프롬프트 캐싱

curl https://aihubmix.com/v1/messages \
  -H "content-type: application/json" \
  -H "x-api-key: $AIHUBMIX_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-opus-4-6",
    "max_tokens": 1024,
    "system": [
      {
        "type": "text",
        "text": "You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n"
      },
      {
        "type": "text",
        "text": "<the entire contents of Pride and Prejudice>",
        "cache_control": {"type": "ephemeral"}
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": "Analyze the major themes in Pride and Prejudice."
      }
    ]
  }'

# Call the model again with the same input until the caching checkpoint
curl https://aihubmix.com/v1/messages # rest of input

import anthropic

client = Anthropic(
  api_key="<AIHUBMIX_API_KEY>",  
  base_url="https://aihubmix.com"
)

params = {
    "model": "claude-opus-4-6",
    "max_tokens": 1024,
    "system": [
        {
            "type": "text",
            "text": "You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n",
        },
        {
            "type": "text",
            "text": "<the entire contents of 'Pride and Prejudice'>",
            "cache_control": {"type": "ephemeral"},
        },
    ],
    "messages": [
        {
            "role": "user",
            "content": "Analyze the major themes in 'Pride and Prejudice'.",
        }
    ],
}
response = client.messages.create(**params)
print(response.usage.model_dump_json())

# Call the model again with the same input until the caching checkpoint
response = client.messages.create(**params)
print(response.usage.model_dump_json())