Qwen: Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Modalities
Text
In / out price
₩85 / ₩339
1M
Context
262.14K
Released
Jul 30, 2025
Apps
Apps that use this model the most.
| Apps | tokens |
|---|---|
| Hermes Agent | 11.32T |
| Zazen (Freebuff fork) | 3.16T |
| Cline | 2.56T |
| Kilo Code | 2.44T |
| pi | 1.59T |
| OpenClaw | 1.05T |
| Codex | 938.81B |
| DeepSeek Harness | 847.26B |
| Portkey AI | 639.39B |
| HighLevel | 375.1B |
| ISEKAI ZERO | 364.56B |
| Framer | 348.63B |
| Hello Minds, powered by Ethoswarm | 316.97B |
| ZCode | 279.83B |
| Descript | 253.44B |