Google AI Studio

Google AI Studio is Google's browser based workbench for building with the Gemini family of models. It is where a developer signs in, tries a prompt against the current models, tunes settings, saves the result and generates an API key to move the same call into code. It exposes the models' multimodal inputs and a context window of up to one million tokens, and a prompt gallery and cookbook show worked examples. It is for developers and technical teams evaluating Gemini or prototyping before they wire the Gemini API into an application. Anything built in the studio can be reproduced through the API, and community forums sit alongside the documentation. The current headline model at the time of writing is Gemini 3.8 Flash. Google AI Studio itself is free of charge in every region where it is available. Costs arise only through the Gemini API. A free tier offers limited access to certain models with free input and output tokens, and Google may use that content to improve its products. The paid tier raises rate limits, adds context caching and a Batch API at half price, and does not use content for product improvement. Published paid tier rates per one million tokens are $0.75 input and $3.75 output for Gemini 3.8 Flash and Gemini 3.7 Flash through December 31, 2026, doubling from January 1, 2027; $1.50 and $9.00 for Gemini 3.5 Flash; $0.30 and $2.50 for Gemini 2.5 Flash; and $1.25 to $2.50 input and $10.00 to $15.00 output for Gemini 2.5 Pro depending on prompt length. Enterprise terms with provisioned throughput and volume discounts run through the Gemini Enterprise Agent Platform.