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
GambarTeksVideo
Harga in / out
₩158 / ₩597
1M
Context
262,14 rb
Dirilis
3 Apr 2026

Apps

Aplikasi yang paling banyak menggunakan model ini.

Appstokens
Hermes Agent11,32 T
Zazen (Freebuff fork)3,16 T
Cline2,56 T
Kilo Code2,44 T
pi1,59 T
OpenClaw1,05 T
Codex938,81 M
DeepSeek Harness847,26 M
Portkey AI639,39 M
HighLevel375,1 M
ISEKAI ZERO364,56 M
Framer348,63 M
Hello Minds, powered by Ethoswarm316,97 M
ZCode279,83 M
Descript253,44 M