Introduction
Model records behave like agent records with two differences that account for most of the confusion: a model is measured in spans rather than traces, and it has nothing to instrument.
A model shows no spans
The empty state says spans appear once the model starts processing requests. Three quite different situations produce it, and they need different responses:
Situation | How to tell | Do |
Nothing calls it | No agent in your estate uses this model | Nothing — it is inventory, not a fault |
Callers are not instrumented | The calling agent is | Instrument the agent; the model's spans follow |
It is called outside traced paths | Your provider bill shows usage this screen does not | Investigate. This is a coverage gap |
Note: A model's spans arrive through its callers. There is no way to instrument a model directly, so an empty model is nearly always a statement about the agents that call it. Start there, not here.
A model is missing from the import list
The list is the connection's answer to "what can you serve", asked at that moment. If a model is not in it, the connection cannot see it — its credentials are scoped more narrowly than you expect, or the platform does not expose that model to this account.
"This connection returned no importable models" means the connection is working and has nothing to offer. That is a different problem from a connection that fails.
Model cost looks wrong
Are you adding it to agent cost? — Do not. A model call inside an agent's run appears in both views. They are two lenses on the same money — see Agent View vs Model View.
Is there a rate for this model? — Usage is observed either way; cost needs a rate. A model with none shows activity and no spend.
Are token counts reported or derived? — Derived counts are an approximation, and accuracy varies by integration rather than by model.
Are you comparing to an invoice? — They answer different questions. See How Cost & Tokens Are Calculated.
Frequently asked
Why does a model have five tabs when an agent has seven? — No
Setup(nothing to instrument), noMonitoring, noOutcomes(an outcome is credited to the agent that accomplished it).Why Inactive rather than Setup Pending? — Because there is no setup. Either spans are arriving or they are not.
Can a policy cover a model? — Yes — the
Applies totab covers agents and models, and the asset picker filters by type.Should I import every model the connection offers? — No. Import what is actually called. An inventory of unused models is noise in every downstream report.
Why does the same model appear under two connections? — Two credentials both reach it. They are genuinely two paths, and importing both is sometimes correct.
Who owns an imported model? — Import sets the owner to the person who ran it. There is no owner edit on the model record today, so import from the account of the person who should own the models.
Why is activity in spans rather than traces? — A model has calls, not runs. One model can appear in spans belonging to many different agents' traces.