AGENTKERNEL
- Home
- All models
- Gemma 3 12B
Gemma 3 12B: price, performance and context
Open Gemma 3 12B by Google costs $0.05 per 1M input and $0.15 per 1M output tokens, handles up to 131.1K tokens in one request (≈ 390 pages of text) and scores 3.8 points on the AgentKernel performance index, rank 212 of 212.
Privacy: zero data retention with 2 providers, not in the EU. Availability over the last 24 h: 99.5%.
Open in the interactive comparisonKey facts
- Licence
- Open weights: free to download and self-host
- Input / 1M tokens
- $0.05
- Output / 1M tokens
- $0.15
- Context window
- 131.1K tokens
- Max. output
- 16.4K tokens
- Performance index
- 3.8 points · rank 212 of 212
- Coding index
- 5.8 points · rank 116 of 119
- Agentic index
- 0.1 points · rank 90 of 91
- Cost at your usage
- $0.088 / month
- Knowledge cutoff
- Aug 2024
- In the catalog since
- Mar 13, 2025
- Capabilities
- Vision, Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|---|---|
| Chat repliesA question with a short history, a detailed answer | $0.00 | 111,000 |
| Email draftsBullet points in, a finished email out | $0.00 | 138,000 |
| Document summariesRead 10 pages, write a one-page summary | $0.00 | 42,000 |
| Code reviewsReview and comment on 500 lines of code | $0.00 | 24,000 |
| Book analysesAnalyse a 300-page book in one go | $0.005 | 1,900 |
Cheaper with similar performance
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |
| Ling 3.0 Flash VLinclusionAI | Open | 24.6 | $0.036 |
| Ling 3.0 FlashinclusionAI | Open | 20.1 | $0.037 |
Stronger models
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ministral 3 3B 2512Mistral | Open | 4.8 | $0.125 |
| Gemma 3 4BGoogle | Open | 4.8 | $0.075 |
| Llama 3.2 1B InstructMeta | Open | 4.8 | $0.077 |