Google Gemma 4 26B A4B API prices rise 13.3% on OpenRouter

Input price increased from $0.0675 to $0.0765 per million tokens. Output price increased from $0.225 to $0.255 per million tokens. The model retains a 262,144-token context window and open weights.

According to Google, Gemma 4 models are multimodal, handling text and image input with audio supported on E2B, E4B, and 12B and generating text output. According to Google, Gemma 4 features a context window of up to 256K tokens. According to Google, Gemma 4 maintains multilingual support in over 140 languages. According to Google, Gemma 4 models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. According to Google, Gemma 4 26B A4B MoE has total parameters of 25.2B. According to Google, Gemma 4 26B A4B MoE has active parameters of 3.8B. According to Google, Gemma 4 26B A4B MoE has 30 layers. According to Google, Gemma 4 26B A4B MoE has a sliding window of 1024 tokens. According to Google, Gemma 4 26B A4B MoE has a context length of 256K tokens. According to Google, Gemma 4 26B A4B MoE has a vocabulary size of 262K. According to Google, Gemma 4 26B A4B MoE has expert count of 8 active / 128 total and 1 shared. According to Google, Gemma 4 26B A4B MoE supports Text and Image modalities.