Gemma 3 27B (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.
Independent benchmark scores for Gemma 3 27B, measured by Artificial Analysis. Higher is better.
Gemma 3 27B 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.
Gemma 3 27B 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 7.4 on the Artificial Analysis intelligence index.
The weights are free and open — you can self-host Gemma 3 27B and pay nothing per token. If you prefer a hosted API, list prices are $0.08 per million input tokens and $0.45 per million output tokens.
Independent benchmarks from Artificial Analysis give it GPQA 42.8%, MMLU-Pro 66.9%, Humanity's Last Exam 4.7%, Long Context Reasoning 5.7%, LiveCodeBench 13.7%, SciCode 21.2%, MATH-500 88.3%, AIME 25.3%, AIME 2025 20.7%, IFBench 31.8%, τ²-Bench 10.5%, τ-Bench Banking 0.8%, Terminal-Bench 4.5%, Terminal-Bench Hard 3.8%. It is particularly used for code generation.
Yes. Gemma 3 27B 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.
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.