Open-weight 0.9B vision-language model for multilingual document parsing, built on ERNIE-4.5-0.3B.
Released
Oct 16, 2025
Context window
Not disclosed
Max output
Not disclosed
Parameters
0.9B
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- Baidu
- Model type
- Multimodal
- Architecture
- Dense
- Parameters
- 0.9B
- Input
- Text Image
- Output
- Text
- Knowledge cutoff
- Not disclosed
- License
- Apache License 2.0
- API access
- No first-party API
- Capabilities
- Small LM Vision