G
Gemma 3 12BOPEN
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.
Prices update automatically — checked daily against provider list prices.
- $0.08 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 82% of the 191 open-weight models tracked here
- 4 of 34 Google models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Gemma 3 12B, measured by Artificial Analysis. Higher is better.
Models at this level cost $0.24 per 1M tokens (median of 22) — this one costs $0.08.
Cheaper and better on this index: DeepSeek V4 Flash 0731 · Solar Pro 4 · Ling-3.0-flash and 6 more
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 daily, 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 4.2%, Long Context Reasoning 8%, 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.