Anthropic のプロンプトキャッシュ — 30分で入力料金を90%削減

# What most people start with: every call re-pays for the whole prompt.
import anthropic

client = anthropic.Anthropic(
    api_key="sk-kn-...",
    base_url="https://api.kunavo.com",
)

SYSTEM = open("system-prompt.md").read()        # 18,000 tokens of rules + examples

# 10 user questions in a session. Every call sends the 18K-token system block.
for question in questions:
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=600,
        system=SYSTEM,
        messages=[{"role": "user", "content": question}],
    )

# Cost per call (input only): 18,000 × $3 / 1M = $0.054
# 10 calls: $0.54 in input alone.

# The fix: mark the static prefix as cacheable. After the first call,
# subsequent calls within ~5 minutes pay 10% the input rate on the cached
# portion. Same answer, 89% cheaper.
resp = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=600,
    system=[
        {
            "type": "text",
            "text": SYSTEM,
            "cache_control": {"type": "ephemeral"},  # mark cacheable
        }
    ],
    messages=[{"role": "user", "content": question}],
)

# First call (cache write):  18,000 × $3.75 / 1M = $0.0675  (1.25× input)
# Calls 2–10 (cache hit):    18,000 × $0.30 / 1M = $0.0054 each
# Total: $0.0675 + 9 × $0.0054 = $0.116  (was $0.54 — 78.5% saved)

# OpenAI Chat Completions style — Kunavo sets the breakpoints for you.
# No flag to set. The "usage" object tells you what was cached.
from openai import OpenAI

client = OpenAI(
    api_key="sk-kn-...",
    base_url="https://api.kunavo.com/v1",
)

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[
        {"role": "system", "content": LONG_SYSTEM_PROMPT},  # >1024 tokens
        {"role": "user", "content": "Latest question…"},
    ],
)

# In the response:
#   resp.usage.prompt_tokens_details.cached_tokens  →  17,800
#   resp.usage.prompt_tokens                        →  18,200
# 17.8K/18.2K = 98% of input came from cache. Bill reflects that automatically.

# Anthropic supports up to 4 cache breakpoints per request — use them
# to keep the cache hot even as later layers change.
client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=600,
    system=[
        {"type": "text",
         "text": ROLE_AND_RULES,                      # ~3,000 tokens
         "cache_control": {"type": "ephemeral"}},     # breakpoint 1
        {"type": "text",
         "text": LARGE_KNOWLEDGE_BASE,                # ~15,000 tokens, rarely changes
         "cache_control": {"type": "ephemeral"}},     # breakpoint 2
    ],
    messages=[
        {"role": "user",
         "content": [
             {"type": "text",
              "text": CONVERSATION_HISTORY,           # grows each turn
              "cache_control": {"type": "ephemeral"}}, # breakpoint 3
             {"type": "text", "text": new_question},
         ]},
    ],
)

# When CONVERSATION_HISTORY changes, breakpoints 1+2 still hit cache.
# Only breakpoint 3 + the new question pay full input rate.

# Always read usage. If cached_tokens is 0 when you expected a hit,
# something's wrong — usually a non-deterministic prefix.
resp = client.messages.create(...)
u = resp.usage
print({
    "input_uncached":  u.input_tokens,
    "input_cache_read": u.cache_read_input_tokens,
    "input_cache_write": u.cache_creation_input_tokens,
    "output": u.output_tokens,
})

# A common gotcha: putting today's date or a request_id in the system prompt
# silently invalidates the cache. Hash your inputs; verify cache_read_input_tokens
# is non-zero on the 2nd identical call.