← All models
Google: Gemma 4 26B A4B logo

Google · Video

Google: Gemma 4 26B A4B

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...

Open-weightIn: Image, Text, VideoOut: Text

Input / M

$0.08 / M

Output / M

$0.26 / M

Cache read / M

$0.04 / M

Context

262K

Released

Apr 3, 2026