introducing ocr in anydoc now your agents can read scanned docs for free → sub-5ms for non ocr → 190ms median per ocr page → layout detection, tables, formulas → ocr hosted option via @firecrawl → free, no api key needed

Unlimited-OCR is now on ModelScope! A 3.3B multilingual OCR model for one-shot parsing across single images, multi-page documents, and PDFs. License: MIT🚀 🤖 📄 Full-document parsing instead of cropped-region OCR 📏 32K output length for long OCR sequences 🧩 Base and gundam image modes for different document layouts ⚙️ Transformers inference + SGLang serving with OpenAI-compatible streaming requests Built to push DeepSeek-OCR-style document parsing further.

just-in-time OCR is all the rage. most pipelines parse every page before anyone asks a question. for an agent working through an ad-hoc data room, that's slow, expensive, and most of those pages never get read. the better pattern is just-in-time OCR in two passes: ✅️ LiteParse (free, OSS, Rust, 50+ formats) does a fast layout-aware first pass: spatial text, bounding boxes, headings, tables, and a per-page complexity flag. a full data room in 32 seconds. ✅️ LlamaParse zooms in on only the pages that need it, by page number, and returns cell-level tables, bounding boxes, and confidence scores. the rest fills in the background. pypdf and pdftotext can't do the first pass well. parsing everything up front can't do it cheaply. two passes gets you both. full breakdown with numbers:

We moved local ocr/pdf processing into stable release; Even though most models can figure out how to process a pdf (via bash tool), having them processed locally still significantly improve the token efficiency and save llm calls and it is proved consistently in our evals. Most importantly, ante will work even better with smaller local models 😘

Mistral Document AI (with OCR 4) and Mistral Medium 3.5 are now in Microsoft Foundry. Extract structure from documents and power apps with reasoning, coding, and agent capabilities, all within a unified platform.