PaddleOCR VL
PaddleOCR VL is PaddlePaddle (Baidu)'s image to text model with a 16K context window and up to 16K output tokens, starting at $0.020 / 1M input and $0.020 / 1M output. A vision-language model from PaddlePaddle tailored for document parsing and optical character recognition across diverse document layouts.
paddlepaddle-paddleocr-vl |
| Image to Text |
| Active |
| PaddlePaddle (Baidu) |
| 16K tokens |
| 16K tokens |
| Image |
| 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·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Novita | $0.020 | $0.020 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| PaddleOCR VL | — | 16K | $0.020 | $0.020 | Current |
| PaddleOCR 0.9B VL | — | — | — | — | Available |