Lesson Content

Setting up your API key.

1. Create an Anthropic account at console.anthropic.com
2. Navigate to API Keys and generate a new key
3. Copy the key immediately – it is shown only once
4. Store it in an environment variable: ANTHROPIC_API_KEY=sk-ant-...

Never hardcode the key in source files. Use environment variables in development and a secrets manager (AWS Secrets Manager, Google Secret Manager, etc.) in production.

Installing the SDK.

Python: pip install anthropic TypeScript/Node: npm install @anthropic-ai/sdk

Always verify current SDK versions and installation instructions at docs.anthropic.com/en/docs/quickstart.

Your first API call (Python example pattern).

import anthropic

client = anthropic.Anthropic() # reads ANTHROPIC_API_KEY from environment

message = client.messages.create(
model="claude-sonnet-4-6", # replace with current model ID from docs
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello, Claude."}
]
)

print(message.content[0].text)

This is a minimal working call. The model parameter should use a current model ID from docs.anthropic.com – not hardcoded values from this course.

The response structure.

The Messages API response contains:

• id: unique message identifier
• type: "message"
• role: "assistant"
• content: array of content blocks (typically a text block with .text property)
• model: the model that generated the response
• stop_reason: why generation stopped (end_turn, max_tokens, tool_use)
• usage: input and output token counts for this request

The usage field is important: log token counts in production to track costs and debug unexpectedly large requests.

Adding a system prompt.

message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
system="You are a helpful assistant for a software development team.",
messages=[
{"role": "user", "content": "What are the main risk factors in this PR?"}
]
)

The system parameter sets the persistent instruction context for the model – equivalent to Custom Instructions in the chat interface.