Prompt Caching: The Architecture Change That Cuts Your LLM Costs in Half
中文摘要
提示词缓存技术可将大模型成本降低一半，Anthropic、OpenAI和Google均已推出。
English Summary
Prompt caching cuts LLM costs in half, with support from Anthropic, OpenAI, and Google.
Original Excerpt
Anthropic just released prompt caching. OpenAI has it. Google too. Continue reading on Medium »