Qwen

Qwen-Max

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.

Input / 1M tokens

$1.04

Output / 1M tokens

$4.16

Context window

33K tokens

Provider

Qwen

Cached input / 1M

$0.208

Knowledge cutoff

2025-03-31