{
  "model": "anthropic/claude-3-5-sonnet-20241022",
  "messages": [
    {
      "role": "system", 
      "content": [
        {
          "type": "text",
          "text": "You are a senior software architect with 15 years of experience in distributed systems, microservices, and cloud architecture. When reviewing code, you focus on scalability, maintainability, security best practices, and performance optimization. You provide detailed technical feedback with specific examples and always suggest concrete improvements...",
          "cache_control": {
            "type": "ephemeral"
          }
        }
      ]
    },
    {
      "role": "user",
      "content": "Review this API design for our new user service"
    }
  ]
}

import requests

def create_cached_request(user_message):
    url = "https://api.anyapi.ai/api/v1/chat/completions"
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    
    # Your expensive system prompt (cache this baby!)
    system_prompt = """
    You are an expert financial advisor with CFA certification and 20 years 
    of experience in portfolio management, risk assessment, and investment 
    strategy. You provide detailed analysis based on current market conditions,
    regulatory requirements, and best practices in wealth management...
    """ # Imagine this is 3000+ tokens
    
    payload = {
        "model": "anthropic/claude-3-5-sonnet-20241022",
        "messages": [
            {
                "role": "system",
                "content": [
                    {
                        "type": "text",
                        "text": system_prompt,
                        "cache_control": {"type": "ephemeral"}
                    }
                ]
            },
            {
                "role": "user",
                "content": user_message
            }
        ]
    }
    
    return requests.post(url, headers=headers, json=payload)

# First call: Pay cache write cost
response1 = create_cached_request("Analyze my portfolio allocation")

# Subsequent calls: Pay only 10% for cached system prompt!
response2 = create_cached_request("What's your take on crypto exposure?")
response3 = create_cached_request("Should I rebalance before year-end?")

# Structure your prompts for maximum cache hits
base_system = {
    "type": "text", 
    "text": "Your massive, reusable system prompt...",
    "cache_control": {"type": "ephemeral"}
}

# Reuse the exact same cached content across requests
def make_request(user_input):
    return {
        "model": "anthropic/claude-3-5-sonnet-20241022",
        "messages": [
            {"role": "system", "content": [base_system]},
            {"role": "user", "content": user_input}
        ]
    }

# Track your cache performance
def analyze_cache_savings(requests_made, avg_system_tokens, hit_rate):
    original_cost = requests_made * avg_system_tokens * INPUT_PRICE
    
    # Anthropic example: 1.25x write + 0.1x reads
    cache_cost = (avg_system_tokens * INPUT_PRICE * 1.25) + \
                 (requests_made * hit_rate * avg_system_tokens * INPUT_PRICE * 0.1)
    
    savings = original_cost - cache_cost
    print(f"You saved: ${savings:.2f} ({savings/original_cost*100:.1f}%)")