← All models View on HuggingFace →
Qwen: Qwen3 30B A3B Thinking 2507
qwen/qwen3-30b-a3b-thinking-2507
Tool useJSONReasoningStreaming
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...
Pricing
Input
$0.08 / 1M
Output
$0.4 / 1M
Specs
Context
131,072 tokens
Input
text
Output
text
Knowledge cutoff: 2025-06-30
Released: 2025-08
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
130,385 downloads/mo
378 likes
apache-2.0 text-generation