Google Gemma 4 26B A4B API price cut 11.8% on OpenRouter
Por ahora esta nota solo está disponible en inglés.
Google's Gemma 4 26B A4B model saw an 11.8% price reduction on OpenRouter effective October 31, 2026, lowering input costs to $0.0675 per million tokens and output costs to $0.225 per million tokens.
Precio en OpenRouter, por 1M de tokens
- 0,08 US$
- 0,10 US$
Price change details
The input price fell from $0.0765 to $0.0675 per million tokens, while the output price dropped from $0.255 to $0.225 per million tokens, according to OpenRouter data comparing October 31 to October 30, 2026. Both input and output prices decreased by 11.8%.
Model specifications
According to Google, Gemma 4 26B A4B is a mixture-of-experts model with 25.2B total parameters and 3.8B active parameters, featuring 8 active experts, 128 total experts, and 1 shared expert. The model supports a context window of up to 256K tokens and handles text and image input. It is licensed under Apache 2.0 and compatible with the latest Transformers version. The pre-training dataset has a cutoff date of January 2025.
Puntos clave
- Gemma 4 26B A4B API costs decreased 11.8% for both input and output tokens on OpenRouter.
- The model is a 25.2B parameter MoE with 3.8B active parameters and 256K context window.
- Google lists the model as multimodal with Apache 2.0 licensing and Transformers compatibility.