Direct answer
What is Reducto?
Reducto is an agentic document platform that extracts, parses, splits, and edits unstructured documents using vision language models and OCR with granular bounding-box citations.
Reducto is an API-first document intelligence platform engineered to convert complex, unstructured documents into clean, LLM-ready data. At its core is the r-1 model, which unifies vision language models (VLMs) and multi-pass OCR to interpret document structures much like a human reader. It reliably reads dense financial tables, figures, scanned records, faxes, and handwriting while preserving formatting context and returning coordinates for bounding-box citations. The platform offers modular endpoints for document parsing, schema-based structured extraction, layout-aware splitting, document classification, and dynamic form editing. It supports over 30 distinct file types, including scanned PDFs, images, spreadsheets, and presentation files across more than 100 languages. In addition to hosted multi-tenant cloud endpoints, Reducto provides regional data residency endpoints in the EU and Australia, as well as private VPC and on-premises deployments for organizations operating under strict compliance obligations.
Reducto pairs multi-pass OCR with vision language models in a unified agentic model (r-1), extracting messy tables, charts, and handwritten elements alongside precise bounding-box citations without requiring manual templates.
Product capabilities
Key features
r-1 Document Parsing
Parses complex layouts, nested tables, figures, and handwritten notes into structured text while providing precise bounding-box citations.
Schema-Level Extraction
Extracts structured fields directly into predefined JSON schemas from forms, invoices, and financial disclosures.
Layout-Aware Splitting
Separates multi-document bundles and multi-page forms into logical units automatically without manual pre-processing.
Dynamic Form Editing
Fills detected checkboxes, blanks, and tables across scanned PDFs and multi-page forms without requiring predefined templates.
Broad File Support
Ingests more than 30 file formats, including PDF, TIFF, PNG, CSV, XLSX, PPTX, DOCX, and HTML.
LLM Optimization
Includes automated intelligent chunking, figure summarization, table clustering, automatic page rotation, and embedding optimization.
Enterprise Security and Deployment
Maintains SOC 2 and HIPAA compliance with support for zero data retention agreements, EU/AU residency, and private VPC or on-prem deployments.
Workflow
How Reducto works
- Upload files via the Python/Node SDK, REST API, or Reducto Studio interface across 30+ supported formats.
- Reducto processes documents using a multi-pass OCR and vision language model architecture (r-1) that evaluates visual structure, text, and tables in context.
- Receive structured JSON, layout trees, summarized figures, or bounding-box citations ready for LLM ingestion, databases, or downstream applications.
Practical fit
Who should use Reducto?
Financial Report Ingestion
Extracting balance sheets, nested tables, footnotes, and charts from SEC filings, investor decks, and financial statements.
RAG Pipeline Preparation
Chunking, summarizing figures, and generating bounding-box citations across technical documentation and policy files for LLM retrieval.
Healthcare and Legal Form Processing
Parsing scanned records, intake forms, and legal contracts under HIPAA-compliant agreements with regional data residency.
Editorial assessment
Pros and limitations
Where it is strong
- High extraction accuracy on dense tables, charts, and scanned handwritten content.
- Provides granular bounding-box citations for auditable provenance in AI pipelines.
- Generous $150 free usage credit on the Standard pay-as-you-go plan.
- Supports VPC, on-premises, and regional data residency deployments for strict compliance.
Where to be careful
- Developer-focused platform requiring code integration (Python, Node, or REST).
- Advanced enterprise protections like zero data retention and custom SLAs require contacting sales.
Commercial context
Reducto pricing
At the review date in September 2026, Reducto provides $150 in free credits (approximately 15,000 pages) on its Standard plan. Ongoing usage is metered per 1,000 pages, starting at $10 for the r-1 Parse endpoint. Growth and Enterprise plans require contacting sales. Verify current rates on the official pricing page.
| Plan | Price | What it includes |
|---|---|---|
| Standard | $0 start ($150 free usage credit) / usage-based pay-as-you-go thereafter starting at $10/1k pages for Parse API and $20/1k pages for Extract API, up to 5 Studio seats, and 200 guaranteed concurrent pages. | |
| Growth | Custom / Includes volume discounts, zero data retention, BAA for HIPAA, EU/AU data residency endpoints, priority Slack/email support, and 350 concurrent pages. | |
| Enterprise | Custom / Includes VPC and on-prem deployment, custom SLAs and MSAs, custom pipelines, dedicated on-call support, SSO/SAML, and 500+ concurrent pages. |
Pricing, limits, taxes, model access, and regional availability can change. Verify the purchase-critical details on the official pricing page linked under Sources.
Transparent ranking
Why Reducto scores 78
Each factor is scored on a 100-point scale, then combined using the public ToolsRank weights. Engagement and momentum stay at a neutral baseline until measured signals exist, so no tool can gain or lose position from numbers nobody recorded.
Compatibility
Languages, platforms, and integrations
Languages
- English
Platforms
- Web
- API
Integrations & surfaces
- Python SDK
- Node.js SDK
- REST API
- Webhooks
Community
Reviews and questions
No approved member reviews yet. Editorial factors above are the only rating on this page.
Reviews and questions come from Google-signed members and are checked by an editor before they appear.
Frequently asked
Reducto FAQ
What is the Reducto r-1 model?+
r-1 is Reducto's proprietary parsing model that combines OCR with vision language models into a unified pipeline. It is designed to capture complex tables, layouts, and formatting at an all-in rate starting at 1¢ per page ($10 per 1,000 pages).
How does Reducto pricing work?+
Reducto uses usage-based pricing per 1,000 pages across specific API endpoints. On the Standard plan, Parse costs $10/1k pages, Extract costs $20/1k pages, Deep Extract and Deep Split cost $40/1k pages, Classify costs $7.50/1k pages, and Edit costs $60/1k pages (or $15 for pre-filled pages). New Standard accounts include $150 in free credits.
What file types can Reducto process?+
The platform supports over 30 file formats, including PDF, images (PNG, JPEG, TIFF, BMP, GIF, PSD, among others), spreadsheets (CSV, XLSX, XLSM, XLS), and text or presentation files (PPTX, PPT, DOCX, DOC, TXT, HTML).
Can Reducto handle non-English languages and handwriting?+
Yes. Reducto features multilingual parsing support across more than 100 languages, handles mixed-language documents, and supports OCR on scanned documents, faxes, and handwritten notes.
Does Reducto comply with HIPAA and SOC 2?+
Yes. Reducto is SOC 2 and HIPAA compliant. Business Associate Agreements (BAAs) and Zero Data Retention Agreements are offered on the Growth and Enterprise plans.
Record history
What changed in this dossier
- Sep 8, 2026 — Documented platform capabilities, r-1 model specifications, endpoint pricing, and compliance options.