You Put the Time at the Top of the Prompt and Paid Full Price Every Call
This story is from 2026-10-15. It is preserved in the archive; the latest stories are on the live feed.
The prompt was long and mostly fixed. Four thousand tokens of instructions, the product manual, a dozen examples. Then the user's question at the bottom. The provider offered prompt caching. Somebody turned it on. The bill did not move. The latency did not move. The dashboard showed almost no cache…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-15 05:33 · DEV Community — AI
You Put the Time at the Top of the Prompt and Paid Full Price Every Call