HomeBriefFor youTrackersTopicsCompaniesGlossaryNewsletterSecurityHealth & medicineFinance & marketsRoboticsModels & researchPolicy & regulationEnterprise & businessDeveloper tools
Glossary

Prompt caching

Charging a reduced rate for the repeated prefix of a prompt, such as a system prompt or a document reused across requests.

Cache reads cost 2.5% to 10% of the input price at the major vendors. Put stable content first in the prompt to benefit.

Related terms

Active parametersAPIAttentionLarge language model (LLM)Latency

← All terms

Get the brief in your inbox

One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.

Published daily by AI Briefing. We never share your address.
Like this? Get tomorrow's brief by email, free.