google-gemini-api

Integrate Gemini API in Node.js apps using the @google/genai SDK.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/jesusjbriceno/flux-free-gateway --skill google-gemini-api-jesusjbriceno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google-gemini-api
Source: https://github.com/jesusjbriceno/flux-free-gateway/tree/main/.agents/skills/google-gemini-api
Command: npx skills add https://github.com/jesusjbriceno/flux-free-gateway --skill google-gemini-api-jesusjbriceno

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines Gemini API integration in Node.js apps by providing a ready-to-use workflow with the GenAI SDK, enabling developers to connect to Gemini models, stream results, handle multimodal inputs, and leverage grounding and function calling.

Core Features & Use Cases

  • SDK-based Gemini integration: Simplified setup with @google/genai and Gemini 2.5 models.
  • Multimodal inputs & streaming: Support for text, images, video, audio, and PDFs with streaming outputs.
  • Advanced workflows: Function calling, grounding (real-time web data), and thinking mode configurations for robust agents.
  • Use Case: Build production-ready assistants that reference current information, execute code, or analyze large documents with cached contexts.

Quick Start

Install @google/genai, initialize GoogleGenAI, and start invoking gemini-2.5-flash via models.generateContent to begin generating content.

Frequently Asked Questions about google-gemini-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate the Gemini API into a Node.js application?

You can integrate the Gemini API in Node.js by installing the @google/genai SDK, initializing the GoogleGenAI client, and invoking models like gemini-2.5-flash using models.generateContent to generate content.

Can I process images and video with Gemini models using the GenAI SDK?

Yes, the GenAI SDK supports multimodal inputs, allowing you to process text, images, video, audio, and PDFs with Gemini models, while also providing streaming outputs for efficient data handling.

Does the Gemini API support function calling and real-time web grounding?

Yes, the Gemini API supports advanced workflows including function calling for executing code and grounding to reference real-time web data, enabling the construction of robust, production-ready agents.

What is the best way to ensure migration-safe SDK usage when invoking Gemini models?

To ensure migration-safe SDK usage, you should enforce explicit model version suffixes when invoking Gemini models, which helps maintain caching stability and prevents breaking changes during updates.

Do I need to meet specific prerequisites to use Gemini grounding features?

Yes, to use grounding features effectively, you must adhere to specific grounding prerequisites defined by the API, ensuring your application can successfully reference real-time web data during generation.

Why does my Gemini API integration fail when processing large documents?

Processing large documents requires adherence to explicit model version suffixes for caching and proper configuration of thinking mode, ensuring the Gemini API can handle cached contexts without failing.