Cheap Tokens, Expensive Scripts

Picking an LLM on price per token is the easy mistake. This episode walks through a real evaluation for the show's own script-writing pipeline — a 26,000-token input with a 9,000-token cached prefix and 6,500 tokens out — and shows how a model with a worse input price can win the bill by a sixth, then lose once caching is off or thinking tokens triple the output. We cover why blended leaderboard pricing misleads, why hidden reasoning tokens are billed as the expensive kind, how OpenRouter host pinning and quantization quietly change your quality score, and why you should estimate to screen but measure to decide. Episode 6134 — myweirdprompts.com/n/6134 (permanent short link: myweirdprompts.com/018539)