OpenAI Prompt Caching 실전 가이드: 비용과 지연 시간 최적화 전략

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    prompt_cache_key="user_123_session_abc"
)

response = client.with_options(timeout=900.0).responses.create(
    model="o1",
    instructions="List and describe all the metaphors used in this book.",
    input="<very long text of book here>",
    service_tier="flex"
)

{
  "model": "gpt-5.1",
  "input": "Your prompt goes here...",
  "prompt_cache_retention": "24h"
}