Your coding agent's cache hit rate is the bill nobody reads

Your coding agent sends almost the same prompt on every turn. The whole conversation so far, plus one new message. If the provider still has that prompt in cache, the turn is cheaper and faster. If

Your coding agent sends almost the same prompt on every turn. The whole conversation so far, plus one new message. If the provider still has that prompt in cache, the turn is cheaper and faster. If not, you pay to read it all again. Most teams never see which one happened. Vercel just made it visible, and the fix is one header. What shipped Vercel's AI Gateway logs now have a Sessions view. A gateway is the layer between your app and the model providers. It routes each request to a provider that