Agent Cost Analysis

Agent cost is non-linear due to context accumulation: 1000 tokens are sent on step 1, 2000 on step 2, 3000 on step 3, totaling 6000 instead of 3000. Amplifying factors: reasoning tokens (paid for but not shown), large tool results (paid for on each subsequent step), wrong path (10 steps instead of 3). Three main optimization levers: KV Cache reuse (-30-60% input cost), context compression, multi-level model routing. Plus cost monitoring and task budget.

Related: KV Cache, [Context Compression], [Three levels of evaluation system]