{"component":{"type":17,"accent_color":7742708,"components":[{"type":9,"components":[{"type":10,"content":"## [Gemma 4 26B A4B  (free)](https://openrouter.ai/google/gemma-4-26b-a4b-it:free)\ngoogle · 262K context · Free"},{"type":10,"content":"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 a fraction of the compute cost. Supports multimodal input including…"}],"accessory":{"type":2,"style":5,"label":"Open","url":"https://openrouter.ai/google/gemma-4-26b-a4b-it:free"}},{"type":14,"divider":true,"spacing":1},{"type":1,"components":[{"type":2,"style":5,"label":"Chat","url":"https://openrouter.ai/chat?models=google%2Fgemma-4-26b-a4b-it%3Afree","emoji":{"name":"💬"}},{"type":2,"style":5,"label":"Compare","url":"https://openrouter.ai/compare/google/gemma-4-26b-a4b-it:free"},{"type":2,"style":5,"label":"API","url":"https://openrouter.ai/google/gemma-4-26b-a4b-it:free/api"}]}]}}