Skip to main content

​
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.
OXR only implements the core parsing capabilities. Some advanced parameters are not available, such as cross-page merging, title level recognition, zip output, and PDF to Office. These parameters are ignored or rejected with a parameter error. See API alignment for the full comparison.

​
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.
Do not use the Free OXR API in production. We do not guarantee service stability, and requests are queued, so processing speed may vary.
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
Files over these limits are rejected. For larger or longer documents, use SoMark production (200MB, 300 pages) or self-host OXR.

​
Usage

The Free OXR API requires no authentication. Set api_key to any value, such as dummy.

​
Self-hosted OXR

You can deploy OXR with Docker on your own GPU server. Use http://<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
OXR is fully open source, and the team pays for the free API out of pocket. If it helps you, drop a ⭐ Star on GitHub. It is the best encouragement for the developers, and it keeps the free API alive longer.

Star OXR on GitHub

github.com/SoMarkAI/OXR