Home › Providers › google › Google: Gemma 3 4B

Google: Gemma 3 4B API Pricing

Google: Gemma 3 4B is an API model from google. It costs $0.04 per 1M input tokens and $0.05 per 1M output tokens, with cached input at $0.02. Its context window is 131,072 tokens with up to 117,964 output tokens. A workload of 10M input + 2M output tokens costs about $0.5 per month.
Input
$0.04
per 1M tokens
Output
$0.05
per 1M tokens
Cached input
$0.02
per 1M tokens
Context window
131K
131,072 tokens
Blended (80/20)
$0.042
per 1M tokens

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

How much does Google: Gemma 3 4B cost for a real workload?

At 10M input + 2M output tokens per month, Google: Gemma 3 4B costs about $0.5 ($0.4 input + $0.1 output). Try your own volumes in the cost calculator.

What are cheaper alternatives to Google: Gemma 3 4B?

Compare Google: Gemma 3 4B with other models

Google: Gemma 3 4B vs Google: Gemma 4 26B A4B (free)Google: Gemma 3 4B vs Google: Gemma 4 31B (free)Google: Gemma 3 4B vs Google: Lyria 3 Pro PreviewGoogle: Gemma 3 4B vs Google: Lyria 3 Clip PreviewGoogle: Gemma 3 4B vs Google: Gemma 3 12BGoogle: Gemma 3 4B vs Google: Gemini 2.5 Flash Lite (batch)

Frequently asked questions

How much does Google: Gemma 3 4B cost?

Google: Gemma 3 4B costs $0.04 per 1M input tokens and $0.05 per 1M output tokens (list price, snapshot October 21, 2026). At 10M input + 2M output tokens per month that is about $0.5.

What is the context window of Google: Gemma 3 4B?

Google: Gemma 3 4B has a context window of 131,072 tokens and can return up to 117,964 output tokens per response.

What are cheaper alternatives to Google: Gemma 3 4B?

Cheaper models include inclusionAI: Ling 3.0 Flash ($0.021 in / $0.063 out), Mistral: Mistral Nemo ($0.029 in / $0.03 out), ScaleDown: Summarize ($0.04 in / Free out). See the full list on this page.

Is Google: Gemma 3 4B free to use?

No. Google: Gemma 3 4B is a paid model at $0.04 input / $0.05 output per 1M tokens. 20 free models are listed on the free models page.

Provider: google · Model ID: google/gemma-3-4b-it · Modality: text+image->text · Price snapshot October 21, 2026, refreshed daily. How we collect prices