G
Gemma 3 4BOPEN
Gemma 3 4B (Google): live API pricing, context window and the best open-source alternatives, tracked daily by OpenSourceAI.tech.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for Gemma 3 4B, measured by Artificial Analysis. Higher is better.
About this model
Gemma 3 4B 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 4B?
Gemma 3 4B 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 1.1 on the Artificial Analysis intelligence index.
Is Gemma 3 4B free?
The weights are free and open — you can self-host Gemma 3 4B and pay nothing per token. If you prefer a hosted API, list prices are $0.05 per million input tokens and $0.1 per million output tokens.
What is Gemma 3 4B good at?
Independent benchmarks from Artificial Analysis give it GPQA 29.1%, MMLU-Pro 41.7%, Humanity's Last Exam 5.2%, Long Context Reasoning 5.7%, LiveCodeBench 11.2%, SciCode 7.3%, MATH-500 76.6%, AIME 6.3%, AIME 2025 12.7%, IFBench 28.3%, τ²-Bench 5%, τ-Bench Banking 0.4%, Terminal-Bench 0.4%, Terminal-Bench Hard 0.8%. It is particularly used for code generation.
Can I self-host Gemma 3 4B?
Yes. Gemma 3 4B 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.
Open-source alternatives
Depending on your workload, an open-weight model that you can self-host may cut costs dramatically or remove per-token pricing entirely. Our comparison pages put this model side by side with the strongest open-source contenders.