BriefTea
Every story in sixty words
Explained 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 999 work? How do aerial platforms work? How do AI checkouts work? Why does AI make work harder? How does AI 'memory' work?The full catalogue
Browse every card filed under A →