Back to all models
qwen

Qwen: Qwen3 30B A3B Thinking 2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

qwen/qwen3-30b-a3b-thinking-2507

Context Size

81.92K

Input Price

30,000 pts/M

Output Price

360,000 pts/M


Architecture

Text

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Details

TokenizerQwen3
Max Completion32,768 tokens
Provider Context81.92K tokens
ModeratedNo
CreatedAug 28, 2025