Skip to content
Dokyumi logo

Dokyumi

Extracts user-defined fields from PDFs and images into schema-shaped JSON through a single extraction API endpoint.

Free plan · From $99/moActively maintained

DocumentsData extractionFree tier
dokyumi.com ↗
Open dokyumi.comAlternativesSet it up for my teamIs Dokyumi yours? Claim the card →
At a glanceswept Oct 23, 2026

not read yet

Use

For
accounts payable, lending and leasing teams with PDFs needing structured fields for downstream software
Price
Free plan · From $99/mopricing page, read Oct 24, 2026
Activity
Actively maintainedsite updated 3 days ago
Company
since 2026 · ~1 peopleper their About page
Runs as
API
Used for
  • extract totals and line items from supplier invoices
  • pull lease dates and rent periods into a register
  • pull dates and balances from bank statements for lending intake
read off dokyumi.com on Oct 24, 2026
Worth knowingcomputed from what we read · each with its source
Pricingpricing page, read Oct 24, 2026

Free plan · From $99/mo

pricing page

The companyeach fact with its source · read Oct 24, 2026
Your datawhat they publish, each line with its page · read Oct 24, 2026

“We do not use your document content to train or fine-tune AI models, ours or anyone else s.”

security page ↗

These are Dokyumi's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.

How a program reaches itfound, not claimed · read Oct 24, 2026
  • MCP servercom.dokyumi/document-extractionverified in the MCP registry
  • Stateanswers, 9 toolschecked 2026-10-24
  • Address to connectdokyumi.com/mcp
  • API docsdokyumi.com/docsthe vendor's page ↗

MCP server details →

This card as JSON, for your agent →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Documentsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare Dokyumi with

Pick up to two.

All 10 alternatives to Dokyumi →

All Documents tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Dokyumi for?

Sign in to leave a note
Questions this page answers
  • What is Dokyumi?

    Extracts user-defined fields from PDFs and images into schema-shaped JSON through a single extraction API endpoint. It is listed in the Atlas under Documents.

  • Who is Dokyumi for?

    accounts payable, lending and leasing teams with PDFs needing structured fields for downstream software

  • How much does Dokyumi cost?

    Dokyumi has a free plan; paid plans start at $99/mo, per its pricing page on 2026-10-24.

  • Is Dokyumi free?

    Yes, Dokyumi has a free plan, per its pricing page on 2026-10-24.

  • Do people use Dokyumi?

    Little sign of use.

  • Is Dokyumi still maintained?

    Actively maintained: site updated 3 days ago.

  • Does Dokyumi train AI on your data?

    No, per its security page (2026-10-24): “We do not use your document content to train or fine-tune AI models, ours or anyone else s.”

  • Is Dokyumi safe?

    We do not audit vendors. What Dokyumi publishes, read 2026-10-24: SOC 2, HIPAA, PCI DSS stated on its security page; on training with your data, “We do not use your document content to train or fine-tune AI models, ours or anyone else s.”.

  • Does Dokyumi give refunds?

    In its own words (terms of service, 2026-10-24): “All charges are final - no refunds on completed extractions.”

  • Is Dokyumi HIPAA compliant?

    Dokyumi states HIPAA compliance on its security page (2026-10-24). We have not verified it.

  • What are alternatives to Dokyumi?

    In Documents, by use: Corenexis, LlamaIndex, Nanonets, Sensible, Mindee, Invoice Data Extraction.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk