About this model
Turns photos and scans of documents into clean Markdown: text, tables, formulas and layout, page after page.
Official page · Weights · AI Search video at 5:48
Every size and format published by Baidu, largest first. Want one we don't host yet? Press Request: we add the most requested ones.
| Model | Parameters | Notes | |
|---|---|---|---|
| Unlimited OCR 2 | 3.3B | BF16 | Hosted here |
| Unlimited OCR (v1) | 3.3B | previous version |
Unlimited OCR 2 is an AI vision model by Baidu. Turns photos and scans of documents into clean Markdown: text, tables, formulas and layout, page after page.
Yes: every account gets one free try of this model, plus welcome credits. After that a run usually costs about 6 credits (1,000 credits = US$1), charged for the real GPU time.
Sign in, open this page, fill in the form and press the run button. It runs on our cloud GPUs: nothing to install, and it works on phones too.
License: MIT. Commercial use of the outputs is allowed by the license.
In the AI Search video at 5:48.
All models · Not affiliated with Baidu or with AI Search.