PaddleOCR VL 1.6
PaddleOCR VL 1.6 is PaddlePaddle (Baidu)'s language model. A compact ~0.9B vision-language model optimized for document parsing tasks such as OCR, tables, formulas, charts, and seals, with a 131K context window and strong benchmark performance on OmniDocBench.
| Specifications | |
|---|---|
paddlepaddle-paddleocr-1-6-vl | |
| Language | |
| Active | |
| PaddlePaddle (Baidu) | |
| Text | |
| Text | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·