Google: Gemma 4 26B A4B Multimodal

By Google

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...

OpenRouter rank

#245

0.00% share

Context window

262K tokens

Input price

$0.060 / 1M tok

Output price

$0.33 / 1M tok

Modalities

imagetextvideo

External ID

google/gemma-4-26b-a4b-it

No ranking history yet

This model is in our catalog but hasn't appeared on a tracked leaderboard yet. Trend lines appear after the next ingestion cycle (within 6 hours).

Back to all rankings