CCDV-F practice › Model Selection & Optimization · Question 45 of 92
Model Selection & Optimization
A request's system prompt, conversation history, retrieved documents, tool results, and the model's response must all fit within what shared limit?
Show answer and explanation
Answer: B — The context window
The context window covers everything in a single request including the response — a commonly missed detail. max_tokens caps only the output portion, not the total.
Keep going
More Model Selection & Optimization questions
- A task requires deliberate multi-step reasoning through an ambiguous clinical case, and…
- Before scaling a pipeline from 1,000 to 500,000 daily requests, what does the blueprint…
- A prompt carefully tuned against one model version produces noticeably different output…
- A long prompt has several stable sections and one volatile section in the middle. What…
- A team is 40% over budget on a pipeline with a large, unchanging system prompt and heavy…