Back to all models
qwen
qwenQwen: Qwen3 235B A22B Thinking 2507
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...
qwen/qwen3-235b-a22b-thinking-2507
Context Size
128K
Input Price
67,500 pts/M4,151 Ks/M
Output Price
525,000 pts/M32,287 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningstoptemperaturetool_choicetoolstop_ktop_p
Details
TokenizerQwen3
Instruct Typeqwen3
Max Completion16,384 tokens
Provider Context128K tokens
ModeratedNo
CreatedJul 25, 2025