Google

GGemma 3 12BOPEN

Gemma 3 12B (Google): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.

Context window
131K
tokens
Input price
$0.05
per M tokens
Output price
$0.15
per M tokens
Provider
Google

Prices update automatically — checked hourly against provider list prices.

See model comparisons → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Gemma 3 12B, measured by Artificial Analysis. Higher is better.

Intelligence index5.5
Coding index5.8
Math index18.3
GPQA34.9%
MMLU-Pro59.5%
Humanity's Last Exam4.8%
Long Context Reasoning6.7%
LiveCodeBench13.7%
SciCode17.4%
MATH-50085.3%
AIME22%
AIME 202518.3%
IFBench36.7%
τ²-Bench10.8%
τ-Bench Banking0.8%
Terminal-Bench0%
Terminal-Bench Hard0.8%
Benchmark data by Artificial Analysis

About this model

Gemma 3 12B is an open-weight AI model by Google. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.

Frequently asked questions

What is Gemma 3 12B?

Gemma 3 12B is an AI language model from Google. It is open-weight: you can download it and run it on your own hardware, for free. It scores 5.5 on the Artificial Analysis intelligence index.

Is Gemma 3 12B free?

The weights are free and open — you can self-host Gemma 3 12B and pay nothing per token. If you prefer a hosted API, list prices are $0.05 per million input tokens and $0.15 per million output tokens.

What is Gemma 3 12B good at?

Independent benchmarks from Artificial Analysis give it GPQA 34.9%, MMLU-Pro 59.5%, Humanity's Last Exam 4.8%, Long Context Reasoning 6.7%, LiveCodeBench 13.7%, SciCode 17.4%, MATH-500 85.3%, AIME 22%, AIME 2025 18.3%, IFBench 36.7%, τ²-Bench 10.8%, τ-Bench Banking 0.8%, Terminal-Bench 0%, Terminal-Bench Hard 0.8%. It is particularly used for code generation.

Can I self-host Gemma 3 12B?

Yes. Gemma 3 12B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.

Related models

Gemini 3.1 Pro PreviewGoogleGemini 3.1 Pro Preview Custom ToolsGoogleNano Banana Pro (Gemini 3 Pro Image)GoogleGoogle Gemini Pro LatestGoogleGemini 2.5 ProGoogleGemini 2.5 Pro Preview 05-06Google