Loading...
Loading...
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...
Input
$0.06
per 1M tokens
Output
$0.33
per 1M tokens
Blended
$0.13
per 1M tokens
Cheaper than 81% of models. Median price is $0.54/1M tokens.
Daily
$0.13
Monthly
$3.83
Context Window
262K
tokens
Larger than 63% of models
Max Output
16K
tokens
6% of context
Context Window Comparison
10.5M
1.0K
24-48 GB
A6000 / M3 Ultra
Quality Index
30.3
154th of 519
Top 30%
Coding Index
18.9
217th of 429
Top 51%
Price/1M
$0.13
126th cheapest
76% below median
Top 19%
Context Window
262K
99th largest
Top 37%