Prompt Caching

import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": "You are an expert legal assistant. Here is the "
                    "complete contract document you must analyze...\n\n"
                    "[... 15,000 tokens of contract text ...]",
            "cache_control": {"type": "ephemeral"}  # ← Cache this!
        }
    ],
    messages=[
        {"role": "user", "content": "Summarize the key obligations."}
    ]
)

# Check cache performance in the response
usage = response.usage
print(f"Input tokens:        {usage.input_tokens}")
print(f"Cache creation:      {usage.cache_creation_input_tokens}")
print(f"Cache read (hits):   {usage.cache_read_input_tokens}")
# First request:  cache_creation = 15000, cache_read = 0
# Second request: cache_creation = 0,     cache_read = 15000  ← 90% cheaper!