Skip to main content
Every Serverless AI endpoint and job has a status that indicates its current stage in the lifecycle. You can see the status in the web console, or in the status.state field returned by the CLI and REST API.

​
Endpoint statuses

​
Job statuses

​
Typical transitions

When an endpoint starts, it moves through the following statuses: PROVISIONING → STARTING → IMAGE_PULLING → RUNNING When you stop and then start an endpoint again: RUNNING → STOPPING → STOPPED → STARTING → IMAGE_PULLING → RUNNING When a job runs to completion: PROVISIONING → STARTING → IMAGE_PULLING → RUNNING → COMPLETED When you cancel a running job: RUNNING → CANCELLING → CANCELLED IMAGE_PULLING can be quick enough that the status never surfaces.

​
Failed and errored workloads

The FAILED and ERROR statuses indicate different kinds of problems:
  • FAILED applies to jobs only and means the job did not complete successfully, for example, because of an error in your code, an incorrect entrypoint, a missing dependency in the image, or an exceeded timeout.
  • ERROR means Serverless AI could not run the workload. For jobs, this indicates an internal Serverless AI error rather than a problem with your workload. Endpoints have no FAILED status, so their ERROR covers workload problems as well, such as a container that could not start.
To tell these causes apart, check the status details in the web console, or the status.state_details field in the CLI, before you retry. Its code and message name the cause:
  • StartFailed: A container that could not start
  • ContainerFailed: A workload that exited with a non-zero code
  • TimeoutExceeded: A job that ran out of time
  • NotEnoughResources: No capacity for the requested platform and preset
When the status details are empty, the cause is internal to Serverless AI. Retry your job or endpoint, and if the status persists, contact support. For deeper investigation, see Debugging failed jobs and endpoints.

​
Provisioning timeout

An endpoint or job waits in PROVISIONING until compute capacity becomes available. If it does not become available within 30 minutes, the resource reports ERROR with the NotEnoughResources code. Delete the resource and create it again with a different platform or preset.