Surya

Surya is a 650M parameter OCR model for document intelligence. It turns document images into text and structured page data, including detected text, bounding boxes, and page-level OCR results.

It adds layout analysis for tables, images, headers, and reading order, plus table recognition for rows and columns. It also includes smaller models for line-level text detection and OCR error detection, and runs inference through a vLLM backend on NVIDIA GPUs or llama.cpp on CPU and Apple Silicon.

Datalab ships a managed platform that runs Surya and Chandra, alongside a public playground and commercial model licensing. The code is licensed under Apache 2.0, while the model weights use a modified AI Pubs Open Rail-M license. The project can be run locally from source, and the managed platform is an optional hosted service.