The token tax nobody budgets for — and why it hits the tightest budgets hardest

Most write-ups about AI agents are about prompts, tools, and evals. Almost none are about the line item that quietly dominates a real deployment: the context tokens you pay for on every single turn. Here is the mechanic. A typical agent loop re-sends the whole conversation so far on each step, so the model can "remember" what happened. Turn 1 sends a little. Turn 20 re-sends everything from turns 1–19 again . Across a session, the input-token cost does not grow with the amount of work done — it…