Basic Content Generation (Python)
import google.generativeai as genai
genai.configure(api_key="YOUR_API_KEY")
model = genai.GenerativeModel("gemini-2.5-pro")
response = model.generate_content(
"Explain what a context window is in one paragraph."
)
print(response.text)Multi-Turn Chat
chat = model.start_chat(history=[])
response = chat.send_message("What is RAG?")
print(response.text)
response2 = chat.send_message("How does that differ from fine-tuning?")
print(response2.text)JavaScript / Node.js Example
import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI("YOUR_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-2.5-pro" });
const result = await model.generateContent("Summarize this in two sentences: ...");
console.log(result.response.text());Common Parameters Worth Knowing
Generation config options like temperature and maxOutputTokens can be passed when initializing the model or per-request depending on the SDK version; the start_chat pattern shown above handles conversation history automatically across turns. See Google's own current documentation for the complete, up-to-date parameter list and model names.
Related Pages
Frequently Asked
Is the model name in these examples always current?
Model names and versions change over time; check Google's current documentation for the latest available Gemini model identifiers before deploying.
Does the Gemini API handle conversation history automatically?
The chat-session pattern shown above manages history for you across turns within that session object, simplifying multi-turn conversations.
Where do I get an API key?
Through Google AI Studio or Google Cloud, depending on your setup; never commit a real API key to public source code or version control.
Where can I see similar examples for other providers?
See our OpenAI API Examples and Claude API Examples pages for equivalent code in other major providers.