Context
131K
Input
$0.02/M
Output
$0.10/M
Aliases:gemma-4-e4b-itgoogle-gemma-4-e4b
Compact per-layer-embedding variant of Gemma 4 from Google DeepMind. Text-only input, text output, with toggleable reasoning.
deepinfra/gemma-4-e4bQuantbf16
- Input
- $0.02/M
- Output
- $0.10/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.10/M