Qwen3-Max-Thinking
This model is retiring on 2026-10-10. Please switch to: https://poe.com/Qwen3.7-Max
Qwen3-Max-Thinking is a flagship reasoning model that integrates adaptive tool use, autonomously employing search, memory, and code interpretation to address complex tasks. It further optimizes performance through test-time scaling, a strategy that allocates additional computation during inference to improve reasoning accuracy and context efficiency.
This model is served by Alibaba Cloud Int. from Singapore.
Notes:
- Context window: 256K
- Pricing is 2x when input tokens >32K, 2.5x when input tokens >128K
- Save 10% on input tokens and 8% on output tokens compared to standard API rates.
This bot supports optional parameters for additional customization.
Powered by a server managed by @empiriolabsai. Learn more
Build with Qwen3-Max-Thinking using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from EmpirioLabs AI
New
Step-3.7-Flash
New
Seedream-5.0-Pro
Seedance-2.0-Mini
Fugu-Ultra
HappyHorse-1.1
Kling-3.0-Turbo
GLM-5.2-EL
Kimi-K2.7-Code-EL
Qwen3.7-Plus
MiniMax-M3-EL