Prompt Caching with Claude
What is Prompt Caching?
Enables developers to cache frequently used context between API calls, providing Claude with more background knowledge and example outputs.
💾
Now available on the Anthropic API
Key Benefits
- 💰 Reduces costs by up to 90%
- ⚡ Reduces latency by up to 85% for long prompts
- 🧠 Provides more context and examples to Claude
When to Use Prompt Caching
🗨️
Conversational agents: Reduce cost and latency for extended conversations
💻
Coding assistants: Improve autocomplete and codebase Q&A
📄
Large document processing: Incorporate complete long-form material including images
📚
Talk to books and papers: Bring any knowledge base alive for Q&A
Pricing for Cached Prompts
| Action | Cost |
|---|---|
| Writing to cache | 25% more than base input token price |
| Using cached content | Only 10% of base input token price |
Customer Spotlight: Notion
Notion is adding prompt caching to Claude-powered features for Notion AI
"We're excited to use prompt caching to make Notion AI faster and cheaper, all while maintaining state-of-the-art quality."
— Simon Last, Co-founder at Notion
@Anthropic
Tags：Prompt CachingClaude APIreduce costsreduce latencycontext for API callscoding assistantslarge document processingNotion AI