Available models
| Model ID | Parameters | Context | Best For |
|---|---|---|---|
gemma-4-31b ⭐ | 31B | 128K | Multimodal, vision |
gemma-4-26b-moe 🔥 | 26B (MoE) | 128K | Efficient inference |
gemma-3-27b | 27B | 128K | General |
gemini-3-flash 🔥 | — | 1M | Ultra-long context |
gemini-2.5-flash | — | 1M | Long context |
Recommendation
Usegemma-4-31b for multimodal tasks. Use Gemini models when you need 1M+ token context windows.