What is OXR
OXR (Optical Everything Recognition) is SoMark’s open-source, state-of-the-art document parsing model with 1.3B parameters. It parses PDFs and document images into agent-friendly data (Markdown / JSON) and returns layout analysis results.OXR on GitHub
Source code, Docker deployment, and model downloads
Online demo
Upload a document and see the parsing result, no sign-up needed
Relationship with SoMark
SoMark is a commercial document intelligence service. OXR is the open-source parsing model and service from the SoMark team. They share the same API conventions, so the SoMark ecosystem works with OXR services:- A self-hosted OXR and the Free OXR API both work with the official SoMark CLI & SDK (
somark-py,somark-js). Just replace the Base URL. - Paths, parameter names, and response structure match the SoMark API.
Free API
OXR provides a free API so you can test parsing on your own documents without registering or requesting an API key. We will keep it online until we can no longer afford to run it.somark.cn mirrors somark.ai. Pick whichever fits your region.Upload limits
File size
Up to 10MB per file
Page count
Up to 20 pages per request
Usage
The Free OXR API requires no authentication. Setapi_key to any value, such as dummy.
Self-hosted OXR
You can deploy OXR with Docker on your own GPU server. Usehttp://<host>:8000/v1 as the Base URL. The 10MB / 20-page limits do not apply. See the OXR repository for deployment steps.
API alignment
See the parameter-by-parameter comparison between OXR and SoMark
Star OXR on GitHub ⭐
Star OXR on GitHub
github.com/SoMarkAI/OXR


