Compare
gemma-4-26b-a4b-it
Comparing 1 model
| Gemma 4 26B A4B | |
|---|---|
| Overview | |
| Status | Active |
| Released | 4/3/2026 |
| Summary | 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... |
| Pricing (per 1M tokens) | |
| Input | $0.08/1M |
| Output | $0.35/1M |
| Context and limits | |
| Context window | 262K |
| Max output | — |
| Modalities | |
| Supported | image, text, video |
| Capabilities | |
| Tool calling | No |
| Structured outputs | No |
| Open source | No |
| License | — |