ModelWatch
← Catalog

Gemma 4 26B A4B

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...

visionopen-weightslow-cost
Input price
$0.07 / 1M tokens
Output price
$0.23 / 1M tokens
Context window
262K tokens
Max output
236K tokens
Output speed
65 tokens/s
Time to first token
1.36s
Inputs
image, text, video
Open weights
Yes
OpenRouter id
google/gemma-4-26b-a4b-it
Listed
Apr 3, 2026

Benchmarks

Intelligence Index
n/a
Engineering Index
n/a

Speed and benchmarks for “Gemma 4 26B A4B (Reasoning)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others