Your first LLM API call (free Gemini API)

mkdir gemini-first-call
cd gemini-first-call
python -m venv .venv

# macOS / Linux
source .venv/bin/activate
# Windows PowerShell
# .venv\Scripts\Activate.ps1

pip install -U google-genai python-dotenv

GEMINI_API_KEY=paste-your-key-here

.env
.venv/
__pycache__/

from dotenv import load_dotenv
from google import genai

load_dotenv()  # reads .env so GEMINI_API_KEY is available

# Model names change as new versions ship. Pick a current Flash model
# from the models page in the Gemini API docs and put it here.
MODEL = "gemini-flash-latest"

client = genai.Client()  # picks up GEMINI_API_KEY from the environment

response = client.models.generate_content(
    model=MODEL,
    contents="Explain what DNS is in three short lines for a first-year student.",
)

print(response.text)

python first_call.py

from dotenv import load_dotenv
from google import genai
from google.genai import types

load_dotenv()
MODEL = "gemini-flash-latest"
client = genai.Client()

response = client.models.generate_content(
    model=MODEL,
    contents="What should I order at a coffee shop if I want something strong but not bitter?",
    config=types.GenerateContentConfig(
        system_instruction=(
            "You are a barista at Brew & Bean in Indiranagar, Bengaluru. "
            "Answer in at most two sentences. Be friendly and plain."
        ),
        temperature=0.4,
        max_output_tokens=300,
    ),
)

print(response.text)
print("Why it stopped:", response.candidates[0].finish_reason)
print("Prompt tokens:", response.usage_metadata.prompt_token_count)
print("Total tokens:", response.usage_metadata.total_token_count)

from dotenv import load_dotenv
from google import genai
from google.genai import types

load_dotenv()
MODEL = "gemini-flash-latest"
client = genai.Client()

chat = client.chats.create(
    model=MODEL,
    config=types.GenerateContentConfig(
        system_instruction="You are a patient tutor. Keep answers under 80 words."
    ),
)

print("Type 'quit' to stop.")
while True:
    user = input("You: ").strip()
    if user.lower() in {"quit", "exit"}:
        break
    if not user:
        continue
    reply = chat.send_message(user)
    print("AI:", reply.text, "\n")

mkdir gemini-js && cd gemini-js
npm init -y
npm install @google/genai

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

// Node 20.6+: run with  node --env-file=.env first_call.mjs
const ai = new GoogleGenAI({}); // reads GEMINI_API_KEY from the environment

const response = await ai.models.generateContent({
  model: "gemini-flash-latest", // use a current model ID
  contents: "Explain what DNS is in three short lines.",
});

console.log(response.text);

import time
from google.genai import errors

def ask(client, model, prompt, retries=3):
    for attempt in range(retries):
        try:
            return client.models.generate_content(model=model, contents=prompt).text
        except errors.APIError as e:
            # 429 = rate limited, 5xx = server trouble: wait and retry
            if e.code in (429, 500, 503) and attempt < retries - 1:
                time.sleep(2 ** attempt)  # 1s, 2s, 4s...
                continue
            raise

I called the Gemini API with the Python google-genai SDK and got this error:

[paste the full error]

Here is my code:

[paste the code, with the API key removed]

Explain what the error means in plain English, list the 3 most likely causes in order, and tell me how to check each one.