Customers

Pricing
Introducing r-1: Reducto’s new SOTA document parsing model
Parse

A new frontier for document parsing

Convert any document into structured, LLM-ready JSON. Accurately parse simple and complex pages with r-1, our new unified model, in one simple call.

Try the API freeRequest a demo

Helping everyone from startups to Fortune 10 enterprises unlock their data.

  • Harvey
  • Scale AI
  • Newfront
  • Medallion
  • Vanta
  • Legora
  • Rogo
  • Levelpath
  • JLL
  • Vise
  • Laurel
  • Toast
  • Mercor
  • Zip
  • Anterior
  • Supio
  • EliseAI
  • Unify
Parse API

Turn any document into structured data

Definition
The Parse API converts any document into structured JSON in a single call. Powered by r-1, it handles OCR, layout detection, table reconstruction, figure summarization, and semantic chunking together. Every block returns with its type, page position, and confidence score.
Who it's for
Engineers building RAG systems, AI agents, or knowledge bases that need to ingest real-world documents without building brittle templates.
The problem it solves
With r-1, Parse handles the complex documents that typically break simpler parsers: dense tables, unusual layouts, formatting-dependent information, long documents, and heterogeneous files that don’t conform to a predictable template.
The agentic document platform

Document work starts here

/parse

Parse

Turn any document into structured, citation-ready output with r-1. Tables, figures, OCR.

You are here
/extract

Extract

Pull defined fields and schemas out of documents with citations on every value.

Read more/split

Split

Break long, multi-document files into logical units for downstream pipelines.

Read more/classify

Classify

Route or label files by document type before they hit a downstream pipeline, with per-criterion confidence.

Read more/edit

Edit

Fill PDF forms or update DOCX files with natural-language instructions via the Edit API.

Read more/studio

Studio

Your visual workbench for document work. Prototype pipelines, tune configurations, deploy by Pipeline ID.

Read more

Try out Parse in Studio or via the API.

Open StudioRequest a demo
Where AI teams use the Parse API

RAG, agents, and search start here

Turn any document into structured data your pipeline can use.

RAG over enterprise documents

Chunks split at section, table, and figure boundaries, so retrieval returns complete units of meaning instead of cut-off fragments.

Document AI agents

Give an agent a structured view of any uploaded file with bounding boxes and confidence scores.

Tables, spreadsheets, and forms

Reconstructs merged cells, nested headers, and multi-page tables. Output in HTML, Markdown, JSON, or CSV.

Scans, faxes, and photographs

r-1 handles handwriting, faded scans, unusual fonts, and photographed pages that break traditional OCR.

Charts and figure extraction

Figures are summarized in natural language, with optional structured data extraction for analytics.

Knowledge bases & search

Every element returns with its position on the page, so search products can link results back to the exact paragraph, row, or figure in the source document.

Try out Parse in Studio or via the API.

Open StudioRequest a demo
Why Parse

Why teams switch to Parse

  1. 01

    Preserves the original layout

    Multi-column layouts, headers, footnotes, sidebars, and multi-page tables. Reading order stays intact.

  2. 02

    Citation-grounded output

    Every block includes a bounding box and confidence score. Trace any output back to its exact location.

  3. 03

    One model for simple and complex pages

    r-1 handles handwriting, faded scans, unusual fonts, and misaligned columns in the same unified parsing model.

  4. 04

    Table fidelity that holds up

    Merged cells, nested headers, multi-page tables reconstruct in HTML, Markdown, JSON, or CSV.

  5. 05

    Sync and async, your call

    Sync for low-latency calls, async with webhooks for batch jobs. Files up to 5GB via presigned URL. Reuse results with jobid:// to skip re-processing.

How Parse works

How Parse works in four steps

  1. STEP 01

    Send a file

    Upload via /upload or pass a public or presigned URL directly. Supports PDFs, images, Office documents, and spreadsheets.

    POST /parse
  2. STEP 02

    We read the page

    r-1 recognizes titles, paragraphs, tables, figures, headers, and footers together.

    r-1 unified model
  3. STEP 03

    We reconstruct structure

    Tables, merged cells, and figures rebuild faithfully—even on complex pages.

    tables · figures · text
  4. STEP 04

    You get JSON back

    Chunks with typed blocks and bounding boxes, optimized for RAG and LLM workflows.

    chunks[].blocks[].bbox
Read the full Parse reference in the docs
Built for production

1B+ pages processed monthly

  • SOC 2 Type II
  • HIPAA
  • Zero Data Retention
  • VPC · On-prem · Air-gapped
  • EU · AU regional endpoints
  • 99.9%+ uptime SLA
  • Enterprise support
Visit the Trust Center

Try out Parse in Studio or via the API.

Open StudioRequest a demo
Further reading

Go deeper on document parsing

  • GuidePDF Parser

    A practical guide to turning PDFs into reliable, structured data for downstream AI workflows.

  • BenchmarkSOTA Table Parsing

    See how modern document parsers perform on the tables that matter most in production.

  • GuideParsing Unstructured Files

    Learn how to build a resilient ingestion layer for unstructured files and mixed document sets.

FAQ

Common questions about Parse

Document work starts here

Run Parse on your hardest document

Drop a PDF in Studio, or hit the API with a single call. No setup, no credit card.

Try the API freeRequest a demo
Reducto logoLLM Center