# Conversation-Level Cost Tracking

> Conversation-level cost tracking measures AI spend at the unit that matters: each conversation or workflow run, with its tokens, tool calls, model choices and latency recorded, across every vendor on one set of axes. It is the difference between knowing the invoice went up and knowing why.

- Part of: [The Sentry AI Transformation Glossary](https://sentrysolutions.ai/glossary)
- Canonical: https://sentrysolutions.ai/glossary/conversation-level-cost-tracking

Vendor invoices arrive as one line per provider, which hides the shape of the spend entirely. Tracked per conversation, the estate becomes legible: which workflows cost what, which agents regressed this week, where the expensive patterns concentrate.

Every optimisation lever depends on this resolution existing first. Routing, context restructuring and tool-call tuning all need a baseline per workflow, and a cost regression should be visible the day it appears, not the month the invoice lands.

## Related terms

- [Semantic Model Routing](https://sentrysolutions.ai/glossary/semantic-model-routing)
- [Agent Management Platform](https://sentrysolutions.ai/glossary/agent-management-platform)