← Course | Module 02 - The API Lesson 8
MODULE 02

Multi-Turn Conversations: Managing Message History

🕑 12 min read 🎯 Beginner

How Conversations Work

Claude doesn't remember previous conversations. Every API call, you send the entire conversation history. Claude reads it all and responds to the latest message.

# Multi-turn conversation messages = [ {"role": "user", "content": "My name is Alex."}, {"role": "assistant", "content": "Nice to meet you, Alex!"}, {"role": "user", "content": "What's my name?"}, ] response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=messages ) # Claude will say "Your name is Alex" - because it's in the history

The Cost Problem

Every message sends the FULL history. As conversations grow, costs multiply:

Message #History SizeInput Cost (Sonnet)
1100 tokens$0.0003
52,000 tokens$0.006
2015,000 tokens$0.045
5040,000 tokens$0.12
Solution: Sliding window + summary

Keep the last 10 messages verbatim. Summarize everything older into a single "context" message at the start. This caps your history size while preserving important context.

Key Takeaways

🖨 Download PDF 🐦 Share on X
← Previous