Google: Gemma 3 4B API Pricing

by google · 131K context window · #12 cheapest paid

$0.0400
Input /1M tokens
$0.0800
Output /1M tokens
131K
Context window

Explore Google's Gemma 3 4B API pricing for your large language model (LLM) projects. Understand the cost structure with rates of $0.04000 per 1 million input tokens and $0.08000 per 1 million output tokens, totaling $0.1200 per 1M tokens. Gemma 3 4B boasts a context window of 131,072 tokens, enabling more comprehensive processing. For example, a project processing 100 million tokens monthly would cost approximately $12.00. Compare Gemma 3 4B's pricing with other LLM APIs to optimize your machine learning budget and make informed decisions for your development needs.

Monthly Cost Examples

Assuming 50% input / 50% output token split

UsageMonthly cost
100K tokens/month<$0.01
1M tokens/month$0.06
10M tokens/month$0.60
100M tokens/month$6.00

Compare with other models

Google: Gemma 3 4B vs OpenAI: GPT-4o →Google: Gemma 3 4B vs OpenAI: GPT-4o-mini →Google: Gemma 3 4B vs OpenAI: o1 →

Automate your model selection

StormRouter sends each request to the cheapest model that can handle it.
Only use Google: Gemma 3 4B when your quality requirements demand it.

Try StormRouter free →

Similar models

Free Models RouterFree/1MStepFun: Step 3.5 Flash (free)Free/1MArcee AI: Trinity Large Preview (free)Free/1MUpstage: Solar Pro 3 (free)Free/1MLiquidAI: LFM2.5-1.2B-Thinking (free)Free/1MLiquidAI: LFM2.5-1.2B-Instruct (free)Free/1M