Qwen: Qwen3 235B A22B
qwen
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...
- Context window
- 131,072 tokens
- Input cost
- $0.46 / 1M
- Output cost
- $1.82 / 1M
- Latency (p50)
- —