PaddlePaddle/PaddleOCR-VL API
About
Integrate multimodal vision capabilities using PaddlePaddle/PaddleOCR-VL, designed to process both text and images seamlessly. This model delivers available completely free of charge, open weights architecture. Access PaddlePaddle/PaddleOCR-VL via the SiliconFlow (China) API with up to 16K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Structured Output
Limits
Context Window
16K
Tokens
Input Limit
16K
Tokens
Max Output
16K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
PaddlePaddle/PaddleOCR-VL by SiliconFlow (China) costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
PaddlePaddle/PaddleOCR-VL
Provider
SiliconFlow (China)Family
Release Date
Oct 16, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
SILICONFLOW_CN_API_KEY
API Base URL
https://api.siliconflow.cn/v1