qwen
Qwen: Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
For $1, you can send approximately:
~34.8messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.50/M = $0.003500
Output cost per message7,000 x $3.60/M = $0.025200
Total cost per message$0.028700
Messages for $134.84
Context window
262k
tokens
Max response
236k
tokens
Input price
$0.50
per million tokens
Output price
$3.60
per million tokens
Modalities
Input:textInput:imageInput:videoOutput:text
Description
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...