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...
Everything else
| Max output | 16K |
|---|---|
| Input / 1M | $0.07 |
| Output / 1M | $0.34 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $0.41 |
| Takes | image, text, video |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2026-04-03 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | google/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.