Google: Gemma 4 31B
google/gemma-4-31b-it
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Modalities
ImageTextVideo
Giá In / out
158 ₩ / 597 ₩
1M
Context
262,14 N
Ngày phát hành
3 thg 4, 2026
Apps
Các ứng dụng sử dụng model này nhiều nhất.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 NT |
| Zazen (Freebuff fork) | 3,16 NT |
| Cline | 2,56 NT |
| Kilo Code | 2,44 NT |
| pi | 1,59 NT |
| OpenClaw | 1,05 NT |
| Codex | 938,81 T |
| DeepSeek Harness | 847,26 T |
| Portkey AI | 639,39 T |
| HighLevel | 375,1 T |
| ISEKAI ZERO | 364,56 T |
| Framer | 348,63 T |
| Hello Minds, powered by Ethoswarm | 316,97 T |
| ZCode | 279,83 T |
| Descript | 253,44 T |