/ Models

Language models

Google: 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...

Maker
Google
Context window
262K
Max output
16K
Input / 1M
$0.07
Output / 1M
$0.34
1M in + 1M out
$0.41

Everything else

Max output16K
Input / 1M$0.07
Output / 1M$0.34
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.41
Takesimage, text, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2026-04-03
Knowledge cutoff
Retires
Catalog idgoogle/gemma-4-26b-a4b-it

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models