import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": "You are a helpful assistant with access to a large knowledge base...",
            "cache_control": {"type": "ephemeral"}  # Cache this content
        }
    ],
    messages=[{"role": "user", "content": "What is...?"}]
)

# Best for: Document analysis, Q&A with static context
system = [
    {
        "type": "text",
        "text": large_document_content,
        "cache_control": {"type": "ephemeral"}  # Single breakpoint at end
    }
]

# Cache grows with conversation
messages = [
    {"role": "user", "content": "First question"},
    {"role": "assistant", "content": "First answer"},
    {
        "role": "user",
        "content": "Follow-up question",
        "cache_control": {"type": "ephemeral"}  # Cache entire conversation
    }
]

system = [
    {
        "type": "text",
        "text": "Tool definitions and instructions",
        "cache_control": {"type": "ephemeral"}  # Breakpoint 1: Tools
    },
    {
        "type": "text",
        "text": retrieved_documents,
        "cache_control": {"type": "ephemeral"}  # Breakpoint 2: Documents
    }
]

# Warm the cache before batch
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=100,
    system=[{
        "type": "text",
        "text": shared_context,
        "cache_control": {"type": "ephemeral", "ttl": "1h"}
    }],
    messages=[{"role": "user", "content": "Initialize cache"}]
)

# Now run batch - all requests hit the cache
for item in batch_items:
    response = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=1024,
        system=[{
            "type": "text",
            "text": shared_context,
            "cache_control": {"type": "ephemeral", "ttl": "1h"}
        }],
        messages=[{"role": "user", "content": item}]
    )

response = client.messages.create(...)

# Monitor these fields
cache_write = response.usage.cache_creation_input_tokens  # New cache written
cache_read = response.usage.cache_read_input_tokens       # Cache hit!
uncached = response.usage.input_tokens                    # After breakpoint

print(f"Cache hit rate: {cache_read / (cache_read + cache_write + uncached) * 100:.1f}%")

def calculate_cost(usage, model="claude-sonnet-4-20250514"):
    # Example rates (check current pricing)
    base_input_rate = 0.003  # per 1K tokens

    write_cost = (usage.cache_creation_input_tokens / 1000) * base_input_rate * 1.25
    read_cost = (usage.cache_read_input_tokens / 1000) * base_input_rate * 0.1
    uncached_cost = (usage.input_tokens / 1000) * base_input_rate

    return write_cost + read_cost + uncached_cost

# Cache + Extended Thinking
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    system=[{
        "type": "text",
        "text": large_context,
        "cache_control": {"type": "ephemeral"}
    }],
    messages=[{"role": "user", "content": "Analyze this..."}]
)