System-prompt caching alone cut repeat-call costs by half Tool definitions cache separately, perfect...
System-prompt caching alone cut repeat-call costs by half
Tool definitions cache separately, perfect for agent loops
Conversation history caching pays off after turn three
1-hour TTL beats the default 5 minutes for batch jobs
My Anthropic API bill dropped 70 percent last month and I did not change a single model. I changed where the cache breakpoints went. Here are the five patterns I now use on every Claude integration I ship.
Originally published at kalyna.pro If your app sends the same large system prompt, tool...
How Anthropic's prompt cache works mechanically — the ephemeral cache_control marker, the two-tier write premium (1.25x for 5-min…
My Anthropic bill doubled two months in a row. Not because I was building something bigger — because...
I kept watching my Claude Code bill climb through long sessions, and most of it was not new work. It...
Block-hash and radix-tree prefix caching in vLLM and SGLang — when it actually saves prefill cost, and the eviction policies that…
We run an AI companion bot. Every chat turn, the model sees the same ~5K-token prefix — character...
