Handles many input formats (PDF, images, DOCX, PPTX, XLSX, HTML, EPUB) and outputs Markdown, JSON, HTML, or chunks sized for RAG
Preserves structure: tables, equations as LaTeX, code blocks, reading order, and image extraction, with headers/footers removed
Selective OCR keeps it fast by only invoking the vision model on bad or scanned pages, with a CPU-only no-OCR path available
Optional --use_llm hybrid mode works with Gemini, Claude, OpenAI-compatible, Azure, Vertex, OpenRouter, or local Ollama models
Apache-2.0 code with CLI, Python API, batch processing, and a simple API server
Very fast and simple to use with almost no learning curve
Answers include citations back to source pages
Generous free tier for light usage
Supports many formats beyond PDF, including Word, PPTX, and ePub
Multi-file folders let you query several documents together
Cons
Model weights are not freely commercial: a modified OpenRAIL-M license caps free use at under $5M funding/revenue and requires paid licensing above that
Best accuracy needs a GPU plus a local inference server (vLLM via Docker, or llama.cpp on CPU/Apple Silicon), adding setup
Very complex layouts with nested tables and forms may still convert poorly
The built-in API server is explicitly basic and not intended for large-scale production use
No real team collaboration or shared workspaces
No self-hosting for sensitive or regulated data
Limited enterprise controls and admin features
Answer quality can degrade on very large or messy scans
Pricing has been reported inconsistently across sources
Comparison generated from each tool's listing. Add or remove tools above to change it.
