Agent Ping for SaaS teams
On a flat plan, inference cost is never evenly distributed. A handful of accounts run ten times the volume of everyone else, and nothing in your billing tells you which ones. Agent Ping attributes every run to the customer and feature behind it, so you can name the unprofitable accounts, price the next feature on real unit cost, and see margin move before the invoice does.
One customer, ten times the usage, same monthly price.
→They are enthusiastic, they are a reference customer, and they are the most expensive thing in your infrastructure. Nobody finds out until someone divides the provider bill by account count and the average stops matching anyone.
The number came from a demo, not from production.
→Demo prompts are short and clean. Real ones arrive with pasted documents and long histories. Price against the median and the tail eats the margin, and repricing a live feature is far harder than pricing it once.
A prompt change added context to every call.
→Nothing broke. No alert fired. Cost per request rose by a third, gross margin dropped a few points across the quarter, and the whole thing was attributed to growth because there was no per-feature number to check it against.
One run event carries the customer, the feature and the cost, so all three failures above become a query instead of an investigation.
Group spend by account and see the distribution. The heavy tail is usually a handful of names, and naming them is what makes a plan change or a usage component possible.
Churn from a degraded AI feature does not arrive as a bug report. Sampled scoring on live runs catches the drift while it is still a chart and not a cancellation.
A customer-facing agent that stalls should page you, not generate a support ticket. Freshness alerting closes the gap between failing and finding out.
Usage-based pricing for an AI feature needs one figure per customer per billing period, across every model the feature touched. Provider invoices cannot give you that; they are one total per API key. Agent Ping can, and it hands it over without lock-in.
Each run is priced server side from the model and token counts on its calls, whether that was one OpenAI call or a chain across Anthropic, OpenAI and Bedrock. The run's cost is a single US dollar figure, tagged with the customer and feature it was for.
Export the runs for a date range from the dashboard, on every plan: each line of runs.ndjson carries the run's customer_id, feature and cost_usd, so the per-customer total is a sum. For an automated monthly job, page through the read API with a read-scoped key, which returns the same fields.
Agent Ping does not send invoices or connect to a billing provider for you. The total goes wherever you already bill from, as a usage line or a metered quantity, with a run-level record behind every number if a customer asks how it was calculated.
# Every run in the billing period; sum cost_usd by customer_id. curl "https://agentping.io/v1/runs?from=2026-09-01T00:00:00Z&to=2026-10-01T00:00:00Z&per_page=100" \ -H "Authorization: Bearer apk_…"
Bulk export is covered in your data.
Instrument one customer-facing workflow and let it run for a week. The distribution usually answers the question on its own.
For product teams → For platform engineering → All features →