Qwen Turbo
Alibaba Cloud
🧠 Language Model
Fast hybrid model with thinking mode. 1M context in non-thinking mode, ideal for real-time applications.
⏹ Retired on 2026-05-13
Specifications
Input modalitiestext
Output modalitiestext
Capabilitiestools, reasoning
Relative speed●●●●● Blazing
Deprecated on2026-04-16
Sunset on2026-05-13
Context window1,000,000 tokens
Max output8,192 tokens
Tool callingYes
Input price$0.0875 / 1M
Output price$0.35 / 1M
Pricing
$0.0875 / 1M input tokens · $0.35 / 1M output tokens
Platform credit pricing — live rates on the Models page.