A media company processes video transcripts for content moderation. Transcripts average 150,000 tokens each. The moderation task requires nuanced judgment about context (a violent scene in a documentary vs. gratuitous content), cultural sensitivity across 40 languages, and legal compliance in 12 jurisdictions. Processing volume is 500 transcripts/day. The moderation team currently uses human reviewers at $18/hour taking 45 minutes per transcript. Which model architecture best handles the context length requirement while managing per-unit economics?

Claude 3.5 Sonnet with 200K context is the correct architectural choice. For 150K-token transcripts, single-pass processing eliminates chunking artifacts — missed context at boundaries, duplicated moderation calls on overlapping segments, and aggregation errors. Sonnet provides the nuance required for cultural and jurisdictional sensitivity. Compared to Opus, it delivers substantial cost savings at scale (500/day) with sufficient capability for this task. Option B's chunking approach is specifically worse here: a violent context split across a chunk boundary may be missed, producing false negatives — exactly the failure mode dangerous for content moderation at scale. Option A (Opus single-pass) is valid but unnecessarily expensive when Sonnet handles 200K context adequately. Option D's extractive pre-summarization for moderation is high-risk: the extractive summarizer may discard exactly the nuanced passages (brief references, euphemisms, contextual cues) that constitute moderation violations.