Qwen: Qwen3 235B A22B reasoning
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...
Capabilities
Context Window 131k tokens
Max Output 8k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.45
Output $1.82
Cache Read -
Cache Write -
Supported Parameters
include_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedtemperaturetool_choicetoolstop_p