Gemma 3 4B
Google · Multimodal · Released Mar 2025
Gemma 3 4B is Google's 4-billion-parameter open-weight text model with a 131K token context window.
- Strengths
- Small model size enables fast inference and low memory requirements while supporting longer context windows than earlier lightweight alternatives.
- Best for
- Lightweight deployments and edge inference where speed and resource efficiency matter more than raw reasoning capacity.
- Limitations
- At 4 billion parameters, it handles less complex reasoning and language tasks than larger models like Gemma 3 12B or Gemma 3 27B, and cannot match the capabilities of Google's frontier Gemini models.
Input / 1M
$0.05
Output / 1M
$0.1
Cached input / 1M
—
Context window
131K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.05 | $0.1 | — | Imported from OpenRouter | openrouter.ai |