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...
모달리티
텍스트
입력 / 출력 단가
₩404 / ₩4,037
1M
컨텍스트
13.11만
출시
2025. 7. 25.
앱
이 모델을 많이 쓰는 앱입니다.
| 앱 | 토큰 |
|---|---|
| Hermes Agent | 11.32조 |
| Zazen (Freebuff fork) | 3.16조 |
| Cline | 2.56조 |
| Kilo Code | 2.44조 |
| pi | 1.59조 |
| OpenClaw | 1.05조 |
| Codex | 9388.13억 |
| DeepSeek Harness | 8472.56억 |
| Portkey AI | 6393.89억 |
| HighLevel | 3750.96억 |
| ISEKAI ZERO | 3645.62억 |
| Framer | 3486.32억 |
| Hello Minds, powered by Ethoswarm | 3169.7억 |
| ZCode | 2798.32억 |
| Descript | 2534.44억 |