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...
Rank
#23
Up 21% week over week
Tokens
499.8B
2026-08-14
Requests
102.0M
102,039,837
Tool calls
-
Input / M
$0.10
Output / M
$0.34
Cache / M
$0.10
Context
262K
262,144 tokens