Efficient, MoE variant of Gemma 4. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.
function_callinghttps://api.deepinfra.com/v1/openai/v1/chat/completions| Provider | Input | Output | Since launch |
|---|---|---|---|
| DeepInfracheapest | $0.07 | $0.34 | — |
| OpenRouter | $0.09 | $0.3 | ↓31% |
| Novita AI | $0.13 | $0.4 | — |
| Vercel AI Gateway | $0.13 | $0.4 | — |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| gemma-4-E4B-it | 131K | — | $0.02$0.1 |
| gemma-4-26B-A4B-it | 262K | — | $0.07$0.34 |
| gemma-4-31B-it-turbo | 262K | — | $0.09$0.34 |
| gemma-4-31B-it | 262K | — | $0.13$0.38 |
| gemma-4-31B-it-Ultra | 131K | — | $0.27$0.76 |
/v1/models/deepinfra/google/gemma-4-26B-A4B-it