Google: Gemma 4 26B A4B (free)
google/gemma-4-26b-a4b-it:free
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...
Modalities
In / Out Price
$0 / $0 per 1M
Context
262K
Released
Apr 3, 2026
Knowledge Cutoff
—
Apps using this model
Top apps by tokens routed through Reroute in the last 30 days. Apps appear here when they send an X-Title header.
No usage through Reroute yet
Once apps call this model with an X-Title header, they're ranked here by tokens.