11 min read
5 Anthropic Prompt Caching Patterns That Cut My API Bill 70%
System-prompt caching alone cut repeat-call costs by half
The Lab · Written in the open · Tagged Cost
Working notes from the studio. The tools I build, the workflows I keep, the mistakes I paid for.
2 entries · latest 2026-06-07
Latest entry
1M context costs full price on every query, caching cuts repeated tokens to 1/10 Use 1M for one-shot deep dives, caching for repeated calls against fixed docs Hybrid: cache the stable 80%, stream the dynamic 20% fresh Real numbers from...
Read the entryAll entries · Cost
11 min read
System-prompt caching alone cut repeat-call costs by half