← All models
Qwen: Qwen3 235B A22B Thinking 2507 logo

Qwen · Text

Qwen: 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...

Open-weightIn: TextOut: Text

Input / M

$0.45 / M

Output / M

$3.50 / M

Cache read / M

—

Context

128K

Released

Jul 25, 2025