Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), 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.
by Qwen|33K context|$1.60/M input tokens|$6.40/M output tokens
Endpoints
Available providers for this model, with details on pricing, context limits, and real-time health metrics.