google-gemini-api

Integrate Google Gemini API with the current @google/genai SDK.

Updated Jan 29, 2026

Search Tags:#multimodal #streaming #code execution #grounding #gemini api #google ai #function calling

Ready to run

npx skills add https://github.com/brendadeeznuts1111/tier-1380-omega --skill google-gemini-api-brendadeeznuts1111

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: google-gemini-api
Source: https://github.com/brendadeeznuts1111/tier-1380-omega/tree/main/skills/google-gemini-api
Command: npx skills add https://github.com/brendadeeznuts1111/tier-1380-omega --skill google-gemini-api-brendadeeznuts1111

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you integrate Google's Gemini API into your applications, avoiding common pitfalls like using deprecated SDKs, incorrect model configurations, and inefficient token usage.

Core Features & Use Cases

Correct SDK Usage: Employs the current @google/genai SDK, guiding you away from the deprecated @google/generative-ai.
Accurate Model Info: Provides correct details on Gemini 2.5 models, including their precise context window limits (1M tokens, not 2M).
Advanced Features: Demonstrates multimodal inputs (images, video, audio, PDFs), function calling, streaming responses, context caching for cost savings, code execution, and grounding with Google Search.
Use Case: Build a chatbot that can analyze user-uploaded images, perform complex calculations using code execution, and provide up-to-date information by searching the web, all while optimizing costs through context caching.

Quick Start

Use the google-gemini-api skill to generate text by sending a prompt to the gemini-2.5-flash model.

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 Google Gemini API using the current SDK?▼

To integrate the Gemini API, use the current @google/genai SDK to avoid deprecated packages. This enables multimodal inputs, function calling, streaming responses, and code execution for your application.

What is the correct context window limit for Gemini 2.5 models?▼

The correct context window limit for Gemini 2.5 models is 1 million tokens. Accurate model specifications prevent incorrect configurations and inefficient token usage during API integration.

How do I process images and PDFs with the Gemini API?▼

Process images and PDFs by sending multimodal inputs to the Gemini API. This supports advanced features like analyzing user-uploaded files alongside function calling and streaming responses.

Can I use context caching with the Gemini API to optimize costs?▼

Yes, you can use context caching with the Gemini API to optimize costs. This feature reduces expenses by caching previous context, avoiding redundant token processing for repeated inputs.

Why is my Gemini API code using a deprecated SDK?▼

Your Gemini API code uses a deprecated SDK if it relies on @google/generative-ai. Migrate to the current @google/genai SDK to access Gemini 2.5 features and avoid integration issues.

Does the Gemini API support code execution and Google Search grounding?▼

Yes, the Gemini API supports code execution via a Python sandbox and Google Search grounding for real-time information retrieval. These features enable complex calculations and up-to-date web data access.