Alibaba Cloud
qwen3-max-preview
This is the best-performing model in the Qwen series. It is ideal for complex, multi-step tasks.
Vision Support
Caching Support
Pricing
$0.86
Input tokens per million
$3.44
Output tokens per million
Caching Pricing
N/A
Cache write per million
N/A
Cache read per million
Technical Specifications
Context Window
262K tokens
Max Output Tokens
66K tokens
Global Availability
Last Updated
N/A