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...
Rank
#101
Up 88% week over week
Tokens
27.6B
2026-08-14
Requests
2.4M
2,447,001
Tool calls
-
Input / M
$0.39
Output / M
$2.34
Cache / M
Free
Context
262K
262,144 tokens