Google: Gemma 3 12B API Pricing
by google · 131K context window · #20 cheapest paid
Explore the Google Gemma 3 12B API pricing for your large language model (LLM) projects. This page details the cost structure, including input pricing at $0.04000 per 1 million tokens and output pricing at $0.13000 per 1 million tokens, resulting in an effective cost of $0.1700 per 1 million tokens. With a context window of 131,072 tokens, Gemma 3 12B allows for substantial input processing. For example, processing 10 million tokens of input and generating 5 million tokens of output would cost approximately $1.05. Ideal for ML engineers comparing LLM APIs, this resource offers a clear understanding of Google's pricing for Gemma 3 12B.
Monthly Cost Examples
Assuming 50% input / 50% output token split
| Usage | Monthly cost |
|---|---|
| 100K tokens/month | <$0.01 |
| 1M tokens/month | $0.09 |
| 10M tokens/month | $0.85 |
| 100M tokens/month | $8.50 |
Compare with other models
Google: Gemma 3 12B vs OpenAI: GPT-4o →Google: Gemma 3 12B vs OpenAI: GPT-4o-mini →Google: Gemma 3 12B vs OpenAI: o1 →Automate your model selection
StormRouter sends each request to the cheapest model that can handle it.
Only use Google: Gemma 3 12B when your quality requirements demand it.