Gemma 4 26B A4B
Google · google/gemma-4-26b-a4b-it
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 weightsimagetexttext+image+video->textvideo
Context
Max context: 262144
Max output: 262144
Max output: 262144
Pricing
Input / 1M: 0.12
Output / 1M: 0.35
Blend / 1M: 0.23
Output / 1M: 0.35
Blend / 1M: 0.23
Quality
Quality index: 67.4
Provider
Provider: Google
Moderated: no
Moderated: no