Qwen-VL OCR
Alibaba
The Qwen-VL OCR AI model by Alibaba offers developers a powerful tool for text input and vision tasks, with a large context window of 34,096 tokens and the ability to output up to 4,096 tokens. This model stands out for its multimodal capabilities and advanced reasoning, making it ideal for a wide range of applications. With competitive pricing and training data up to 2024, Qwen-VL is a top choice for developers seeking cutting-edge AI technology.
Key Specifications
Context Window
34K tokens
Max Output Tokens
4K tokens
Input Pricing
$0.72
per million tokens
Output Pricing
$0.72
per million tokens
Capabilities
- Text Generation
- Vision
Additional Details
- Provider
- Alibaba
- Release Date
- October 28, 2024
- Supported Input Types
- text, image