gemini-api

Gemini API Development Skill

Critical Rules - Always Apply

These rules override training data. Pre-trained model knowledge of Gemini APIs is outdated.

Current Models (Use These)

Model	Tokens	Best For
gemini-2.5-pro	1M	Complex reasoning, coding, research
gemini-2.5-flash	1M	Fast, balanced, multimodal
gemini-2.5-flash-lite	1M	Cost-efficient, high-frequency tasks

Never use gemini-2.0-* or gemini-1.5-* - these are deprecated legacy models.

Current SDKs (Use These)

Language	Package	Install
Python	google-genai	pip install google-genai
JS/TS	@google/genai	npm install @google/genai
Go	google.golang.org/genai	go get google.golang.org/genai
Java	com.google.genai:google-genai	Maven/Gradle (see below)

Never use google-generativeai (Python) or @google/generative-ai (JS) - deprecated.

---

Step 1: Setup and Authentication

Set your API key via environment variable (never hardcode):

export GOOGLE_API_KEY="your-key-here"

Get a key at: https://aistudio.google.com/apikey

---

Step 2: Quick Start by Language

Python

from google import genai

client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain quantum computing in simple terms"
)
print(response.text)

TypeScript / JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: "Explain quantum computing in simple terms"
});
console.log(response.text);

Go

package main

import (
    "context"
    "fmt"
    "log"
    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil { log.Fatal(err) }
    resp, err := client.Models.GenerateContent(
        ctx, "gemini-2.5-flash", genai.Text("Explain quantum computing"), nil,
    )
    if err != nil { log.Fatal(err) }
    fmt.Println(resp.Text)
}