Reducto Launches r-1 Doc Parser: Beats LVMs, 6x Cheaper than OCR
Scobleizer · x · 2026-09-02
Reducto AI announced r-1, a new document parsing model designed for complex visual layouts and multi-page tables.
- Performance: 20% lower error rate compared to their most powerful agentic OCR models.
- Cost: Up to 6x cheaper than basic OCR (e.g., Azure Doc Intelligence) even at list price.
- Basis: Built on two years of experience handling hard-to-parse formats like strikethroughs and spanning tables.
The model is currently in early preview and will improve over the coming weeks.
Related event: Reducto Launches r-1 Document Parsing Model with 20% Fewer Errors(2 posts)→
More from Models
- Hands-on review: Claude Fable 5.1 matches Opus at lower cost with prompt cache savings — every · 2026-09-02
- Anthropic Fable 5.1 System Prompt Leaked, Spanning 270k+ Characters — Scobleizer · 2026-09-02
- Security model Mythos achieves record 69% recall in defensive benchmark — jfiance · 2026-09-02
- Fable 5.1 now integrates Anthropic's statistical text watermarking — RaGE_Syria · 2026-09-02
- Multi-agent evals lack model comparisons, need more details — scaling01 · 2026-09-02
- Review: Anthropic Fable 5.1 Is Back as the Strongest Coding Model Yet — danshipper · 2026-09-02