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
Teks
Harga in / out
₩404 / ₩4.037
1M
Context
131,07 rb
Dirilis
25 Jul 2025
Apps
Aplikasi yang paling banyak menggunakan model ini.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 T |
| Zazen (Freebuff fork) | 3,16 T |
| Cline | 2,56 T |
| Kilo Code | 2,44 T |
| pi | 1,59 T |
| OpenClaw | 1,05 T |
| Codex | 938,81 M |
| DeepSeek Harness | 847,26 M |
| Portkey AI | 639,39 M |
| HighLevel | 375,1 M |
| ISEKAI ZERO | 364,56 M |
| Framer | 348,63 M |
| Hello Minds, powered by Ethoswarm | 316,97 M |
| ZCode | 279,83 M |
| Descript | 253,44 M |