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...
Modalitäten
Text
In / out Preis
404 ₩ / 4.037 ₩
1M
Kontext
131.072
Veröffentlicht
25.07.2025
Apps
Apps, die dieses Modell am häufigsten nutzen.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 Bio. |
| Zazen (Freebuff fork) | 3,16 Bio. |
| Cline | 2,56 Bio. |
| Kilo Code | 2,44 Bio. |
| pi | 1,59 Bio. |
| OpenClaw | 1,05 Bio. |
| Codex | 938,81 Mrd. |
| DeepSeek Harness | 847,26 Mrd. |
| Portkey AI | 639,39 Mrd. |
| HighLevel | 375,1 Mrd. |
| ISEKAI ZERO | 364,56 Mrd. |
| Framer | 348,63 Mrd. |
| Hello Minds, powered by Ethoswarm | 316,97 Mrd. |
| ZCode | 279,83 Mrd. |
| Descript | 253,44 Mrd. |