AIF-C01 Fundamentals of Generative AI Practice Question

A media company is evaluating foundation models for a generative AI application that produces image captions and short video summaries. The team must balance output quality, latency, and operational cost. Which TWO considerations are most important when selecting a foundation model for this multimodal task? (Choose two.)

⚠ Common exam trap

The trap here is gravitating toward tangential factors like licensing or language coverage while overlooking that modality support and performance economics are the decisive selection criteria.

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

✓

Whether the model supports the required input modalities, such as images and video frames.

For a multimodal captioning and summarization workload, the model must accept images and video frames as input, so modality support is a prerequisite. Because the team must also balance latency and cost, evaluating inference speed and pricing against throughput needs is equally critical. Together these ensure the model can handle the data and remain practical to operate at scale.

Answer analysis

Option-by-option breakdown

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

✗
Whether the model can generate outputs in multiple human languages simultaneously.
Why it's wrong here
Multilingual generation may be valuable in some deployments, but the scenario describes captioning and summarizing visual media, not translation or cross-language output. Language coverage is not stated as a requirement and does not address the balance of quality, latency, and cost. This makes it a plausible but ultimately irrelevant selection factor here.
✗
Whether the model was trained using a specific programming language's libraries.
Why it's wrong here
Foundation models are trained on data, not on a programming language's libraries. The framework used during training does not constrain how the model is invoked at inference time. This consideration is irrelevant to selecting a model for image captioning and video summarization, so it does not help the team meet its quality, latency, or cost goals.
✓
Whether the model supports the required input modalities, such as images and video frames.
Why this is correct
The task requires processing images and video frames, so the model must accept those modalities as input. A text-only model cannot caption or summarize visual content regardless of its quality. Verifying modality support is therefore a fundamental selection criterion, ensuring the chosen model can actually ingest the required data types before any other trade-off is evaluated.
✓
Whether the model's inference latency and cost align with the application's throughput requirements.
Why this is correct
Because the team must balance latency and operational cost, evaluating the model's inference speed and per-request pricing is essential. A highly capable model that is too slow or too expensive can make the application impractical at scale. Matching latency and cost to expected throughput ensures the deployed solution remains both responsive and financially sustainable.
✗
Whether the model's license permits the company's intended commercial distribution of outputs.
Why it's wrong here
Licensing is a genuine legal consideration, but the stem specifically asks about balancing output quality, latency, and operational cost for a multimodal task. While licensing must eventually be reviewed, it is not among the performance and cost trade-offs the team is weighing here, making it a less fitting answer than the modality and performance criteria.

Go deeper

AIF-C01 Fundamentals of Generative AI Practice Question

Why each option matters

Option-by-option breakdown

Related to this question