# Install with Go go install github.com/google-gemini/gemini-api-cli/cmd/gemini-api@latest For Windows (PowerShell), run iwr -useb https://raw.githubusercontent.com ...

Building for extended reality (XR) has traditionally meant wiring together heavy 3D game engines, low-level perception pipelines, and device-specific SDKs before you can even test a simple hand-pinch ...

Gemini 4 Argon is our newest frontier model, built to take your most complex tasks from start to finish and turn ambitious ideas into real projects you can use. With major improvements in visual ...

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 ...

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 ...

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.

Google AI Studio Playground provides a visual interface to prototype and learn how to build managed agents without having to create and write API calls. Managed agents run within a secure, ephemeral ...

The Gemini API converts speech in audio files into text using the Gemini 3.5 Transcribe model (gemini-3.5-transcribe). Based on Gemini's audio understanding capabilities, it delivers accurate ...

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 ...

Tool use allows Live API to go beyond just conversation by enabling it to perform actions in the real-world and pull in external context while maintaining a real time connection. You can define tools ...

This page provides a reference for all Interactions API error codes, describes the error response format, and explains how the API delivers errors for different ...

AI coding agents rely on training data that cuts off at a set date. Because of this, agents often suggest deprecated models (gemini-1.5), older SDKs (google-generativeai), or outdated code patterns.