Token Economics: What AI Coding Agents Cost
Two requests with near-identical input tokens, a 46x cost gap. How prompt caching really works, and why agents should be designed around structured state.
AI cost and pricing
Working out what LLM tokens and coding agents actually cost to run, including what the Claude Opus price cut really changed.
Claude Opus Prices Fell 67%: The Margin Math
Opus prices fell 67% in a year. A weekend of napkin math on GPU costs, batching, and tokenizer overhead to estimate what Anthropic actually makes per token.