google

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...

  • Context window: 262,144 tokens
  • Input: image, text, video
  • Output: text
  • Pricing: $0/M input tokens, $0/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.