Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...
Rank
#215
Down 3% week over week
Tokens
1.7B
2026-08-14
Requests
408.9K
408,877
Tool calls
-
Input / M
$0.45
Output / M
$1.82
Cache / M
Free
Context
131K
131,072 tokens