChecks for this process
- Credit memo mistaken for an invoice
- Invoice total confused with previous account balance
- Foreign currency or unclear tax presentation
- Duplicate invoice number under a supplier alias
Prove the fit on a representative batch.
Select representative suppliers, a multi-page invoice and one credit memo. Compare the extracted fields with approved AP entries and measure the corrections your reviewers actually make.
Compare extracted values with a reviewer’s reference set. Record corrections, unresolved fields, review time, and credits used before connecting downstream actions.
The free plan’s credit limits apply. Assisted pilots are scoped with Dokyumi before work begins.
Expand when the next process is ready
Use a paid plan for recurring monthly invoice intake. Add schemas for receipts, credits or purchase orders when those document types enter the same review process.
For a tailored implementation
Discuss custom volume and schema setup for multiple entities or large supplier populations.
Talk through document mix and volumeStart small. Add capacity as intake grows.
All self-service plans include the REST API, upload-site webhooks, custom confidence thresholds, and schema inference. Choose by volume, schema count, and upload sites.
Each document uses one credit per 5 pages, rounded up. An 8-page file uses 2 credits. Self-service files can be up to 50 pages; larger files, custom-built schemas, and additional volume are quoted through Enterprise. Full pricing details
Questions about ap invoice intake
Will extraction post bills to my ERP?
No native posting is implied. Your integration maps the result and performs the accounting system write after your approval checks.
Does it detect duplicate payments?
Your own records and matching logic are needed for duplicate checks. Extracted supplier names and invoice references provide useful inputs.
Can invoice lines be customized?
Yes. Define the line-item structure your process needs, then evaluate it on your suppliers’ actual formats before expanding volume.
How do I test this workflow on my own documents?
Start free with 25 credits per month, 2 schemas, and 1 branded upload site. The starter schema opens in the schema builder after sign-up. Edit the fields, save it, and upload a representative file through your account or the extraction API. Account documents are stored according to Dokyumi’s privacy policy; contact hello@dokyumi.com for deletion requests and retention requirements.