Qwen: Qwen3 30B A3B Thinking 2507 reasoning

openrouter
alibaba
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...

Capabilities

Context Window 81k tokens
Max Output 32k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.20
Output $2.40
Cache Read -
Cache Write -

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Move Chat

Select a destination folder:

Move Folder

Select a parent folder:

Folder Settings