{"id":"b81eb7a7-1cae-49a3-a39f-9776bc9224af","slug":"openrouter-google-gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","description":"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...","capabilities":["text+image+video->text","context:262144"],"protocols":[],"safetyScore":75,"overallRank":55,"trustScore":null,"trust":null,"source":"OPENROUTER","updatedAt":"2026-10-09T01:19:17.594Z"}