# Pricing a multi-agent system run by its step count > A modelled agent step costs $0.0240 on Sonnet 5. Three steps is $0.0720 and twenty is $0.4800, and the step count is decided at runtime. URL: https://getculpa.com/multi-agent-cost-calculator Last reviewed: 2026-08-05 Rates effective: 2026-07-02 ## Answer A multi-agent system run costs its per-step bundle times the number of steps it takes, and that count is decided by the model at runtime rather than by your configuration. Culpa, a local-first LLM cost, margin, and forecast ledger, prices every call and groups them by run, so a run reports its own total and its own depth. ## Why this happens Pricing a single agent call is easy and pricing a run is the thing anyone actually needs, because a run is what a user experiences and what a customer is charged for. The difficulty is that the multiplier isn't yours to set. How many steps a task takes gets decided during the run, by the model, based on what it finds, so two runs of the same feature can differ several times over with nothing in your configuration changing. That makes the average run a poor planning unit and the distribution the thing to look at. A second effect the simple multiplication misses, and this calculator deliberately leaves it out: each step re-sends the conversation before it, so input grows with step number and a long run costs more than its step count suggests. Treat the figure here as a floor. It's the right floor, and it's the number most teams lack entirely. ## What this usually looks like - You know cost per call and not cost per run. - Two runs of the same feature differ several times in cost. - Nobody records how many steps a run took. - Your pricing assumes an average run depth nobody measured. - A run occasionally costs many times the typical one and nothing flagged it. ## Common mistakes - Pricing a run from cost per call. Why it hurts: A run is an unknown number of calls, so per-call cost says nothing about what a task costs. Do instead: Group calls by run, and report cost per run with its step count beside it. - Planning from the average run. Why it hurts: Run depth is decided at runtime and is usually skewed, so the average hides the expensive tail. Do instead: Look at the distribution, and price the top decile of runs separately. - Treating this multiplication as the whole cost. Why it hurts: Each step re-sends the history, so input grows with depth and the simple product is a floor. Do instead: Use it as a floor, then measure real runs to see how far above it you land. - Capping output per request and calling it a budget. Why it hurts: That bounds one step, and nothing bounds the number of steps a run may take. Do instead: Cap the step count too, which is the only limit that bounds a run. ## Self-check - Find the step count of your longest run last week and price it above. - Compare that against your median run, priced the same way. - Check whether anything limits how many steps a run may take. - Measure a real run's total against this calculator's floor and note the gap. ## The same step, at three depths (illustrative) A modelled agent step of 8,000 input and 800 output tokens, priced on Claude Sonnet 5 at its real introductory rates of $2.00 and $10.00 per million from the price book effective 2026-07-02. The same step is multiplied by three run depths. Rates are published, the step shape and the depths are modelled, and the figures exclude the context growth described above. one step: 8,000 x $2.00/M + 800 x $10.00/M = $0.0160 + $0.0080 = $0.0240 a 3-step run: $0.0240 x 3 = $0.0720 a 7-step run: $0.0240 x 7 = $0.1680 a 20-step run: $0.0240 x 20 = $0.4800 the deepest run costs 6.67 times the shallowest, on identical steps Nothing about the step changed across those three rows. The only variable is a number the model chose during the run, which is why a per-call cost tells you so little here and why the step count belongs beside every run total you report. ## Cost figures Every figure carries its confidence and its source. No figure on this page is provider-reported. - $0.0240 a step, modelled cost of one agent step at 8,000 input and 800 output tokens on Claude Sonnet 5 [calculated] Source: 8,000 input at $2.00 per million is $0.0160 and 800 output at $10.00 per million is $0.0080, giving $0.0240, using the price book's real Claude Sonnet 5 introductory rates effective 2026-07-02. Multiplied by modelled depths that gives $0.0720 at 3 steps, $0.1680 at 7 and $0.4800 at 20, a ratio of 6.67 between the deepest and shallowest. Rates are published, the step shape and depths are modelled, and the figures exclude context growth across steps. ## FAQ Q: How do I calculate the cost of a multi-agent run? A: Price one step's token bundle, then multiply by the step count. In the modelled example a step of 8,000 input and 800 output tokens costs $0.0240 on Claude Sonnet 5, so a 3-step run is $0.0720 and a 20-step run is $0.4800. Q: Why do two runs of the same feature cost differently? A: Step count. How many times the loop goes round is decided during the run by the model, based on what it finds, so identical requests can take three steps or twenty. In the modelled example that alone is a 6.67 times difference. Q: Is this calculator the full cost of a run? A: It's a floor, deliberately. Each step re-sends the conversation before it, so input grows with depth and a real run costs more than the simple product. The floor is still worth having, because most teams have no per-run figure at all. Q: How do I stop a run from getting expensive? A: Limit the number of steps. A per-request output cap bounds one step and nothing bounds the loop, so a ten-step run costs ten times whatever anyone thought the ceiling was. The step limit is the only one that binds a run. ## 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=multi-agent-cost-calculator&cluster=problem 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.