← All models View on HuggingFace →
Qwen: Qwen3 235B A22B
qwen/qwen3-235b-a22b
Tool useJSONReasoningStreaming
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...
Pricing
Input
$0.455 / 1M
Output
$1.82 / 1M
Specs
Context
131,072 tokens
Input
text
Output
text
Knowledge cutoff: 2025-03-31
Released: 2025-04
Supported parameters
include_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedtemperaturetool_choicetoolstop_p
Open weights · HuggingFace
500,568 downloads/mo
1,093 likes
apache-2.0 text-generation