Implement generative AI solutions →mediumMultiple SelectObjective-mapped

AI-102 Implement generative AI solutions Practice Question

Which TWO options are valid ways to reduce the cost of using Azure OpenAI Service?

⚠ Common exam trap

Microsoft Azure exams often test the misconception that adjusting model parameters like temperature or max_tokens can reduce cost, when in fact only token count and throughput commitments directly affect pricing.

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

✓

Use provisioned throughput with reserved capacity.

Provisioned throughput with reserved capacity allows you to commit to a specific amount of throughput (tokens per minute) for a fixed period, typically one month or one year, in exchange for a significant discount compared to pay-as-you-go pricing. This reduces per-token costs when you have predictable workloads.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Use provisioned throughput with reserved capacity.
Why this is correct
Reserved capacity offers a discount compared to pay-as-you-go.
✗
Increase the temperature parameter.
Why it's wrong here
Temperature does not affect token count or cost.
✓
Use a smaller model like GPT-3.5 instead of GPT-4.
Why this is correct
Smaller models have lower cost per token.
✗
Increase the max_tokens parameter to get longer responses.
Why it's wrong here
Longer responses consume more tokens, increasing cost.
✗
Enable content filtering on all requests.
Why it's wrong here
Content filtering does not reduce token usage; it may even increase latency.

Go deeper

AI-102 Implement generative AI solutions Practice Question

Why each option matters

Option-by-option breakdown

Related to this question