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...
Available via OpenRouter: create a free account at openrouter.ai, generate an API key, then call this model as google/gemma-4-26b-a4b-it:free through the OpenRouter API (or any OpenRouter-compatible app/client).
Official: openrouter.ai/google/gemma-4-26b-a4b-it:free