Start free
Upgrade to scale

Pay as you go
Free

1,000 free credits, then pay as you go.

Get started for free
Everything included:
  • 1,000 free credits to get started
  • OCR for scans and faxes, tables, checkboxes, handwriting OCR, and source bounding boxes
  • Schema extraction with grounded, verified citations
  • Automatic schema generation from the document
  • Playground and self-serve dashboard
  • Unlimited team seats
Afterwards: 1 credit per page for Parse, 4 credits per page for Parse + Extract, at $0.003 per credit.
Enterprise
Custom

Production processing at scale.

Talk to us
Everything in Pay as you go, plus:
  • Volume rates on committed usage
  • Customer-specific tuning for edge cases
  • Custom data-retention terms
  • Production SLAs
  • HIPAA compliance and BAA add-on
  • Priority support

Compare
Plans

Pay as you go
Get started for free
Enterprise
Talk to us
Parsing
OCR on scans, faxes, and rotated pagesIncludedIncluded
Full table structure, with row and column spansIncludedIncluded
Checkbox and selection stateIncludedIncluded
Handwriting OCRIncludedIncluded
Figures and imagesIncludedIncluded
Bounding boxes on everythingIncludedIncluded
PDF, DOCX, PPTX, and image inputIncludedIncluded
Extraction
Structured schema extractionIncludedIncluded
Automatic schema generation from the documentIncludedIncluded
Hallucination guard: values that fail grounding are nulled and flagged, not guessedIncludedIncluded
Verbatim quote verification: every citation is a real substring of the sourceIncludedIncluded
Extraction citationsIncludedIncluded
Bounding boxes on extracted valuesIncludedIncluded
Tooling
Playground: benchmark on your own documentsIncludedIncluded
Self-serve dashboard and API keysIncludedIncluded
Usage visibility and auto-rechargeIncludedIncluded
Unlimited team seatsIncludedIncluded
Commercial terms
RateParse 1 credit/page · Parse + Extract 4 credits/page ($0.003/credit)Volume rates
Rate limitsStandardRaised on request
Data retentionSync never stored · async 3-day auto-deleteCustom terms
BAANot includedIncluded
SupportEmailPriority

Common questions

If something isn't here, email hello@hanji.dev.

  • One page of the source document. Plain text, dense tables, scanned forms, OCR, handwriting, and bounding boxes are included in the same flat rate. Parse is 1 credit per page ($0.003/page). Parse + Extract is 4 credits per page ($0.012/page), with the required parsing included.
  • Extract includes parsing plus additional passes to return structured fields with grounding for each value. The rate is a fixed 4 credits per page, so it does not change based on document type, OCR needs, tables, or configuration.
  • Gemini is model infrastructure priced by tokens. Hanji is a document-processing pipeline priced in flat credits per page. It includes OCR fallbacks, table structure, retries, bounding boxes, and grounded structured output. You can review our benchmarks for accuracy and hallucination rates on real documents.
  • Yes. For Enterprise customers, we can benchmark Hanji on your real documents and downstream success metrics, then tune the workflow around the fields and edge cases that matter most.
  • Yes. If you need HIPAA support or a BAA to evaluate real documents, contact us and we can prioritize the process.
  • Yes. Higher-volume customers can receive negotiated volume pricing based on the same dollars-per-1,000-credits unit. Contact us at hello@hanji.dev.
  • The billing unit stays credits, and each operation has a fixed credit rate per page — parse is 1 credit, extract is 4. Rates are flat and published, with no automatic complexity surcharges. New capabilities may get their own rates; currently-included options like chunking, cell-level tables, and images cost nothing extra.

Show us where it breaks

Bring us the docs your pipeline struggles with. We’ll work through the edge cases and tune Hanji for your workflow.

Book a demoGet started