To install the Anthropic SDK, run:
pip install anthropic

Make sure you have your API key ready from: https://console.anthropic.com/

✓ API key loaded successfully from .env file
  Key starts with: sk-ant-a...

✓ Anthropic client initialized successfully!

Claude's response:
I'm Claude, an AI assistant created by Anthropic to be helpful, harmless, and honest in conversations and tasks.

Full message object structure:

ID: msg_01SEBSy2jWuJBH7y211tbEbc
Model: claude-sonnet-4-20250514
Role: assistant
Stop Reason: end_turn

Token Usage:
  Input tokens: 18
  Output tokens: 29

Content type: <class 'anthropic.types.text_block.TextBlock'>
Content: I'm Claude, an AI assistant created by Anthropic to be helpful, harmless, and honest in conversations and tasks.

Streaming response:

Here's a haiku about coding:

Lines of logic flow  
Debugging through endless nights—  
Code compiles at dawn

✓ Streaming complete!

Available Claude Models:

1. claude-sonnet-4-20250514 (Latest)
   - Most intelligent model
   - Best for complex tasks
   - Balanced speed and capability

2. claude-opus-4-20250514
   - Highest capability
   - Best for most complex tasks
   - Slower but most powerful

3. claude-3-5-sonnet-20241022
   - Previous generation
   - Still very capable
   - Cost-effective option

4. claude-3-haiku-20240307
   - Fastest model
   - Most cost-effective
   - Good for simple tasks

Choose based on your needs: complexity, speed, and cost.

Result: 2 + 2 = 4

📚 ANTHROPIC SDK BEST PRACTICES:

1. **API Key Security**
   - Store API keys in environment variables
   - Never commit keys to version control
   - Use .env files or secret managers

2. **Token Management**
   - Set appropriate max_tokens limits
   - Monitor usage via message.usage
   - Consider costs based on input/output tokens

3. **Error Handling**
   - Always wrap API calls in try-except blocks
   - Handle rate limits gracefully
   - Implement retry logic for transient errors

4. **Model Selection**
   - Use Haiku for simple, fast tasks
   - Use Sonnet for balanced performance
   - Use Opus for most complex reasoning

5. **Conversation Management**
   - Keep conversation history for context
   - Trim old messages to stay within limits
   - Use system prompts for consistent behavior

6. **Performance**
   - Use streaming for long responses
   - Batch requests when possible
   - Cache common responses

7. **System Prompts**
   - Be clear and specific
   - Set the right tone and expertise level
   - Include output format requirements

8. **Testing**
   - Test with various inputs
   - Monitor response quality
   - Track token usage and costs

🚀 NEXT STEPS & RESOURCES:

📖 Official Documentation:
   - API Reference: https://docs.anthropic.com/
   - Python SDK: https://github.com/anthropics/anthropic-sdk-python
   - Cookbook: https://github.com/anthropics/anthropic-cookbook

💡 Advanced Topics to Explore:
   - Prompt engineering techniques
   - Extended context windows (200K tokens)
   - Fine-tuning strategies
   - Caching for cost optimization
   - Multi-modal applications
   - Agentic workflows

🛠️ Useful Tools:
   - Prompt Generator: https://console.anthropic.com/
   - Token Counter: Monitor your usage in the console
   - Workbench: Test prompts in the web interface

📚 Learning Resources:
   - Anthropic Blog: Latest updates and research
   - Community Discord: Get help from other developers
   - Example Projects: Check out the cookbook

🎯 Practice Projects:
   1. Build a customer service chatbot
   2. Create a code review assistant
   3. Develop a document summarizer
   4. Make a creative writing helper
   5. Build a data analysis assistant

Happy coding with Claude! 🤖✨


==================================================
Tutorial Complete! You're ready to build with Anthropic's API!
==================================================