Skip to main content

Prompt Caching

Supported Providers:

haimaker follows the OpenAI prompt caching usage object format:

"usage": {
  "prompt_tokens": 2006,
  "completion_tokens": 300,
  "total_tokens": 2306,
  "prompt_tokens_details": {
    "cached_tokens": 1920
  },
  "completion_tokens_details": {
    "reasoning_tokens": 0
  },
  "cache_creation_input_tokens": 0
}
  • prompt_tokens: All prompt tokens including cache-miss and cache-hit input tokens.
  • completion_tokens: Output tokens generated by the model.
  • total_tokens: Sum of prompt_tokens + completion_tokens.
  • prompt_tokens_details.cached_tokens: Tokens that were a cache-hit for that call.
  • ANTHROPIC_ONLY: cache_creation_input_tokens - Number of tokens that were written to cache (Anthropic charges for this).

Quick Start​

Note: OpenAI caching is only available for prompts containing 1024 tokens or more.

Python​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

for _ in range(2):
    response = client.chat.completions.create(
        model="openai/gpt-4o",
        messages=[
            {
                "role": "system",
                "content": [
                    {
                        "type": "text",
                        "text": "Here is the full text of a complex legal agreement" * 400,
                    }
                ],
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "What are the key terms and conditions in this agreement?",
                    }
                ],
            },
            {
                "role": "assistant",
                "content": "Certainly! the key terms and conditions are the following: the contract is 1 year long for $10/mo",
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "What are the key terms and conditions in this agreement?",
                    }
                ],
            },
        ],
        temperature=0.2,
        max_tokens=10,
    )

print("response=", response)
print("response.usage=", response.usage)

# On second call, cached_tokens should be > 0
assert response.usage.prompt_tokens_details.cached_tokens > 0

Anthropic Example​

Anthropic charges for cache writes.

Specify the content to cache with "cache_control": {"type": "ephemeral"}.

If you pass that in for any other LLM provider, it will be ignored.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet-20240620",
    messages=[
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": "You are an AI assistant tasked with analyzing legal documents.",
                },
                {
                    "type": "text",
                    "text": "Here is the full text of a complex legal agreement" * 400,
                    "cache_control": {"type": "ephemeral"},
                },
            ],
        },
        {
            "role": "user",
            "content": "what are the key terms and conditions in this agreement?",
        },
    ]
)

print(response.usage)

Deepseek Example​

Works the same as OpenAI.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

messages_1 = [
    {
        "role": "system",
        "content": "You are a history expert. The user will provide a series of questions, and your answers should be concise and start with `Answer:`",
    },
    {
        "role": "user",
        "content": "In what year did Qin Shi Huang unify the six states?",
    },
    {"role": "assistant", "content": "Answer: 221 BC"},
    {"role": "user", "content": "Who was the founder of the Han Dynasty?"},
    {"role": "assistant", "content": "Answer: Liu Bang"},
    {"role": "user", "content": "Who was the last emperor of the Tang Dynasty?"},
    {"role": "assistant", "content": "Answer: Li Zhu"},
    {
        "role": "user",
        "content": "Who was the founding emperor of the Ming Dynasty?",
    },
    {"role": "assistant", "content": "Answer: Zhu Yuanzhang"},
    {
        "role": "user",
        "content": "Who was the founding emperor of the Qing Dynasty?",
    },
]

messages_2 = [
    {
        "role": "system",
        "content": "You are a history expert. The user will provide a series of questions, and your answers should be concise and start with `Answer:`",
    },
    {
        "role": "user",
        "content": "In what year did Qin Shi Huang unify the six states?",
    },
    {"role": "assistant", "content": "Answer: 221 BC"},
    {"role": "user", "content": "Who was the founder of the Han Dynasty?"},
    {"role": "assistant", "content": "Answer: Liu Bang"},
    {"role": "user", "content": "Who was the last emperor of the Tang Dynasty?"},
    {"role": "assistant", "content": "Answer: Li Zhu"},
    {
        "role": "user",
        "content": "Who was the founding emperor of the Ming Dynasty?",
    },
    {"role": "assistant", "content": "Answer: Zhu Yuanzhang"},
    {"role": "user", "content": "When did the Shang Dynasty fall?"},
]

response_1 = client.chat.completions.create(model="deepseek/deepseek-chat", messages=messages_1)
response_2 = client.chat.completions.create(model="deepseek/deepseek-chat", messages=messages_2)

print(response_2.usage)