List model deployment startups
Lists the replica startups for a model deployment.
Authorizations
Send Authorization: Bearer <api_key>. The legacy Authorization: Api-Key <api_key> scheme is also accepted.
Query Parameters
Start of the query window, in epoch milliseconds.
End of the query window, in epoch milliseconds. Must be after the start.
Only include startups that lasted at least this many milliseconds.
x >= 0Opaque cursor returned by a previous page. Omit to fetch the first page. Pass the same filters and sort as the request that returned it.
Maximum number of attempts to return.
1 <= x <= 100Only include attempts with one of these outcomes. Repeat to pass several.
Outcome of a whole startup attempt.
SUCCESS, FAILED, STALLED Only include attempts that spent longer than 0 ms in this phase. A stage of a replica startup.
SCHEDULING: waiting for the replica to be placed on a node.IMAGE_PULL: pulling the container image.WEIGHT_DOWNLOAD: downloading model weights.CONTAINER_CREATE: creating and starting the model container, includingCONTAINER_STARTandREADINESS.CONTAINER_START: starting the model container.READINESS: waiting for the model to pass its readiness check.
CONTAINER_START and READINESS are accepted as filters but are reported only as
part of CONTAINER_CREATE.
SCHEDULING, IMAGE_PULL, WEIGHT_DOWNLOAD, CONTAINER_CREATE, CONTAINER_START, READINESS Only include attempts whose replica ID matches exactly, or whose deployment name contains this text (case-insensitive).
Field to sort attempts by. Defaults to STARTED_AT.
Field to sort startup attempts by.
OUTCOME, STARTED_AT, READY_AT, DURATION Sort direction. Defaults to desc.
asc, desc Response
A page of startup attempts, newest first by default.