Skip to main content
This page describes Anthropic’s Prompt Caching feature. To learn more about Anthropic models, see Anthropic Overview.

​
Quick Start

Cache frequently used context (system prompts, large documents, code bases) to reduce costs by up to 90% and latency by up to 85%. 
curl -X POST https://api.orq.ai/v2/router/chat/completions \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "system",
        "content": [
          {
            "type": "text",
            "text": "You are an expert Python developer with deep knowledge of best practices.",
            "cache_control": { "type": "ephemeral" }
          }
        ]
      },
      {
        "role": "user",
        "content": "Write a function to parse JSON"
      }
    ],
    "max_tokens": 1024
  }'

​
How It Works

Prompt caching stores frequently used content blocks on Anthropic’s servers for reuse across requests:
  1. Mark content for caching: Add cache_control: { type: "ephemeral" } to text blocks
  2. First request: Content is processed normally and cached (cache write)
  3. Subsequent requests: Cached content is reused (cache read)
  4. Cache lifetime: 5 minutes from last use (automatically managed)

​
Configuration

Mark content blocks for caching by adding the cache_control parameter:
ParameterTypeRequiredDescription
type"ephemeral"YesOnly supported cache type
ttl"5m" | "1h"NoCache duration (default: "5m")

​
Cache TTL Options

The ttl parameter controls how long cached content persists:
  • "5m" (5 minutes) - Default cache duration
  • "1h" (1 hour) - Extended cache duration for longer-running workflows
{
  "cache_control": {
    "type": "ephemeral",
    "ttl": "1h"
  }
}
The ttl option is only available for Anthropic Claude models.
Cache placement rules:
  • Add cache_control to the last message or content block you want cached
  • Everything up to that point is included in the cache
  • Minimum cacheable content: 1024 tokens (~800 words)
  • Maximum: 4 cache breakpoints per request

​
Supported Models

Prompt caching is available on all current Claude Opus, Sonnet, and Haiku models. For the complete list of supported models, see Anthropic’s official documentation. Provider availability: All models supporting prompt caching are available through anthropic, aws, and google providers.

​
Use Cases

​
Static System Prompts

Cache role definitions and instructions that don’t change: 
curl -X POST https://api.orq.ai/v2/router/chat/completions \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "system",
        "content": [
          {
            "type": "text",
            "text": "You are an expert software engineer specializing in Python.\nYour responses should be:\n- Clear and concise\n- Include code examples\n- Follow PEP 8 style guidelines\n- Include error handling",
            "cache_control": { "type": "ephemeral" }
          }
        ]
      },
      {
        "role": "user",
        "content": "How do I read a CSV file?"
      }
    ],
    "max_tokens": 1024
  }'

​
Large Document Context

Cache documents, codebases, or knowledge bases: 
curl -X POST https://api.orq.ai/v2/router/chat/completions \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Here is our API documentation:\n\n[Large documentation content here...]",
            "cache_control": { "type": "ephemeral" }
          },
          {
            "type": "text",
            "text": "How do I authenticate with the API?"
          }
        ]
      }
    ],
    "max_tokens": 1024
  }'

​
Multi-turn Conversations

Cache conversation history for long interactions: 
curl -X POST https://api.orq.ai/v2/router/chat/completions \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "user",
        "content": "What is Python?"
      },
      {
        "role": "assistant",
        "content": "Python is a high-level programming language..."
      },
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What are its main features?",
            "cache_control": { "type": "ephemeral" }
          }
        ]
      },
      {
        "role": "assistant",
        "content": "Pythons main features include..."
      },
      {
        "role": "user",
        "content": "Can you give me a code example?"
      }
    ],
    "max_tokens": 1024
  }'

​
RAG with Document Collections

Cache retrieved documents for multiple queries: 
curl -X POST https://api.orq.ai/v2/router/chat/completions \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant that answers based on provided context."
      },
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Context:\n[Retrieved document content here...]",
            "cache_control": { "type": "ephemeral" }
          },
          {
            "type": "text",
            "text": "Question: What is the main topic of these documents?"
          }
        ]
      }
    ],
    "max_tokens": 1024
  }'