G
Gemma 3 27BOPEN
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.
Prices update automatically — checked daily against provider list prices.
- $0.17 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 64% of the 191 open-weight models tracked here
- 8 of 34 Google models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Gemma 3 27B, measured by Artificial Analysis. Higher is better.
Models at this level cost $0.26 per 1M tokens (median of 29) — this one costs $0.17.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 24 more
About this model
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 daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Gemma 3 27B?
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.
Is Gemma 3 27B free?
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.
What is Gemma 3 27B good at?
Independent benchmarks from Artificial Analysis give it GPQA 42.8%, MMLU-Pro 66.9%, Humanity's Last Exam 4.4%, Long Context Reasoning 6.3%, 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.
Can I self-host Gemma 3 27B?
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.