Get Your CertAIF-C01PlayCompete
‹ All AIF-C01 questions

AIF-C01 Practice Question 63: Context Window Input Limit

AWS Certified AI Practitioner (AIF-C01) · Test 7 · question 3 of 10

Fundamentals of GenAIeasy

A paralegal pastes a 600-page merger agreement into an assistant built on a foundation model and the request fails with an error saying the input is too long. The wording of the instruction is fine and the model answers correctly on shorter contracts. Which property of the model is the limit here?

Select one answer
Show answer and explanation

Answer:

  • A. The context window: the maximum amount of text the model can take in a single request

Every foundation model has a fixed context window, measured in tokens, that bounds how much text it can consider at once. AWS publishes it per model: in the Amazon Nova understanding family the context window is 128K for Nova Micro, 300K for Nova Lite and Nova Pro, and 1M for Nova Premier. A 600-page agreement simply does not fit, and no amount of rewording will make it fit; the usual fixes are to chunk the document and retrieve only relevant sections, or to move to a model with a larger window (option A).

- B is wrong because temperature controls how much randomness the model uses when sampling the next token. It has no relationship to input length, and lowering or raising it will not make a long document acceptable. - C is wrong because maximum output tokens caps the length of the response. The failure here is on the way in, before the model generates anything. Nova's understanding models cap output at around 10K tokens regardless of how large their context window is. - D is wrong because the training cutoff governs what the model *knows* from pre-training. The contract is supplied in the prompt, so its date is irrelevant, and a cutoff problem produces a stale or wrong answer, not a length error.

Reference: What is Amazon Nova?

Practice Test 7 ›

Study guides for AIF-C01

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
How AWS Certification Exams Work: Scoring and RenewalHow AWS certification exams work: levels, booking, question types, unscored questions, scaled scores, pass marks, validity and how recertification works.
What Is Amazon Bedrock? Models, Pricing and GuardrailsWhat is Amazon Bedrock? How a request reaches a model, what happens to your data, token pricing, Guardrails, Knowledge Bases, AgentCore and the exam traps.
Google Cloud Generative AI Leader vs AWS AI PractitionerGoogle Cloud Generative AI Leader vs AWS AI Practitioner: format, cost, topics, free preparation and which certification to take first.
AWS certification cost in 2026, and free ways to prepareWhat every AWS certification costs in 2026 in USD and INR, retake and reschedule rules, the 50% voucher, and the free official ways to prepare.
AWS Generative AI Developer Professional (AIP-C01) guideWhat the AWS Certified Generative AI Developer – Professional (AIP-C01) exam covers - format, cost, the five domains, the services, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Which AWS certification should you get? 2026 roadmapWhich AWS certification to get first, by role and experience, with each exam's status in October 2026, what is changing, and prices in USD and INR.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.