Managed agents on the Gemini API give you a configurable agent harness. A single API call provisions a Linux sandbox where the agent reasons, executes code, manages files, and browses the web ...

In a typical AI workflow, you might pass the same input tokens over and over to a model. The Gemini API offers implicit caching to optimize performance and costs.

Gemini 3.7 Flash is a previous-generation model in the Gemini 3 series of natively multimodal reasoning models, now replaced by Gemini 3.8 Flash.

Environments are managed Linux sandboxes that give agents an isolated place to execute code and persist files. They are decoupled from interaction context, so you can reuse the same environment across ...

Use your Google AI subscription plan in AI Studio. Google AI Pro and Ultra subscription plans provide greater model access and increased rate limits for prototyping and development in AI Studio. To ...

The Gemini Live API enables real-time, bidirectional voice conversations with Gemini models. Standard voice models work well for immediate back-and-forth dialogue. You speak to the model, and it ...

Prompt design is the process of creating prompts, or natural language requests, that elicit accurate, high quality responses from a language model. This page introduces basic concepts, strategies, and ...

To learn about video understanding, see the Video understanding guide.

This guide covers best practices you can follow to optimize your use of the Live API. See Get started with Live API page for an overview and sample code for common use cases. To get the best ...

Veo 3.1 Lite Preview is a high-efficiency, developer-first video model providing high-fidelity video generation, editing, and cinematic control. It leverages the state-of-the-art Veo 3.1 model to ...

Gemini 4 Argon is our latest frontier model, built to take your most ambitious ideas from start to finish. Whether you are vibe-coding your first web app, turning a photo of your desk into a playable ...

TTS models accept text-only inputs and produce audio-only outputs. For a complete list of restrictions specific to TTS models, review the Limitations section.