dataSchema-shaped output
The fields in the selected schema are returned as structured JSON.
A supported document in.
Structured JSON out.
Define the fields you need and send a supported PDF or image to one shared endpoint. Dokyumi returns structured data with confidence and validation details—no per-layout templates or cloud account required.
25 free credits/month · up to 5 pages per credit · no credit card
Documented result contract
Every produced result exposes data, confidence, and validation.errors, with a completed or review status.
The terminal is an illustrative API example, not a customer result.
schema → JSON
Dashboard · create schema: invoice
✓ vendor_name string
✓ invoice_number string
✓ total currency
✓ due_date date
$ curl … https://dokyumi.com/api/v1/extract
{
"vendor_name": "Acme Corp",
"invoice_number": "INV-2024-0847",
"total": 4632.50,
"due_date": "2024-03-31"
}
✓ completed · inspect confidence + validation▊
Schema-first
JSON shaped to your fields
One API
shared extraction endpoint
Supported files
PDF, JPEG, PNG, TIFF, WEBP
Zero infra
no AWS or GCP account needed
How it works
Other tools give you a raw text dump. Dokyumi returns schema-guided structured data with confidence and validation details.
1
Define Your Schema
Describe your document type and the fields you want to extract in plain English. Start from invoices, bank statements, tax forms, or another supported document class.
2
Call the Extraction API
Send the file and your schema slug to POST /api/v1/extract. One curl command, one API key, one shared endpoint.
3
Get Structured JSON
Upload a supported document and receive structured data with confidence and validation details. OCR caching can reduce processing work on repeat files; every extraction still consumes credits.
One API call. Structured JSON.
POST a supported document and schema slug to the shared extraction endpoint. Get back structured data with confidence and validation details in one synchronous response.
REQUESTPOST /api/v1/extract
curl -X POST \
https://dokyumi.com/api/v1/extract \
-H "Authorization: Bearer dk_live_..." \
-F "file=@invoice.pdf" \
-F "schema=invoice-parser"RESPONSE200 OK · EXAMPLE
{
"id": "6f8c2d4a-7b31-4e95-9a20-c1d7f6b84210",
"status": "completed",
"schema": "invoice-parser",
"data": {
"vendor_name": "Acme Corp",
"invoice_number": "INV-2026-0847",
"subtotal": 4250.00,
"total": 4632.50,
"line_items": [...]
},
"confidence": {
"vendor_name": 0.99,
"invoice_number": 0.99,
"total": 0.97
},
"validation": {
"valid": true,
"errors": [],
"low_confidence_fields": []
},
"meta": {
"processing_time_ms": 1843,
"page_count": 1,
"credits_used": 1,
"ocr_cached": false,
"model": "anthropic/claude-sonnet-4"
},
"request_id": "5a1d9e73-4c26-48b0-a915-7f3e2c6d8041"
}Python, Node.js, Java, Go, Ruby — if it speaks HTTP, it works with Dokyumi. See language examples →
What people are parsing
Define fields for a supported document class, then test representative layouts and review results.
Invoice Processing
Extract vendor name, invoice number, line items, totals, and due dates. Apply review and business checks before mapping into your accounting system.
→ vendor, amount, line_items[], due_date
Bank Statements
Extract transactions, balances, account numbers, and date ranges from supported PDF statements. Test representative bank layouts and route review results.
→ transactions[], opening_balance, closing_balance
Insurance Claims
Extract claim numbers, policy details, loss descriptions, and coverage amounts. Route review results to a human before downstream use.
→ claim_number, policy_id, loss_date, amount
Tax Documents
Parse W-2s, 1099s, Schedule Cs, and other supported tax documents into structured data. Review validation details before mapping into tax software.
→ wages, federal_tax_withheld, employer_ein
Medical Records
Extract diagnoses, medication lists, lab values, and provider info from clinical documents. Review the structured output before mapping it into an EHR.
→ diagnoses[], medications[], provider, date
Logistics & Shipping
Bills of lading, customs declarations, and packing lists. Extract origin, destination, cargo details, and weight, then inspect review results.
→ shipper, consignee, cargo[], weight, hs_code
Built for developers
A stable contract for a production integration.
One Stable API
Dokyumi handles document understanding, extraction, and model routing behind one endpoint, so your integration stays stable as the system improves.
Schema Validation
A model-reported confidence map and validation details identify review cases. Inspect both validation errors and low-confidence fields before downstream use.
OCR Caching
Identical documents can reuse cached OCR on repeat extractions, reducing OCR work and often improving response time. Each extraction still consumes credits.
White-Label Portals
Create branded upload portals for your customers on every plan — 1 site on Free, 5 on Starter, 25 on Growth, unlimited on Enterprise. Submissions appear in your dashboard and support webhook delivery.
How Dokyumi compares
Textract and Document AI are broader cloud document-processing platforms, while LlamaParse is oriented toward retrieval pipelines. Dokyumi is designed for structured data extraction with a schema you define.
| Feature | Dokyumi | AWS Textract | Google Doc AI | LlamaParse |
|---|---|---|---|---|
| No AWS/GCP account required | ||||
| Custom extraction schema | Partial | |||
| Schema-selected extraction API | ||||
| White-label upload portals | ||||
| OCR result caching | ||||
| Field confidence scores | ||||
| Predictable flat-rate pricing | ||||
| Free tier | 25 credits/mo | 1K pages/mo | 1K pages/mo | 10K credits/mo |
Comparison based on publicly available information as of March 2026. Pricing subject to change.
Just need one document type parsed — not a custom schema or API? See which tool fits →
What a produced result gives you
These are fields in Dokyumi's result contract, not anonymous customer claims. Inspect the same receipt in the API response and extraction dashboard.
confidenceField confidence map
Model-reported confidence stays attached to each extracted field for review.
validation.errorsValidation receipt
Schema validation issues are returned explicitly instead of being hidden behind a success claim.
Frequently asked questions
Everything you need to know before you start extracting.
What is Dokyumi?+
Dokyumi is a no-code document parsing API platform. You describe the fields you want to extract, create a schema, and select that schema when you call the shared extraction endpoint. Dokyumi returns structured data with a model-reported confidence map and validation details.
How does Dokyumi compare to AWS Textract or Google Document AI?+
AWS Textract and Google Document AI are raw OCR engines — they return raw text or key-value pairs and require you to write significant post-processing code. Dokyumi is schema-first: you define the fields you want (like vendor_name, invoice_total, due_date) and receive structured data with confidence and validation details. No AWS or GCP account is required.
What document types does Dokyumi support?+
Dokyumi supports schema-defined extraction from PDF, JPEG, PNG, TIFF, and WEBP files with repeatable fields, including invoices, bank statements, tax forms, pay stubs, claims, contracts, leases, and similar business documents. Validate each document class on representative files before automating it.
What file formats are supported?+
Dokyumi accepts PDF, JPEG, PNG, TIFF, and WEBP files up to 20MB. For best OCR results, documents should be at least 150 DPI. Both scanned documents and digital PDFs are supported.
How do I get started with Dokyumi?+
Sign up for free at dokyumi.com. You get 25 free credits per month with no credit card required; one credit covers a document up to 5 pages. Create your first extraction schema by describing your document in plain English (or use AI inference to auto-detect the schema), then send a file and the schema slug to POST /api/v1/extract.
What is the pricing?+
Dokyumi bills in extraction credits: one credit covers one document of up to 5 pages, and longer documents use one more credit per 5 pages. The free tier includes 25 credits per month. Paid plans are $99/month for Starter (500 credits, 10 schemas) and $499/month for Growth (3,000 credits, 50 schemas, white-label portals). Every self-serve plan accepts documents up to 50 pages; higher volume, longer documents, and custom-built schemas are quoted on Enterprise. There is no per-page metering and no overage billing.
What are white-label portals?+
White-label portals are branded upload interfaces you can give to your customers. Instead of exposing your API, you create a branded page where clients upload documents. Submissions appear in your dashboard and can be delivered to your system by webhook. White-label sites are available on every plan: 1 on Free, 5 on Starter, 25 on Growth, and unlimited on Enterprise.
Does Dokyumi have an API I can call from my code?+
Yes. Send a POST request to the shared /api/v1/extract endpoint with a file and schema slug. The response contains structured data, a model-reported confidence map, and validation details. See the full API documentation at dokyumi.com/docs.