Qwen: Qwen3 235B A22B Thinking 2507

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...

Modalities
Text
In / out price
₩404 / ₩4,037
1M
Context
131.07K
Released
Jul 25, 2025

Pricing

Prices are quoted in Korean won. Changes to the exchange rate or margin show up immediately.

Input (prompt)₩404 / 1M
Output (completion)₩4,037 / 1M
Cache read₩40 / 1M
Cache write

1,000 input tokens plus 1,000 output tokens costs about ₩4.44.