BriefTea
Every story in sixty words
Get the free app no ads · no paywallExplained in plain English
AI models typically charge based on the amount of data 'input' (what you tell the AI) and 'output' (what the AI tells you). Anthropic has kept these prices stable but significantly cut the cost of reading 'cached context'. This means if the AI needs to re-read information it's already processed, it's much cheaper, leading to overall savings, especially for complex tasks.
Stories that explain this
Anthropic launches Fable 5.1 with cheaper cached promptsRelated explainers
What are AI 'tokens'? Who is Anthropic? Why cache AI prompts? How does AI dynamic pricing work? Why AI pricing is broken What is carbon pricing? Why do diners dislike AI pricing? What is drip pricing?The full catalogue
Browse every card filed under A →We would like to count visits and see which links bring readers here. That means storing a random ID in your browser. No cookies, no ads, no profile. How it works.