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...
Modalidades
Texto
Preço in / out
₩ 404 / ₩ 4.037
1M
Contexto
131,07 mil
Lançado
25 de jul. de 2025
Apps
Apps que mais utilizam este modelo.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 tri |
| Zazen (Freebuff fork) | 3,16 tri |
| Cline | 2,56 tri |
| Kilo Code | 2,44 tri |
| pi | 1,59 tri |
| OpenClaw | 1,05 tri |
| Codex | 938,81 bi |
| DeepSeek Harness | 847,26 bi |
| Portkey AI | 639,39 bi |
| HighLevel | 375,1 bi |
| ISEKAI ZERO | 364,56 bi |
| Framer | 348,63 bi |
| Hello Minds, powered by Ethoswarm | 316,97 bi |
| ZCode | 279,83 bi |
| Descript | 253,44 bi |