qwen
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...
Input Cost
$1.04
per 1M tokens
Output Cost
$4.16
per 1M tokens
Context Window
32,768
tokens
Developer ID: qwen/qwen-max
Related Models
qwen
$0.08/1M
Qwen: Qwen3 VL 8B Instruct
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built...
qwen
$0.46/1M
Qwen: Qwen3 235B A22B
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, acti...
qwen
$0.15/1M
Qwen: QwQ 32B
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tune...