# Baidu releases Unlimited-OCR under permissive MIT license

> The Chinese tech giant's multilingual vision-language model targets text extraction across languages and document types.

Published by The Open Weights on Jun 19, 2026. Canonical: https://theopenweights.com/news/unlimited-ocr-5bqq

## Key facts

- Company: Baidu
- Model: Unlimited-OCR
- Version: v1
- Category: Vision-Language
- Modalities: Vision-Language
- License: MIT (Open weights, commercial use allowed)
- Context window: 33K tokens
- Architecture: UnlimitedOCRForCausalLM
- Precision: BF16
- Weights size: 6.7 GB
- Significance: notable
- Published: 2026-06-19
- Last verified: 2026-10-25
- Hugging Face: https://huggingface.co/baidu/Unlimited-OCR
- Canonical URL: https://theopenweights.com/news/unlimited-ocr-5bqq

Baidu has published [Unlimited-OCR](https://huggingface.co/baidu/Unlimited-OCR) on Hugging Face, a multilingual vision-language model aimed at optical character recognition. The release lands under the MIT license, one of the most permissive options available, meaning developers can use, modify, and ship the model commercially with minimal restrictions.

Unlimited-OCR is built as a vision-language system rather than a traditional OCR pipeline. That approach has become increasingly common for document understanding, where models read images and produce structured or plain text while drawing on broader language reasoning to handle layout, context, and multiple scripts.

## Why it matters

OCR remains one of the most practical and widely deployed AI tasks, underpinning everything from document digitization to data entry and accessibility tools. A few points stand out about this release:

- The MIT license lowers the barrier for commercial adoption and downstream fine-tuning.
- A multilingual focus suggests the model is intended to work across scripts rather than English-only text.
- Backing from Baidu, a major player in Chinese-language AI, adds weight to the multilingual claim.

Baidu has not yet detailed parameter counts, context length, or benchmark results in the available record, so independent evaluation will be the real test of how Unlimited-OCR compares to established open OCR systems. For now, the model is available to download and try directly from its [Hugging Face repository](https://huggingface.co/baidu/Unlimited-OCR).

## Get the model

- [Hugging Face](https://huggingface.co/baidu/Unlimited-OCR)

## Sources

- [baidu/Unlimited-OCR](https://huggingface.co/baidu/Unlimited-OCR) — Hugging Face, Jun 19, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Baidu releases Unlimited-OCR under permissive MIT license", The Open Weights, Jun 19, 2026, https://theopenweights.com/news/unlimited-ocr-5bqq