PaddleOCR VL 0.9B
PaddleOCR-VL-0.9B is the vision-language model at the core of PaddleOCR-VL, which is designed for document parsing. It combines a dynamic-resolution visual encoder with ERNIE-4.5-0.3B to recognize document elements including text, tables, formulas, and charts across 109 languages. Summary written by AI Index from Baidu’s own pages.
Prices
1 offering · prices as listedPaddleOCR-VL-0.9B| Conditions/ page | Page |
|---|---|
| Standard | ¥0.18 |
Prices from 百度智能云千帆:模型价格 (opens in a new tab) (checked Nov 8, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Languages
- 109
- Model ID
Not stated on Baidu’s pages: input modalities, output modalities, file formats, output formats, max file size (mb), context, max output, structured output.
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers OCR models yet. We will cite one when its license allows.
Changes
All changes →- Now priced on Baidu Qianfan, China Page ¥0.18
Sources
- 百度智能云千帆:模型价格in Chinese (opens in a new tab) cloud.baidu.com · checked Nov 8, 2026
- GitHub - PaddlePaddle/PaddleOCR: Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. · GitHub (opens in a new tab) github.com · checked Nov 6, 2026
Baidu · China · cloud.baidu.com
Related models
Snapshots, the same family and other models from this provider