San Francisco – September 7, 2026 -- Reducto has introduced r-1, a document parsing model that processes complex files for 1 cent per page while cutting parsing errors by up to 20% compared with existing tools.
r-1 replaces multi-tool pipelines with a single model priced up to 6 times lower
Organizations handling dense tables, handwriting, scans, and non-standard layouts have typically relied on combinations of tools and post-processing layers to reach usable accuracy. Reducto says r-1 consolidates layout detection, reading order, tables, formatting, grounding, and granular citations into one model, eliminating the need to route files across multiple providers.
r-1 outperforms hyperscaler tools including Amazon Textract and Azure Document Intelligence in company evaluations
In Reducto's internal testing, r-1 beat commonly used cloud services and large language models on complex document sets while offering a complete parse at a flat rate with no additional model charges or feature-based multipliers. The model targets documents where conventional parsers fail, including watermarked files, strikethrough-heavy contracts, and low-quality scans.
Reducto plans a model family spanning cost, speed, and accuracy tiers
r-1 is the first release in a planned lineup that will include r-1 mini for latency- and cost-sensitive workloads, plus automatic routing that assigns each page to the appropriate model. r-1 is currently available in preview through a configuration flag in the Reducto Parse API.
Reducto offers up to $5,000 in migration credits to challenge rival parsers
Organizations using competing parsing tools can access up to $5,000 in credits to test r-1 against their most difficult documents, paired with benchmarking support from Reducto.