What is Google AI Studio?

A free, developer-facing web tool for building and testing prototypes with Google's Gemini models. Provides an intuitive environment for prompt design, testing, and iteration, with seamless integration into production apps via the Gemini API. Supports multimodal input including text, images, audio, and video.

Business problems it solves

About "Google AI Studio"

How to Use

Create an account and log in

Access Google AI Studio with your Google account and log in.
Create a prompt

Click "Create Prompt" and build a prompt using text, images, audio, video, or other input.
Select a model and configure settings

Choose a model such as Gemini 1.5 Pro or Gemini 1.5 Flash, and configure output format, token count, and other parameters as needed.
Run and review results

Click "Run" to execute the prompt and review the generated output.
Save and share projects

Save prompts and results to Google Drive, or create a shareable link to share with others.

Features

Multimodal input

Accepts text, images, audio, video, and other formats as input.
Access to advanced generative AI models

Use Google's latest generative AI models including Gemini 1.5 Pro and Gemini 1.5 Flash.
Long-context processing

Supports a context window of up to 1 million tokens (~500,000 Japanese characters), enabling long-document processing.
Prompt gallery

A library of prompt templates for various use cases to accelerate development.
API key and integration

Obtain a Gemini API key and integrate it into your own applications to extend AI capabilities.

Pricing

	Free (in Studio)	Paid (Gemini API)
Monthly price	Free	Pay-per-use
Available models	Gemini 1.5 Pro, Gemini 1.5 Flash, etc.	Same
Input token pricing	Free	$3.50–$7.00 per 1M tokens
Output token pricing	Free	$10.50–$21.00 per 1M tokens
Context window	Up to 1M tokens	Same
API key	Yes (free)	Yes (paid use)
Commercial use	Yes	Yes
Support	Community	Priority (varies by plan)