ToolsSeptember 8, 2026via MarkTechPost

Reducto Releases r-1: A Single Pass Document Parsing Model That Cuts Errors 20% at 1 Cent Per Page

Why it matters

A single-pass document parsing model that consolidates OCR, layout, tables, and formatting into one inference step, with meaningful cost and accuracy gains. Practitioners using document AI should evaluate whether the 20% error reduction and 3-6x cost cut justify switching from their current pipeline.

Key signals

  • r-1 released September 1, 2026
  • 20% error reduction reported
  • Pricing: 1 cent per page (vs. legacy 3-6 cents per page)
  • Consolidates OCR, layout detection, tables, formatting, and grounding into single pass
  • Replaces multi-stage agentic pipeline
  • Cost reduction: 66-83% cheaper than prior approach
  • Release date: September 1, 2026
  • 20% error reduction vs. prior version
  • Pricing: $0.01 per page (flat rate)
  • Legacy pricing: $0.03–$0.06 per page
  • Cost savings: 66–75% reduction
  • Single-pass architecture: replaces multi-stage agentic pipeline
  • Unified capability: OCR, layout detection, tables, formatting, grounding in one model

The hook

1 cent per page. Reducto's r-1 cuts document parsing errors 20% and costs 66-83% less than the multi-stage pipeline it replaces.

We look at r-1, the document parsing model Reducto released on September 1, 2026. We walk through how it folds OCR, layout detection, tables, formatting and grounding into one full page pass, replacing the multi stage agentic pipeline it ships alongside. We break down the two numbers that matter for

The week's key stories, every Friday.

For practitioners and enthusiasts — free, in your inbox.

Free forever. No spam.