Gemma 4 31B
Google · Multimodal · Released Apr 2026
Gemma 4 31B is Google's 31-billion-parameter open-weight text model with a 262K token context window.
- Strengths
- As an open-weight model, it can be deployed and fine-tuned locally without API dependency, and the larger 31B parameter count provides stronger reasoning than the earlier Gemma 4 26B variant.
- Best for
- Applications requiring on-device inference, custom fine-tuning, or environments where API access is constrained or undesirable.
- Limitations
- Open-weight models typically require more infrastructure to run than API calls, and capability trails Google's proprietary Gemini models; use Gemini 3.1 Pro or Gemini 3.5 Flash for frontier performance or cost-efficient API access.
Input / 1M
$0.14
Output / 1M
$0.4
Cached input / 1M
—
Context window
262K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in increased 16.7% out increased 14.3%
- 90d
- in increased 16.7% out increased 14.3%
- 1y
- in increased 16.7% out increased 14.3%
- Since launch
- in increased 16.7% out increased 14.3%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 24 Jul 2026 | $0.14 | $0.4 | — | Imported from OpenRouter | openrouter.ai |
| 22 Jul 2026 | $0.12 | $0.35 | $0.09 | Imported from OpenRouter | openrouter.ai |
| 21 Jul 2026 | $0.12 | $0.37 | — | Imported from OpenRouter | openrouter.ai |
| 19 Jul 2026 | $0.22 | $0.55 | $0.12 | Imported from OpenRouter | openrouter.ai |
| 18 Jul 2026 | $0.12 | $0.37 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.22 | $0.55 | $0.12 | Imported from OpenRouter | openrouter.ai |
| 14 Jul 2026 | $0.06 | $0.35 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.12 | $0.35 | $0.09 | Imported from OpenRouter | openrouter.ai |