provider.rate_limited

The provider is rate limiting this deployment


Type	`https://mthds.ai/errors/provider.rate_limited`
Family	`provider`: The inference provider behind a model.
Domain	`runtime`: nobody could have acted beforehand, so whoever made the call waits, retries or reports the problem
Retry	`yes`: repeating the operation may succeed, after `retry_after` seconds when the problem gives it
HTTP status	`429`
Raised as	a problem document, sent as the body of an HTTP response or kept in a run's record

What it means

The inference provider refused a call for its rate, which is not a quota: it passes.

What to do

Run the method again after retry_after seconds when the problem gives it.

Next steps

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

Reader	Kind	Detail
The domain's actor	`wait`	Wait, then run the method again.
Any other reader	`wait`	Wait, then run the method again.

Detail

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

The provider '{provider}' is rate limiting this deployment's calls to the model '{model}'.

Parameters

Every parameter is present on every occurrence of the code.

Name	Type	Description
`provider`	`identifier`	The provider.
`model`	`identifier`	The model called.