easyMultiple Select
AIF-C01 Practice Question: A developer is new to Amazon Bedrock and wants to…
A developer is new to Amazon Bedrock and wants to understand the components of tokenization and context windows. Which TWO statements are correct? (Select TWO.)
⚠ Common exam trap
In AWS exams, often test the misconception that a larger context window universally improves response quality, when in reality it can degrade performance due to the 'lost in the middle' effect, where models struggle to attend to relevant information in very long sequences.
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 context window determines the maximum number of tokens the model can process in a single request
Option C is correct because the context window defines the hard limit on the total number of tokens (input plus output) that a foundation model can handle in one inference request on Amazon Bedrock, so exceeding it requires truncation or chunking. Option E is correct because modern tokenizers such as BPE or SentencePiece break text into tokens that may be whole words, subwords, punctuation, or characters, not fixed units. Option A is wrong because a larger context window only increases how much text can be supplied; response quality still depends on prompt design, model capability, and relevance of the included content. Option B is wrong because tokenization does not split solely on whitespace; subword tokenizers split within words and handle punctuation and special characters. Option D is wrong because Bedrock pricing is based on the number of input and output tokens processed (per 1,000 tokens), not on tokens per second, which is a throughput metric.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A larger context window always produces better quality responses
Why it's wrong here
Context window size bounds how much text a model can consider; it does not guarantee quality, since irrelevant or noisy content can degrade responses and models differ in reasoning ability. It is tempting because larger windows do allow more input. A larger window is genuinely needed when prompts or documents exceed a smaller model's limit.
- ✗
Tokenization splits text only on whitespace
Why it's wrong here
Tokenizers use subword algorithms such as byte-pair encoding, splitting punctuation, numbers and rare words into fragments, so whitespace is only one signal. It is tempting because splitting on spaces is the intuitive mental model. Whitespace-only splitting would be correct only for trivial word-count approximations, not for real model input.
- ✓
The context window determines the maximum number of tokens the model can process in a single request
Why this is correct
The context window is the fixed token budget spanning prompt plus generated output for one request. Exceeding it forces truncation or rejection, so it directly determines the maximum tokens a model can process in a single request.
- ✗
The cost of a request is based on the number of tokens per second
Why it's wrong here
Bedrock bills on input and output token counts, not tokens per second, which measures throughput. It is tempting because streaming responses make token rate visible and latency-sensitive workloads care about it. Per-token pricing would be the right framing when estimating cost from prompt and completion lengths.
- ✓
Tokens can be words or subwords, depending on the tokenizer
Why this is correct
Tokenizers split text into units that may be whole words, subword fragments or characters, depending on vocabulary and frequency. Rare words typically fragment into subwords, so tokens are not strictly words, satisfying the statement about token composition.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 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 AIF-C01 practice question is part of Courseiva's free Amazon Web Services 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 AIF-C01 exam.