提示缓存：重复发送的上下文至少便宜 10 倍

import anthropic

client = anthropic.Anthropic(base_url="https://www.ruapi.ai", api_key="sk-...")

response = client.messages.create(
    model="claude-sonnet-5-5",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": LONG_SYSTEM_PROMPT,  # 说明、文档、项目代码
            "cache_control": {"type": "ephemeral"},
        }
    ],
    messages=[{"role": "user", "content": "你的问题"}],
)
print(response.usage.cache_read_input_tokens, response.usage.cache_creation_input_tokens)

from openai import OpenAI

client = OpenAI(base_url="https://www.ruapi.ai/v1", api_key="sk-...")

response = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": LONG_SYSTEM_PROMPT,
                    "cache_control": {"type": "ephemeral"},
                }
            ],
        },
        {"role": "user", "content": "你的问题"},
    ],
)
print(response.usage.prompt_tokens_details.cached_tokens)