baiduCatalog Onlyfree endpoint
paddleocr
baidu/paddleocr
Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.
Context Length
Not published
Input Pricing
Not published
Output Pricing
Not published
Recent Latency
No probes
Model Architecture & Limits
Canonical IDbaidu/paddleocr
Publisher / Originatorbaidu
Model FamilyNot published
ArchitectureConvolutional Neural Network (CNN)
Context Window LimitNot published
Max Output TokensNot published
Endpoint Protocolnim-custom
Capabilities & Modal Surfaces
Chat Conversation✕ No
Tool / Function Calling✕ No
Reasoning / Thinking✕ No
Structured Output (JSON)✕ No
Vision / Multimodal✓ Yes
Audio Processing✓ Yes
License & Restrictions
NVIDIA API Trial Terms of Service
Commercial and research use permitted under governing model and API terms.