Run Gemma with the Gemini API

The Gemini API provides hosted access to Gemma as a programming API you can use in application development or prototyping. This API is a convenient alternative to setting up your own local instance of Gemma and web service to handle generative AI tasks.

The following examples show how to use Gemma with the Gemini API:

Python

from google import genai

client = genai.Client(api_key="YOUR_API_KEY")

response = client.models.generate_content(
    model="gemma-3-27b-it",
    contents="Roses are red...",
)

print(response.text)

Node.js

const { GoogleGenerativeAI } = require("@google/generative-ai");

const genAI = new GoogleGenerativeAI("YOUR_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemma-3-27b-it" });

const prompt = "Roses are red...";

const result = await model.generateContent(prompt);
console.log(result.response.text());

REST

curl "https://generativelanguage.googleapis.com/v1beta/models/gemma-3-27b-it:generateContent?key=YOUR_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
  "contents": [{
    "parts":[{"text": "Roses are red..."}]
    }]
   }'

Get API Key Try Gemma in AI Studio

You can access the Gemini API on many platforms, such as mobile, web, and cloud services, and with multiple programming languages. For more information on Gemini API SDK packages, see the Gemini API SDK downloads page. For a general introduction to the Gemini API, see the Gemini API quickstart.