AI API Tutorial for Python Beginners: Your First AI App in 10 Minutes

You don't need a PhD in machine learning to use AI in your Python projects. With modern AI APIs, you can build a chatbot, summarizer, or code generator in under 10 minutes. This tutorial walks you through everything from installation to your first working app.

Prerequisites

• Python 3.8 or higher
• Basic Python knowledge (variables, functions, strings)
• An AIPower API key (free, takes 30 seconds to get)

Step 1: Install the SDK

pip install openai

Yes, you install the OpenAI SDK even though you're using AIPower. AIPower uses the same API format as OpenAI, so any OpenAI-compatible SDK works out of the box.

Step 2: Set Up the Client

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aipower.me/v1",
    api_key="YOUR_API_KEY",  # Get yours at aipower.me
)

Step 3: Your First API Call

response = client.chat.completions.create(
    model="deepseek/deepseek-chat",  # Great quality, very cheap
    messages=[
        {"role": "user", "content": "What is the capital of France?"}
    ],
)

print(response.choices[0].message.content)
# Output: "The capital of France is Paris."

That's it. You just made your first AI API call. Let's build something useful.

Project 1: Text Summarizer

def summarize(text, max_sentences=3):
    response = client.chat.completions.create(
        model="deepseek/deepseek-chat",
        messages=[
            {"role": "system", "content": f"Summarize the following text in {max_sentences} sentences. Be concise."},
            {"role": "user", "content": text}
        ],
    )
    return response.choices[0].message.content

article = """
Your long article text goes here...
"""
print(summarize(article))

Project 2: Simple Chatbot

messages = [
    {"role": "system", "content": "You are a helpful assistant. Be concise."}
]

print("Chat with AI (type 'quit' to exit)")
while True:
    user_input = input("You: ")
    if user_input.lower() == "quit":
        break
    messages.append({"role": "user", "content": user_input})
    response = client.chat.completions.create(
        model="deepseek/deepseek-chat",
        messages=messages,
    )
    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    print(f"AI: {reply}")

Project 3: Code Generator

def generate_code(description, language="Python"):
    response = client.chat.completions.create(
        model="auto-code",  # Smart routing picks the best coding model
        messages=[
            {"role": "system", "content": f"Write {language} code. Only output the code, no explanation."},
            {"role": "user", "content": description}
        ],
    )
    return response.choices[0].message.content

code = generate_code("A function that checks if a number is prime")
print(code)

Choosing the Right Model

Error Handling

try:
    response = client.chat.completions.create(
        model="deepseek/deepseek-chat",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(response.choices[0].message.content)
except Exception as e:
    print(f"API error: {e}")

Next Steps

• Try different models — change one parameter to compare GPT, Claude, and DeepSeek
• Add streaming for real-time output (stream=True)
• Build a web app with Flask or FastAPI
• Use model="auto" to let smart routing pick the best model

Get your free API key at aipower.me — 50 free calls included, no credit card required.