Oracle
1Z0-1158-26
Oracle Cloud Infrastructure Enterprise AI Professional
Exam Version: 6.0
Questions & Answers PDF
(Demo Version - Limited Content)
For More Information - Visit link below:
https://p2pexam.com/1z0-1158-26
, Question 1. (Single Select)
In OCI Generative AI on-demand pricing, how is a transaction defined for character-billed models?
A: One transaction equals one full API call, regardless of length.
B: One transaction equals one gigabyte of Object Storage.
C: One character equals one transaction, billed per 10,000 transactions for Cohere and Meta models.
D: One transaction equals one unit-hour of dedicated GPU capacity.
Answer: C
Explanation:
For on-demand inferencing, 1 character = 1 transaction, billed per 10,000 transactions for Cohere and Meta
models. Frontier models (xAI Grok, Google Gemini, OpenAI gpt-oss) are billed per 1,000,000 tokens
instead.
Question 2. (Single Select)
Which statement describes the relationship between a Generative AI Application and a Deployment for
hosted agents?
A: Each Application can have only one Deployment ever, so upgrades require a new Application.
B: The Application provides the stable endpoint URL and top-level configuration; only one Deployment can
be active at a time, and it serves all requests.
C: The Application is the Dockerfile, and the Deployment is the OCIR repository.
D: The Deployment provides the endpoint URL, and the Application is a temporary container.
Answer: B
Explanation:
The Generative AI Application is the top-level resource that provides the stable endpoint URL. A
Deployment represents a specific container image; only one can be active per Application at a time, and
switching deployments enables zero-downtime version upgrades.
https://p2pexam.com/1z0-1158-26 Page 2 of 5
1Z0-1158-26
Oracle Cloud Infrastructure Enterprise AI Professional
Exam Version: 6.0
Questions & Answers PDF
(Demo Version - Limited Content)
For More Information - Visit link below:
https://p2pexam.com/1z0-1158-26
, Question 1. (Single Select)
In OCI Generative AI on-demand pricing, how is a transaction defined for character-billed models?
A: One transaction equals one full API call, regardless of length.
B: One transaction equals one gigabyte of Object Storage.
C: One character equals one transaction, billed per 10,000 transactions for Cohere and Meta models.
D: One transaction equals one unit-hour of dedicated GPU capacity.
Answer: C
Explanation:
For on-demand inferencing, 1 character = 1 transaction, billed per 10,000 transactions for Cohere and Meta
models. Frontier models (xAI Grok, Google Gemini, OpenAI gpt-oss) are billed per 1,000,000 tokens
instead.
Question 2. (Single Select)
Which statement describes the relationship between a Generative AI Application and a Deployment for
hosted agents?
A: Each Application can have only one Deployment ever, so upgrades require a new Application.
B: The Application provides the stable endpoint URL and top-level configuration; only one Deployment can
be active at a time, and it serves all requests.
C: The Application is the Dockerfile, and the Deployment is the OCIR repository.
D: The Deployment provides the endpoint URL, and the Application is a temporary container.
Answer: B
Explanation:
The Generative AI Application is the top-level resource that provides the stable endpoint URL. A
Deployment represents a specific container image; only one can be active per Application at a time, and
switching deployments enables zero-downtime version upgrades.
https://p2pexam.com/1z0-1158-26 Page 2 of 5
