According to Anthropic (@AnthropicAI), the company has launched a new 1-hour prompt caching TTL option in addition to the standard 5-minute interval. This upgrade can cut costs by up to 90% and decrease latency by up to 85% for long prompts, making extended AI agent workflows significantly more efficient (Source: Anthropic Twitter, May 22, 2025). For crypto traders and algorithmic trading platforms leveraging AI, this improvement enables faster, more cost-effective market analysis and automation, potentially increasing trading frequency and improving real-time decision-making capabilities.