Gemini 3 is here!

Try it free of charge in Google AI Studio

                                                    ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­  

Email not displaying correctly? View it online

Bring any idea to life with Gemini 3

Try it free of charge

Hi Anshari, You can now build and test with Gemini 3 in Google AI Studio, or access the model via the Gemini API with a paid key. Vibe code: Build web apps with exceptional zero-shot generation and richer UI Reason across modalities: Handle complex multimodal inputs with state-of-the-art reasoning Build agents: Utilize improved agentic coding, tool use, and instruction following Try it free of charge in AI Studio

Bring any idea to life with a simple prompt Check out these open source apps built with Gemini 3 - remix to make them your own in Google AI Studio: Bring Anything to Life - turn any image into an interactive experience Visual Computer - draw to control a virtual OS Shader Pilot - build a complex 3D world with customizable Research Visualization - transform research paper into an interactive site Tempo Strike - slash sparks to the beat using webcam and your hands For more apps, web pages, games, and 3D visualization examples, explore the apps gallery. When you're ready, deploy your creation directly from Google AI Studio or save the code to GitHub. Explore the app gallery Try I'm feeling lucky

New API features for Gemini 3 With Gemini 3, we are introducing new parameters designed to give developers more control over latency, cost, and multimodal fidelity. To learn more about the new API parameters, see the Gemini 3 Developer Guide.

thinking_level Configure thinking levels to adjust the model's internal reasoning depth.

media_resolution Define per part vision token usage based on your required level of visual fidelity.

thought_signature Preserve agentic reasoning in multi-tool workflows with stricter validation.

Start building with the API  You can use our SDKs for Python, JavaScript, and Go, or make a direct REST API call with cURL. Get your API key, select a billing-enabled project for your API key, and start building.

from google import genai client = genai.Client() prompt = "Find the race condition in this multi-threaded C++ snippet: [code here]" response = client.models.generate_content(   model="gemini-3-pro-preview",   contents=prompt ) print(response.text)

Ready to build?

Documentation Explore all model capabilities and get advanced prompting tips. Read the API docs Start building  Start building by vibe coding apps in Google AI Studio. Vibe code with Gemini 3

Happy building,  The Google AI Studio team

Prompt models Manage API keys Vibe code

Prompt models

Manage API keys

Vibe code

Get the latest product updates

Get the latest product updates

© 2025 Google LLC 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA This email was sent to anshari.kurniawan@gmail.com because you signed up to receive emails about Google AI. If you do not wish to receive these emails, please unsubscribe.