Token savings are great, but I wonder whether the biggest long-term benefit is latency reduction rather then API cost,Faster feedback loops can easily outweigh a few cents saved per request
Vendor lock-in has always been a concern, but AI workloads make the conversation even more important. Designing portable architectures from day one is becoming a competitive advantage.
This is a great reminder that many of today's "breakthroughs" were imagined decades ago. What's changed isn't just the technology, but the economics and engineering needed to make it practical