AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is 'context length' limitation in LLMs and how do 'long-context models' address it?
⚠ Common exam trap
Many candidates confuse 'context length' with unrelated operational metrics like API timeouts or hardware limits, rather than recognizing it as a core architectural token limit of the LLM itself.
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
✓
The maximum text an LLM can process at once — long-context models extend this to 128K+ tokens
'context length' in large language models (LLMs) refers to the maximum number of tokens (words, subwords, or characters) the model can process in a single input, including both the prompt and the generated output. Long-context models, such as GPT-4 Turbo or Claude 3, extend this limit to 128K tokens or more, enabling the model to handle entire documents, lengthy conversations, or large codebases without truncation.
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 physical cable length limitation when connecting AI servers in a data centre
Why it's wrong here
Optical and copper cabling in a data centre have physical distance limits (e.g., 100 m for Cat-6 Ethernet, and single-mode fibre spans tens of kilometres), but these constrain signal integrity and network latency, not the model's ability to hold text. 'Context length' is a model-level parameter expressed in tokens, which represent subword units of text, not physical infrastructure. No cable run can change how much textual input a transformer's attention mechanism can process in a single API call.
- ✓
The maximum text an LLM can process at once — long-context models extend this to 128K+ tokens
Why this is correct
This is the correct answer. Context length (or context window) is the maximum number of tokens an LLM can accept in a single inference call, including both the user-provided prompt and the model's generated response. Modern Azure OpenAI models like GPT-4o support up to 128K tokens, enabling full-document analysis and multi-turn conversations that collectively would be far too large for older 4K-token models. Measuring context in tokens matters because a token is roughly 4 characters, so 128K tokens corresponds to roughly 100 to 200 pages of English text, depending on vocabulary and punctuation.
- ✗
The minimum number of examples required before the model produces reliable outputs
Why it's wrong here
The minimum number of examples needed for reliable output is a property of few-shot learning, which is a separate mechanism from context length. In few-shot prompting, you place labelled examples inside the prompt to condition the model's behaviour, and adding more examples consumes the same finite context window. However, context length itself does not define a minimum example count; it only caps the total number of tokens (including examples, instructions, and user input) that can fit in the request, so even a zero-shot request must respect the same limit.
- ✗
The duration (in seconds) before an Azure OpenAI API request times out
Why it's wrong here
API request timeouts are governed by Azure OpenAI service configuration, such as a 60-second or 120-second pause while waiting for a response, and are tied to network latency, model compute time, and rate limiting. Context length has nothing to do with elapsed seconds; it is a static capacity limit measured in tokens. A model with a tiny context window can still take a long time to respond if the input is complex or the backend is saturated, while a short timeout could fail even on a small, quick request.
Go deeper
Related to this question
About these practice questions
One of 985 original AI-900 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 AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 exam.