by Baidu
PaddleOCR-VL is an advanced and efficient document parsing model specifically designed for element recognition within documents. Its core component, PaddleOCR-VL-0.9B, is a compact yet powerful vision-language model (VLM) composed of a NaViT-style dynamic resolution visual encoder and the ERNIE-4.5-0.3B language model, enabling precise element recognition. This model supports 109 languages and excels at recognizing complex elements such as text, tables, formulas, and charts while maintaining extremely low resource consumption. Through comprehensive evaluations on widely used public benchmarks and internal benchmarks, PaddleOCR-VL achieves state-of-the-art (SOTA) performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions, multimodal document parsing approaches, and advanced general-purpose multimodal large models, while also offering faster inference speed.
| Input | $2 / 1M tokens |
Use paddleocr-vl-0.9b via the AIHubMix unified API — one interface for every major LLM.