# What is cost per agent step? > Cost per agent step rises as a run goes on, because each step resends the transcript before it. Why doubling steps more than doubles spend. URL: https://getculpa.com/what-is-cost-per-agent-step Last reviewed: 2026-08-01 ## Answer Cost per agent step is the model spend for one call inside an agent run, and it isn't constant across the run. Each step carries the transcript of the steps before it, so input grows as the agent works. Culpa, a local-first LLM cost, margin, and forecast ledger, prices every step individually and shows where in a run the money actually goes. ## Why this happens Teams reason about agent steps as if they were identical units, which makes step count feel like a linear dial. It isn't. Step twenty resends everything steps one through nineteen produced, so input per step climbs with each iteration while output stays roughly flat. Total input across a run grows with the square of the step count rather than in proportion to it. A step budget raised from twenty to forty looks like a doubling and lands as something much larger. ## What this usually looks like - Raising a step limit produced a cost increase far bigger than the ratio of the limits. - Long runs cost disproportionately more than short ones on the same feature. - Input tokens per call climb steadily within a single run and nobody plots that curve. - The agent's most expensive steps are its last ones, which is the opposite of where attention goes. ## Common mistakes - Treating step count as a linear cost dial. Why it hurts: Input accumulates, so total run input grows roughly with the square of the step count. Do instead: Model the run as accumulating context, and price a step budget before raising it. - Resending the full transcript at every step. Why it hurts: Early steps get paid for over and over, once per remaining step in the run. Do instead: Summarise older steps into a compact state object, and keep only recent turns verbatim. - Setting one step budget for every task the agent handles. Why it hurts: Easy tasks finish early and hard ones run to the ceiling, so the ceiling sets your cost, not the work. Do instead: Let the agent stop when it's done, and put the ceiling on accumulated spend rather than on steps. ## Self-check - Plot input tokens against step number for one long run. The slope is your accumulation rate. - Compare the cost of the first step and the last step of the same run. Most teams have never looked. - Take your step limit, double it on paper, and compute the new run cost. It won't be double. - Check what share of runs actually hit the step ceiling. If most do, the ceiling is setting your bill. - Confirm older steps get compacted rather than resent verbatim, and price the difference before deciding. ## Twenty steps, then forty, on the same task (illustrative) An agent on Claude Haiku 4.5 at real rates of $0.001 per 1k input and $0.005 per 1k output. The base prompt is 2,000 tokens, each step adds about 900 tokens of transcript, and each step returns 300 tokens. Those volumes are modelled. Step 1: (2.0 x $0.001) + (0.3 x $0.005) = $0.0020 + $0.0015 = $0.0035 Step 20 input is 2.0k + (19 x 0.9k) = 19.1k: (19.1 x $0.001) + (0.3 x $0.005) = $0.0191 + $0.0015 = $0.0206 Total input over 20 steps = (20 x 2.0k) + (0.9k x 190) = 211k, so 211 x $0.001 = $0.211 Output over 20 steps = 6k, so 6 x $0.005 = $0.030. Run total = $0.241 At 40 steps input becomes (40 x 2.0k) + (0.9k x 780) = 782k, and the run total is $0.842 Step twenty costs six times step one, and doubling the step budget multiplied the run cost by 3.5 rather than by 2. The step count is the dial everyone reaches for, and it isn't the dial that sets the bill. ## Cost figures Every figure carries its confidence and its source. No figure on this site is provider-reported. - $0.0035 to $0.0206 — modelled cost of a single agent step, first step against twentieth, on Claude Haiku 4.5 [estimated] Source: Both endpoints at real Claude Haiku 4.5 rates per 1k tokens from the price book, effective 2026-07-02. A range because the per-step token volumes are modelled. - $0.241 — modelled total cost of a 20-step run before any step-budget increase [calculated] Source: 211k input tokens x $0.001 plus 6k output tokens x $0.005 per 1k, from the teardown arithmetic. ## FAQ Q: Why does a later agent step cost more than an earlier one? A: Because it resends what the earlier steps produced. Output per step stays roughly flat while input climbs with every iteration, so the last step of a long run can cost several times the first one on identical rates. Q: Does doubling the step limit double the cost? A: No, it more than doubles it. Total input across a run grows roughly with the square of the step count, so a run allowed forty steps instead of twenty can cost three to four times as much rather than twice. Q: What's the cheapest way to cut cost per agent step? A: Stop resending the full transcript. Compact older steps into a short state summary and keep only recent turns verbatim. That flattens the accumulation curve, which matters far more on long runs than the per-step rate does. ## Sources - Anthropic pricing: https://platform.claude.com/docs/en/docs/about-claude/pricing Run the free Cost Leak Scan: https://app.getculpa.com/scan?source=pseo&slug=what-is-cost-per-agent-step&cluster=metric Machine-readable index of every guide: https://getculpa.com/api/pages Human-readable index of every guide: https://getculpa.com/guides Site overview: https://app.getculpa.com/llms.txt Privacy: Culpa runs on your infrastructure. Your prompts and responses never leave it. Culpa counts calls to run your plan, and it fails open, so if it ever breaks your app keeps running.