Rule applied: calls move to the small model. Nothing was stopped, and the support lead was told.
AAcme IncTodayAll teamsExport
Requests Every model call, by teamLive
Request log 2,412,880 this month
Time
Team
Route
Model
Cost
Result
10:42:11
Engineering
code-review
Large model
$0.047
Done
10:42:09
Support
summarise-ticket
Small model
$0.002
Fell back
10:42:08
Support
summarise-ticket
Large model
$0.032
Budget reached
10:42:06
Finance
invoice-extract
Large model
$0.064
Done
10:42:05
Support
draft-reply
Large model
$0.035
Done
10:42:03
Sales
draft-email
Small model
$0.001
Done
10:42:02
Support
summarise-ticket
Large model
$0.019
Done
10:42:01
Engineering
code-review
Large model
$0.061
Done
10:41:58
Sales
lead-summary
Small model
$0.002
Done
10:41:57
Engineering
test-writer
Large model
$0.052
Done
10:41:55
Support
draft-reply
Large model
$0.031
Done
10:41:54
Finance
invoice-extract
Large model
$0.058
Done
10:41:52
Engineering
code-review
Large model
$0.044
Done
10:41:51
Sales
draft-email
Small model
$0.001
Done
10:41:49
Support
summarise-ticket
Large model
$0.022
Done
10:41:48
Finance
po-lookup
Small model
$0.001
Done
Team budgets November
Support$6,000 of $6,000
On track
Near cap
Capped, now on small model
Engineering$7,860 of $12,000
Sales$1,700 of $4,000
Finance$1,380 of $4,000
Providers
Provider one Healthy
Provider two Healthy
The problem
AI arrived team by team
Each team picked a provider, made a key and shipped. Now the bill is one number, the keys are everywhere and nothing stops one runaway job from spending the month.
We pick the one that fits the systems you already run. You own the config, the tests and the runbooks, so you can swap any part later. Most often it is a LiteLLM proxy; agentgateway, Agent Router or Bifrost when they fit better.
Does it run in our cloud?
Yes. The gateway, its logs and its keys stay in your cloud account.
Do teams have to change their code?
Only the address they call and the key they use. The gateway speaks the same interface the providers do.
What happens when a team hits its budget?
The rule you set decides: warn, move to a cheaper model or stop. Nothing is cut off without a rule you approved.
How long does it take?
About 3 weeks for the gateway and the first teams. More teams move onto it after the handover, using the runbook.
LLM gateway, running in your cloud in about 3 weeks.
One door for every model call. You own the config, the tests and the runbooks.