Features

Automatic Caching: Passive caching that automatically identifies repeated context content without changing API call methods (In contrast, the caching mode that requires explicitly setting parameters in the Anthropic API is called “Explicit Prompt Caching”, see Explicit Prompt Caching (Anthropic API))
Cost Reduction: Input tokens that hit the cache are billed at a lower price, significantly saving costs
Speed Improvement: Reduces processing time for repeated content, accelerating model response

This mechanism is particularly suitable for the following scenarios:

System prompt reuse: In multi-turn conversations, system prompts typically remain unchanged
Fixed tool lists: Tools used in a category of tasks are often consistent
Multi-turn conversation history: In complex conversations, historical messages often contain a lot of repeated information

Scenarios that meet the above conditions can effectively save token consumption and speed up response times using the caching mechanism.

Code Examples

Anthropic SDK Example
OpenAI SDK Example

Install SDK

pip install anthropic

Environment Variable Setup

export ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic
export ANTHROPIC_API_KEY=${YOUR_API_KEY}

First Request - Establish Cache

  import anthropic

  client = anthropic.Anthropic()

response1 = client.messages.create(
      model="MiniMax-M2.7",
    system="You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n",
      messages=[
          {
              "role": "user",
              "content": [
                  {
                      "type": "text",
                    "text": "<the entire contents of 'Pride and Prejudice'>"
                }
            ]
        },
    ],
    max_tokens=10240,
)

print("First request result:")
for block in response1.content:
    if block.type == "thinking":
        print(f"Thinking:\n{block.thinking}\n")
    elif block.type == "text":
        print(f"Output:\n{block.text}\n")
print(f"Input Tokens: {response1.usage.input_tokens}")
print(f"Output Tokens: {response1.usage.output_tokens}")
print(f"Cache Hit Tokens: {response1.usage.cache_read_input_tokens}")

Second Request - Reuse Cache

response2 = client.messages.create(
    model="MiniMax-M2.7",
    system="You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n",
    messages=[
          {
              "role": "user",
              "content": [
                  {
                      "type": "text",
                    "text": "<the entire contents of 'Pride and Prejudice'>"
                }
            ]
        },
    ],
    max_tokens=10240,
)

print("\nSecond request result:")
for block in response2.content:
    if block.type == "thinking":
        print(f"Thinking:\n{block.thinking}\n")
    elif block.type == "text":
        print(f"Output:\n{block.text}\n")
print(f"Input Tokens: {response2.usage.input_tokens}")
print(f"Output Tokens: {response2.usage.output_tokens}")
print(f"Cache Hit Tokens: {response2.usage.cache_read_input_tokens}")

Response includes context cache token usage information:

{
    "usage": {
        "input_tokens": 108,
        "output_tokens": 91,
        "cache_creation_input_tokens": 0,
        "cache_read_input_tokens": 14813
    }
}

Install SDK

pip install openai

Environment Variable Setup

export OPENAI_BASE_URL=https://api.minimax.io/v1
export OPENAI_API_KEY=${YOUR_API_KEY}

First Request - Establish Cache

from openai import OpenAI

client = OpenAI()

response1 = client.chat.completions.create(
    model="MiniMax-M2.7",
    messages=[
        {"role": "system", "content": "You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n"},
        {"role": "user", "content": "<the entire contents of 'Pride and Prejudice'>"},
    ],
    # Set reasoning_split=True to separate thinking content into reasoning_details field
    extra_body={"reasoning_split": True},
)

print("First request result:")
print(f"Response: {response1.choices[0].message.content}")
print(f"Total Tokens: {response1.usage.total_tokens}")
print(f"Cached Tokens: {response1.usage.prompt_tokens_details.cached_tokens if hasattr(response1.usage, 'prompt_tokens_details') else 0}")

Second Request - Reuse Cache

response2 = client.chat.completions.create(
    model="MiniMax-M2.7",
    messages=[
        {"role": "system", "content": "You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n"},
        {"role": "user", "content": "<the entire contents of 'Pride and Prejudice'>"},
    ],
    # Set reasoning_split=True to separate thinking content into reasoning_details field
    extra_body={"reasoning_split": True},
)

print("\nSecond request result:")
print(f"Response: {response2.choices[0].message.content}")
print(f"Total Tokens: {response2.usage.total_tokens}")
print(f"Cached Tokens: {response2.usage.prompt_tokens_details.cached_tokens if hasattr(response2.usage, 'prompt_tokens_details') else 0}")

Response includes context cache token usage information:

{
    "usage": {
        "prompt_tokens": 1200,
        "completion_tokens": 300,
        "total_tokens": 1500,
        "prompt_tokens_details": {
            "cached_tokens": 800
        }
    }
}

Important Notes

Caching applies to API calls with 512 or more input tokens
Caching uses prefix matching, constructed in the order of “tool list → system prompts → user messages”. Changes to any module’s content may affect caching effectiveness

Best Practices

Place static or repeated content (including tool list, system prompts, user messages) at the beginning of the conversation, and put dynamic user information at the end of the conversation to maximize cache utilization
Monitor cache performance through the usage tokens returned by the API, and regularly analyze to optimize your usage strategy

Pricing

Prompt caching uses differentiated pricing:

Cache hit tokens: Billed at discounted price
New input tokens: Billed at standard input price
Output tokens: Billed at standard output price

See the Pricing page for details.

Pricing example:

Assuming standard input price is $10/1M tokens, standard output price is $40/1M tokens, cache hit price is $1/1M tokens:

Single request token usage details:
- Total input tokens: 50000
- Cache hit tokens: 45000
- New input content tokens: 5000
- Output tokens: 1000

Billing calculation:
- New input content cost: 5000 × 10/1000000 = $0.05
- Cache cost: 45000 × 1/1000000 = $0.045
- Output cost: 1000 × 40/1000000 = $0.04
- Total cost: 0.05 + 0.045 + 0.04 = $0.135

Compared to no caching (50000 × 10/1000000 + 1000 × 40/1000000 = $0.54), saves 75%

Cache Comparison

	Prompt Caching (Passive)	Explicit Prompt Caching (Anthropic API)
Usage	Automatically identifies and caches repeated content	Explicitly set cache_control in API
Billing	Cache hit tokens billed at discounted price No additional charge for cache writes	Cache hit tokens billed at discounted price First-time cache writes incur additional charges
Expiration	Expiration time automatically adjusted based on system load	5-minute expiration, automatically renewed with continued use
Supported Models	MiniMax-M2.7 series MiniMax-M2.5 series MiniMax-M2.1 series	MiniMax-M2.7 series MiniMax-M2.5 series MiniMax-M2.1 series MiniMax-M2 series

Get started

Use Guides

FAQs

Terms & Policy

Prompt Caching

Features

Code Examples

Important Notes

Best Practices

Pricing

Further Reading

Explicit Prompt Caching (Anthropic API)

Cache Comparison

Get started

Use Guides

FAQs

Terms & Policy

Documentation Index

​Features

​Code Examples

​Important Notes

​Best Practices

​Pricing

​Further Reading

Explicit Prompt Caching (Anthropic API)

​Cache Comparison

Features

Code Examples

Important Notes

Best Practices

Pricing

Further Reading

Cache Comparison