Back to all models
qwen
qwenQwen: Qwen3 235B A22B
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...
qwen/qwen3-235b-a22b
Context Size
131.072K
Input Price
2,798.25 Ks/M
Output Price
11,193 Ks/M
Architecture
Text
Supported Parameters
include_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedtemperaturetool_choicetoolstop_p
Details
TokenizerQwen3
Instruct Typeqwen3
Max Completion8,192 tokens
Provider Context131.072K tokens
ModeratedNo