Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Rank
#29
Up 23% week over week
Tokens
390.7B
2026-08-14
Requests
88.4M
88,445,822
Tool calls
-
Input / M
$0.12
Output / M
$0.40
Cache / M
$0.05
Context
262K
262,144 tokens