Browser playground for prompting and prototyping with Gemini models
Google AI Studio is the browser playground for Gemini models, aimed at developers who want to test prompts before wiring them into an application. You get adjustable temperature and safety settings, system instructions, multi-turn chats, and image, audio or video input for the multimodal models. A free API key lets you prototype with rate-limited access, and any prompt can be exported as ready-to-run code in common languages. It is a testing surface rather than a hosting platform: serious traffic usually moves to Vertex AI with Google Cloud billing behind it.
Last updated: 2026-09-20. This site only provides an index; for exact features, pricing, and licensing, see the official website.
prompt prototyping, gemini testing, multimodal experiments and api key evaluation
If you're comparing similar products, check the alternatives below, or browse all tools in the AI Models & Platforms category.
The playground and a free API key are available at no cost within rate limits. Free-tier usage follows Google's terms for that tier, and heavier or commercial workloads generally move to a paid Google Cloud setup with Vertex AI.
You can prototype and even ship small tools, but production traffic usually migrates to Vertex AI for quotas, service accounts, monitoring and billing controls. Treat AI Studio as the place to get prompts working, not to run them at scale.
Text, images, audio and video, depending on the model you select, with adjustable temperature, safety settings and system instructions. That makes it a quick way to test multimodal prompts before writing any application code.
Developer console and API keys for the Claude model family
Node-based local interface for running image and video diffusion models
Hosted Jupyter notebooks with optional free GPU and TPU runtimes
Where most of the open machine learning world lives