Gemma 3 27B
Google · Multimodal · Released Mar 2025
Google's 27-billion-parameter open-weight text model with a 110K token context window.
- Strengths
- Offers a larger parameter count than the Gemma 3 12B while remaining lightweight and open-weight, suitable for running on consumer hardware with strong inference performance.
- Best for
- Self-hosted deployments and on-device inference where you need solid reasoning and language understanding without moving to proprietary APIs.
- Limitations
- Smaller context window than Gemma 4 31B, which supersedes it as the next step in the open-weight lineup, and lacks the capabilities of Google's proprietary Gemini models.
Input / 1M
$0.08
Output / 1M
$0.45
Cached input / 1M
$0.04
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out increased 181.3%
- 90d
- in decreased 0.0% out increased 181.3%
- 1y
- in decreased 0.0% out increased 181.3%
- Since launch
- in decreased 0.0% out increased 181.3%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 23 Jul 2026 | $0.08 | $0.45 | $0.04 | Imported from OpenRouter | openrouter.ai |
| 17 Jul 2026 | $0.1 | $0.3 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.08 | $0.45 | $0.04 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.08 | $0.16 | — | Imported from OpenRouter | openrouter.ai |