[ ABORT TO HUD ]
SEQ. 1
SEQ. 2

Defining Cache Breakpoints

Prompt Caching Framework20 min350 BASE XP

Strategic Context Storage

Anthropic's Prompt Caching allows developers to persist large prefixes (like system instructions or tool definitions) in the model's high-speed memory. Unlike automatic caching systems, Anthropic requires explicit markers. You must append a cache_control object set to {"type": "ephemeral"} at specific breakpoints in your request array.

The 4-Breakpoint Constraint

A single API request can contain a maximum of 4 cache breakpoints. This limit forces developers to be strategic: typically, you would cache your system prompt at breakpoint 1, your tool definitions at breakpoint 2, and maybe a large set of reference 'knowledge documents' at breakpoint 3. This leaves the final user-turn volatile while keeping the heavy repetitive context 'warm' in the cluster.

Architecture Note: Hashing is performed on the entire prefix up to the breakpoint. Even a single character change before a breakpoint will invalidate the cache for that block and all subsequent blocks.
SYNAPSE VERIFICATION
QUERY 1 // 3
How is a cache boundary physically marked in the Anthropic schema?
By checking a box in the Console
By appending a cache_control object set to 'ephemeral' inside specific content arrays
By putting the context in XML tags
Using an external Redis database
Watch: 139x Rust Speedup
Defining Cache Breakpoints | Prompt Caching Framework — Claude Academy