Getting Your API Key

First, sign up at console.anthropic.com and generate an API key. You'll get $5 in free credits to start experimenting.

Installation

# Python
pip install anthropic
Node.js
npm install @anthropic-ai/sdk

Your First Request

Python

import anthropic
client = anthropic.Anthropic()  # Uses ANTHROPIC_API_KEY env var
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude!"}
    ]
)
print(message.content[0].text)

Node.js

import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic();
const message = await client.messages.create({
  model: 'claude-sonnet-4-6',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Hello, Claude!' }],
});
console.log(message.content[0].text);

Streaming Responses

For real-time output, use streaming:

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Write a poem"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

Best Practices

• Set appropriate max_tokens: Don't waste tokens on unused output
• Use system prompts: Set context and behavior guidelines
• Handle rate limits: Implement exponential backoff
• Cache frequently used prompts: Save on input token costs
• Choose the right model: Match model capability to task complexity

Error Handling

The API returns standard HTTP status codes. Always handle errors gracefully:

• 400: Bad request (check your parameters)
• 401: Authentication error (check your API key)
• 429: Rate limited (slow down or upgrade your plan)
• 500: Server error (retry with backoff)