Google · OpenRouter
Gemma 4 26B A4B (free) pricing
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...
OpenRouterOpenRouter API
This is OpenRouter route pricing from the public models API, not a claim about the creator's direct API price.
Tool useVisionVideo inputReasoningHugging Face
2,000 input + 500 output tokens$0 / request
Calculate a complete workload →