Setting Up Your Development Environment

Let's get your development environment ready. By the end of this lesson, you'll have made your first successful API call to Claude Opus 4.6.

Step 1: Get Your API Key

1. Visit console.anthropic.com
2. Create an account or sign in
3. Navigate to API Keys
4. Click Create Key and give it a descriptive name
5. Copy the key — you won't see it again

Security tip: Never hardcode API keys in your source code. Always use environment variables.

Step 2: Set Up Your Environment

Python Setup

# Create a project directory
mkdir claude-opus-course && cd claude-opus-course

# Create and activate virtual environment
python -m venv venv
source venv/bin/activate  # macOS/Linux
# venv\Scripts\activate   # Windows

# Install the Anthropic SDK
pip install anthropic

# Set your API key
export ANTHROPIC_API_KEY="your-key-here"

Node.js / TypeScript Setup

# Create a project
mkdir claude-opus-course && cd claude-opus-course
npm init -y

# Install the SDK
npm install @anthropic-ai/sdk

# Set your API key
export ANTHROPIC_API_KEY="your-key-here"

Step 3: Your First API Call

Python

import anthropic

client = anthropic.Anthropic()

message = client.messages.create(
    model="claude-opus-4-6-20250514",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude! What makes you special?"}
    ]
)

print(message.content[0].text)

TypeScript

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic();

const message = await client.messages.create({
    model: "claude-opus-4-6-20250514",
    max_tokens: 1024,
    messages: [
        { role: "user", content: "Hello, Claude! What makes you special?" }
    ],
});

console.log(message.content[0].text);

Step 4: Verify Your Setup

Run your script. If you see a thoughtful response from Claude, your environment is ready.

python first_call.py
# or
npx tsx first_call.ts

Understanding the Response Object

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [{ "type": "text", "text": "Hello! ..." }],
  "model": "claude-opus-4-6-20250514",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 147
  }
}

Key fields:

• content: Array of content blocks (text, tool use, etc.)
• stop_reason: Why the model stopped (end_turn, max_tokens, tool_use)
• usage: Token counts for billing

Recommended Project Structure

claude-opus-course/
├── .env                  # API key (add to .gitignore!)
├── .gitignore
├── requirements.txt      # or package.json
├── src/
│   ├── ch02/            # Chapter 2 exercises
│   ├── ch03/            # Chapter 3 exercises
│   └── ...
└── projects/
    ├── research-agent/
    ├── doc-analyzer/
    └── multi-agent/

You're all set. In the next chapter, we'll dive deep into the Claude API.