# Unlimited-OCR-2 parses entire multi-page documents in one request

> Original title: Introducing Unlimited-OCR-2, built to parse entire documents in one request instead of page by page.

- Source: ModelScope
- Published: 2026-10-27T12:00:45.000Z
- Bad Influence: https://badinfluence.news/items/dl9k6emssnqx2kjdp1959bfhh
- Original: https://x.com/ModelScope2022/status/2115051070384734675

## Summary

PaddlePaddle's Unlimited-OCR-2 parses every page of a document in a single request, preserving cross-page context instead of treating pages as isolated images. The model reaches state-of-the-art results on MPDocBench and the hundred-page MarathonDocBench, and its Sparse Reference Sliding Window Attention keeps per-step decoding latency and memory nearly constant as documents grow. It supports native Transformers and SGLang serving under an MIT license.

## Post

Introducing Unlimited-OCR-2, built to parse entire documents in one request instead of page by page.
🤖 https://modelscope.ai/models/PaddlePaddle/Unlimited-OCR-2

🏆 SOTA for ultra-long documents: Reaches state-of-the-art results on both MPDocBench and the hundred-page MarathonDocBench.
📚 Parse across pages: Processes every page in one request, preserving cross-page context instead of treating pages as isolated images.
⚡ Built to scale: Sparse Reference Sliding Window Attention keeps per-step decoding latency and memory footprint nearly constant as documents grow.
🛠️ Ready to deploy: Supports native Transformers for quick tests and SGLang for serving.  
📜 MIT License.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVorvCPWIAAXAqc.jpg&mode=thumb&exp=1793404800&sig=4181a1b9d9d8995f)