Qwen-Max, based on Qwen2.5, provides the best inference performance among Qwen models, especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion tokens and further post-trained with curated Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) methodologies. The parameter count is unknown.
Recent activity on Qwen-Max
Total usage per day on OpenRouter
Prompt
267K
Completion
54K
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.