model.unavailable

This deployment serves no backend for the model


Type	`https://mthds.ai/errors/model.unavailable`
Family	`model`: The model a step names.
Domain	`operator`: whoever runs the runtime acts
Retry	`no`: repeating the operation fails the same way
HTTP status	`501`
Raised as	a problem document, sent as the body of an HTTP response or kept in a run's record

What it means

The model exists, but this deployment serves no backend for it, so the fix lies with whoever runs the runtime rather than with the method.

What to do

If you run the runtime, configure a backend for the model. Otherwise, use a model the runner lists in GET /models.

Next steps

A problem carries the step aimed at whoever reads it: the first when its reader is the domain's actor, whoever runs the runtime, and the second for any other reader.

Reader	Kind	Detail
The domain's actor	`fix_configuration`	Configure a backend for the model '`{model}`' on this deployment.
Any other reader	`change_model`	Use a model this deployment serves in place of '`{model}`', or ask whoever runs the runtime to serve it.

Detail

The problem's detail is written from this template, filled with the occurrence's parameters:

The {model_type} model '{model}' exists, but this deployment does not serve it (reason: {reason}).

Parameters

Every parameter is present on every occurrence of the code.

Name	Type	Description
`model`	`identifier`	The model the method names.
`model_type`	`identifier`	The kind of model.
`reason`	one of `not_served`, `not_allowed`, `unknown_at_provider`, `fallback_disabled`, `no_fallback_served`	Why it is not served: no backend serves it, the deployment does not allow it, its provider does not know it, or the fallback that would serve it is disabled or served by no backend.