google
Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
For $1, you can send approximately:
~431messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.08/M = $0.000536
Output cost per message7,000 x $0.26/M = $0.001785
Total cost per message$0.002321
Messages for $1430.94
Context window
262k
tokens
Max response
236k
tokens
Input price
$0.08
per million tokens
Output price
$0.26
per million tokens
Modalities
Input:imageInput:textInput:videoOutput:text
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...