Cost by Product

AgentPulse attributes the cost of every run to a product, so you can see exactly where your LLM spend goes.

Why per-product, not per-model

Your model invoice tells you what you spent, not where it went. A single line item for "LLM API" is useless when you run a dozen agents across several products. AgentPulse rolls each run's cost_usd up to the product its agent belongs to, so spend is attributed to the part of your business that incurred it.

Reporting cost

Send cost_usd on each run. Compute it however fits your setup — token counts times your negotiated rate, a provider usage field, or a flat per-call estimate. AgentPulse does not care how you derive it; it cares that the number rides along with the run.

The dashboard

The lead metric is a bar chart of USD spend per product with each product's percentage share of the total. Click any product to filter the entire dashboard — runs, traces, and metrics — to that product. The 24h / 7d / 30d period selector applies throughout.

From visibility to guardrail

Once cost is attributed you can alert on it: a cost_usd rule per hour turns a passive chart into an active budget. See Alert Rules.