---
title: "Track cost per request · Agent Wranglers"
url: https://agentwranglers.se/playbook/scaling/load-balancing-and-autoscaling/cost-per-request
updated: 2026-10-21
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Track cost per request

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Load balancing and autoscaling](https://agentwranglers.se/playbook/scaling/load-balancing-and-autoscaling.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-21.

- ID: SCL-33
- Level: Recommended
- Chapter: [Load balancing and autoscaling](https://agentwranglers.se/playbook/scaling/load-balancing-and-autoscaling)
- Rule: Divide each service's monthly cost by the work it did, such as cost per 1,000 requests or per active customer. Alert when it rises more than 20% from the month before.
- How: Total cost grows with traffic, which is expected. A rising cost per unit means scaling went wrong, such as an autoscaler that never scales down or a cache that misses. [Watch what the service costs](https://agentwranglers.se/playbook/infrastructure/cost-and-ownership/budgets-for-every-account) tracks the totals and tags. Take the request counts from [rate, errors and duration](https://agentwranglers.se/playbook/operations/metrics-and-traces/red-metrics). Show the unit cost on the [service dashboard](https://agentwranglers.se/playbook/operations/metrics-and-traces/service-dashboards), and compare it before and after each scaling change.
- Check: A monthly report shows the cost per 1,000 requests for each service. An alert fires when it rises more than 20% from the month before.

## Related rules

- [Give every account a budget with alerts](https://agentwranglers.se/playbook/infrastructure/cost-and-ownership/budgets-for-every-account) in Infrastructure
- [Measure rate, errors and duration](https://agentwranglers.se/playbook/operations/metrics-and-traces/red-metrics) in Operations
- [Give each service one dashboard](https://agentwranglers.se/playbook/operations/metrics-and-traces/service-dashboards) in Operations

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/scaling/load-balancing-and-autoscaling/cost-per-request">Agent Wranglers scaling playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Turn off optional work under load](https://agentwranglers.se/playbook/scaling/load-balancing-and-autoscaling/degrade-under-load)
- [Load balancing and autoscaling](https://agentwranglers.se/playbook/scaling/load-balancing-and-autoscaling)