All Models

PaddleOCR VL

AttachmentsOpen Weights

Multimodal model for analyzing text, images, documents, and rich media

Providers1
ReleasedOct 22, 2025
Input Modalitiestext, image
Output Modalitiestext

Available Providers (1)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
NovitaAIpaddlepaddle/paddleocr-vl$0.02/MTok$0.02/MTok16.4K16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output