How to use the review
Record the usual token and tool costs, the cost of a repair cycle and how many cycles can occur. Set one budget for the whole task. Decide what happens when the next attempt would exceed it.
Your numbers stay in your browser. They are not sent or stored, and the check needs no sign-up. The workbook download asks for your name, role and email address first.
Four numbers about a normal task
Cost one round of each
Whatever sent the work back, a round costs the same three things: the steps that run again, the check that re-reads the new attempt, and the extra context the redo carries. Add only the paths your workflow actually has. Zero is a real answer; blank is not.
-
Transport refusal
429 rate limit, 503 unavailable, or a timeout
The model or tool API did not answer. This is a failure to reach the service, not a problem with the output.
Bites at peak only Context grows no Attempt billed usually not
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
-
Judge / critic rejection
an LLM-as-judge fails the draft
A model or a rubric reads the finished output, decides it is not good enough, and sends it back with feedback.
Bites every run Context grows yes Attempt billed yes
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
-
Validation failure
bad JSON, schema mismatch, guardrail trip
The output did not parse, did not match the schema, or tripped a guardrail, so the model has to produce it again.
Bites every run Context grows usually Attempt billed yes
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
-
Tool error
not found, permission denied, bad arguments
A tool the agent called returned an error: not found, permission denied, bad arguments. The agent has to re-plan or try again.
Bites every run Context grows yes Attempt billed yes
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
-
Human rejection
a maker-checker sends it back
A person reviewing the work sends it back. Their reading costs no tokens; the redo does.
Bites every run Context grows yes Attempt billed yes
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
-
name it yourself
Anything else in your system that makes model work happen a second time.
Bites you decide Context grows you decide Attempt billed
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
-
name it yourself
Anything else in your system that makes model work happen a second time.
Bites you decide Context grows you decide Attempt billed
1 How often does it send work back?
2 What does one round cost?
=One round —tokens
3 When does it stop, and who owns that?
No cap means the worst case has no ceiling, and the tool will say Unbounded.
Add a path only if it makes the model do work a second time. That is what this tool counts. A send-back that spends no further tokens — a person editing the output themselves, say — belongs in your process notes, not here.
All seven paths are in your workflow.
One budget for the whole task
No price entered yet, so this stays in tokens. The scheduling example leaves the price blank on purpose: it is the one figure nobody else can supply, because it depends on your provider, your tier and your own mix of input and output tokens. Put your number in Your price per million tokens above and the cost per task appears here. At that rate, a typical task costs —, and a thousand of them cost —. That is the everyday figure, not the worst case.
For scale: the same task at frontier rates
Your typical cost per task, priced at what three frontier models charge. It is a range because input and output are priced differently: the low figure is all input, the high figure is all output, and real work sits between them, usually nearer the low end. Checked 28 September 2026.
| Model | Input per 1M | Output per 1M | Your typical task | Worth knowing |
|---|---|---|---|---|
| Claude Opus 5.5 Anthropic | 4.00 | 20.00 | — | US-only inference costs 1.1×. Fast mode costs 2×. |
| GPT-6 Astra OpenAI | 10.00 | 50.00 | — | Long context costs $20 in and $75 out, so a growing redo can double this. |
| Gemini 3.1 Pro Google | 2.00 | 12.00 | — | Prompts over 200k cost $4 in and $18 out. |
Figures are US dollars, which is how all three publish. Rates change, and two of these carry a condition that doubles them, so check the provider before you quote one: Anthropic · OpenAI · Google .
Pass, attention or fail
Each check reads your figures and says where you stand, then what to do about it. Work down the list; the one to fix first is called out at the bottom.
- Pass
- Nothing to do here.
- Attention
- It works today, and something about it will surprise you. Worth fixing.
- Fail
- This is the one that stops you scaling. Fix it first.
- Not answered
- The check needs a figure you have not entered yet.
- Not answered
1. Every path that sends work back is listed
A path you have not listed is spend you cannot see. Most teams count their retries and miss the judge entirely, because a judge rejection looks like normal operation rather than a failure.
No path is marked as present yet.
Do this
- Not answered
2. Each round is costed as repeated, review and growth
A round is three things and teams usually count only the first. The review call and the growing context are what make a judge loop expensive, and neither appears in a retry counter.
No path is marked as present yet.
Do this
- Not answered
3. Every loop has a limit, a decided outcome, and an owner
A loop with no cap has no worst case. This is the check that turns "it depends" into a number, and an uncapped path is the single most common finding here.
No path is marked as present yet.
Do this
- Not answered
4. Both numbers fit: what you pay daily, and your busiest minute
One number is not enough, because the two ways this hurts you are different. The typical cost is what you pay every day, and it decides whether the product makes money. The worst case at peak decides whether one bad minute takes the whole system down. A workflow can be fine on one and fatal on the other.
Peak tasks per minute and the quota are needed for this one.
Do this
- Not answered
5. One token budget for the whole task, not one per call
A task that goes round three times spends three times. A budget checked on each call sees the attempts one at a time and never sees the total, so it cannot stop a task that is running away. To do that, every round has to count against one limit that belongs to the task.
Choose how your budget is enforced.
Do this
Your next step
Worked example
A scheduling agent drafts a reply three times while a judge requests more detail. Count all three drafts and all three checks before comparing this path with a human handover.
What to take away
Use the estimate to choose a stopping rule. Confirm the inputs against a trace before treating the result as an operating budget.
Published 28 September 2026 · Content CC BY 4.0 · Code MIT · © The Living Craft