Google Gemma 3 12B
by Helicone · family gemma · listed Dec 2024V
Open Gemma instruction model for efficient chat and self-hosted deployments
Current rates USD per 1M tokens
Input$0.05
Output$0.10
Cache read—
Cache write—
Against the market
On the record
- Model id
gemma-3-12b-it- Context window
- 131K tokens
- Max output
- 8K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- Dec 2024
- Released
- 2024-12-01
- Last updated
- 2024-12-01
- Provider docs
- helicone.ai/models
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- Deep Infra$0.05 in · $0.15 out
- Kilo Gateway$0.05 in · $0.15 out
- NovitaAI$0.05 in · $0.10 out
- OpenRouter$0.05 in · $0.15 out
- Hugging Face$0.05 in · $0.15 out
- Eden AI$0.05 in · $0.15 out
- Merge Gateway$0.09 in · $0.29 out
- NanoGPT$0.272 in · $0.272 out