What the late payment interest claimer costs
The model reads agreements, and a business signs those a few times a year per customer at most. Everything that happens per invoice, per payment and per night is arithmetic against a table. Here is where each cent goes.
Key takeaways
- About $4 a month at 200 customers. Roughly $14 at 800 customers.
- One Bedrock read per agreement is the only line that scales. Everything else is rounding.
- Nothing is always-on, so a quiet month genuinely costs almost nothing.
- The bill tracks customers, not invoices. Ten thousand invoices a month cost the same as one hundred.
- The duplicate test runs before the read, so resends are free.
- The three real risks: a retry loop, storage nobody expires, and a bigger model than the job needs.
The bill at three volumes
These are US East prices at the time of writing, at three volumes that bracket most small businesses. Find the bar closest to your own and read across.
Line by line
| Line | At 200 customers | How it scales |
|---|---|---|
| Bedrock read | $2.80 | Linear. One call per agreement, roughly 1,800 in and 200 out tokens. |
| SES | $0.16 | Linear. About 3 messages per agreement. |
| DynamoDB + S3 | $0.34 | Storage grows with what you retain, not with throughput. |
| Lambda + SQS | $0.12 | Linear, and effectively free at this scale. |
| CloudWatch | $0.16 | Flat, if you set retention. Unbounded if you do not. |
| Secrets Manager | $0.40 | Flat. One secret, $0.40 a month. |
| AWS Budgets | $0.46 | Flat. Two actions, so you find out before the bill does. |
Roughly one model call per customer agreement version, against a mid-tier model. The extraction is narrow: the payment terms, any verification period, any contractual late payment remedy, and the clause each came from. Length is not difficulty, and a frontier model finds the same four clauses for several times the price.
The three ways this bill surprises you
Every one of these has happened to somebody, and all three are cheap to prevent.
- Re-reading every agreement on every nightly run. Terms change when somebody signs something. Extract once per version and re-read on change.
- Recomputing every open debt every night. Store the daily amount and multiply by days. A nightly full recalculation over six years of history is the one way to make this expensive.
- Keeping every accounting export forever. Keep the derived debt record, which is small and has to last six years, and expire the raw exports once reconciled.
What it costs when nothing happens
This matters more than the headline number for a seasonal business. In a month with nothing to process the bill is the fixed band: Secrets Manager at forty cents, AWS Budgets at forty-six, and a few cents of storage. Call it a dollar. There is no instance to stop and nothing to remember to turn off.
- Management
- Analytics
- Front-end & mobile
Set these on day one
- A dead-letter queue on every SQS queue, with a maximum receive count of three.
- Thirty-day retention on every CloudWatch log group. There is no default that is safe.
- An S3 lifecycle rule on the object prefix, tiering at 90 days and expiring at your actual record-keeping horizon.
- Two AWS Budgets actions — one that emails at half your expected spend, one at double it. The second is how you find out about a loop in an hour instead of a month.
- Provisioned concurrency: none. Nothing here is latency-sensitive enough to justify paying for a warm function.
Next: the same system drawn for engineers — service names, resource identifiers, IAM scopes, table schemas and the model id.
All posts