easyMultiple Choice
PDE Practice Question: A user gets the above error when trying to get…
Exhibit
Refer to the exhibit.
Error log from Cloud Logging:
{
"textPayload": "Prediction failed: Model 'projects/my-project/locations/us-central1/models/12345' is not deployed to endpoint 'projects/my-project/locations/us-central1/endpoints/67890'. Ensure the model is deployed to the endpoint before making predictions.",
"timestamp": "2024-03-15T10:30:00Z",
"resource": {
"type": "aiplatform.googleapis.com/Endpoint"
}
}A user gets the above error when trying to get online predictions. The model was created and the endpoint exists. What is the most likely reason?
⚠ Common exam trap
Google Cloud exams often test the misconception that creating an endpoint automatically deploys the latest model version, when in fact you must explicitly specify a model version during endpoint creation or update.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
No version of the model is deployed to the endpoint.
The error 'No version of the model is deployed to the endpoint' occurs when the endpoint exists but has no active model version assigned to it. In Google Cloud AI Platform (Vertex AI), an endpoint must have at least one deployed model version to serve predictions. Without a deployed version, the endpoint cannot handle inference requests, even though the endpoint resource exists.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The endpoint does not exist.
Why it's wrong here
The stem states the endpoint already exists, so this contradicts the given facts rather than explaining the error. Endpoint-not-found errors do occur when a deployment was never created or the name is misspelled. The likely cause is a missing model artefact or an unhealthy deployment behind the existing endpoint.
- ✗
The endpoint is in a different region than the model.
Why it's wrong here
Azure Machine Learning online endpoints and their models are not required to reside in the same region; the model is registered in the workspace and deployed to the endpoint's region. Cross-region setups are valid. The error instead stems from the deployment failing to provision behind the existing endpoint.
- ✓
No version of the model is deployed to the endpoint.
Why this is correct
Online prediction requests fail when the endpoint has no deployed model version to route them to. Creating the model and endpoint alone is insufficient; a version must be deployed to the endpoint before it can serve predictions, which is the missing step here.
- ✗
The model does not exist.
Why it's wrong here
The stem states the model was created, so a missing model contradicts the given facts. Model-not-found errors arise when scoring scripts reference an unregistered or wrongly versioned artefact. The likely cause is the deployment failing to provision, leaving the existing endpoint without a healthy backing deployment.
Go deeper
Related to this question
About these practice questions
One of 747 original PDE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.