← All models View on HuggingFace →
Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
Tool useJSONReasoningStreaming
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Pricing
Input
$0.1 / 1M
Output
$0.1 / 1M
Specs
Context
262,144 tokens
Input
text
Output
text
Knowledge cutoff: 2025-06-30
Released: 2025-07
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
47,142 downloads/mo
405 likes
apache-2.0 text-generation