The fastest path from prompt to production with Gemini
Install for macOS
Explore all of Google’s AI models in one place
Access a unified AI playground to test your prompts across all our modalities. Experiment with text, image, audio, and video models in one place to find the perfect fit for your project.
Build
Go from idea to app with the power of Gemini
The fastest way to build AI-first applications. Use natural language to generate fully functional apps with built-in features like Nano Banana or Google Search integration, then deploy with a single click.
Operate
Stay on top of your resource usage
Manage API keys and projects in one space. Track your usage, billing, and rate limits from one centralized dashboard, and view detailed logs to get the most out of your projects.
Start building with the API today
Developer quickstart
Set up your environment and make your first API request in minutes
from google import genai
client = genai.Client()
response = client.models.generate_content(
model="gemini-3-pro-preview",
contents="Explain how AI works in a few words"
)
print(response.text)
Explore our models
Gemini
Our state of the art models, excellent at coding, reasoning, creative writing, and multimodal capabilities.
Imagen
Our best image generation model yet, engineered for creativity. Bring your imagination to life faster than ever before.
Veo
Our latest video generation model, designed to empower filmmakers and storytellers.
Gemini TTS
Transform text input into single speaker or multi-speaker audio using native, controllable text-to-speech.
Gemini Native Audio
Hyper realistic audio generation, supporting a wide variety of voices.
Gemma
Lightweight, state-of-the-art open models built from the same technology that powers our Gemini models.