Qianfan-OCR
Qianfan-OCR is Baidu's 4B-parameter end-to-end document intelligence model that unifies document parsing, layout analysis and understanding in a single vision-language architecture, converting document images directly to Markdown.
text + image → text · made by Baidu
$0.067→$0.27per Mtok in / out
Baidu
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Baidu cloud | standard | $0.067per Mtok in$0.27per Mtok outcloud.baidu.com · read 2026-08-25 |
About
Qianfan-OCR — a text model from Baidu, sold by one company from $0.067 in and $0.27 out per million tokens.
It takes text and images and returns text, with a context window of 32,000 tokens. The catalogue files it under ocr and extract. Only Baidu sells it, at $0.067 in and $0.27 out per million tokens.
Every current figure
- Maker
- Baidu
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 32,000 tokens
- Licence
- not read
- Sellers
- 1
- Price
- $0.067 in and $0.27 out per million tokens — Baidu