# Model selection (Opus vs Sonnet vs Haiku)

Match the task to the tier: Opus for hardest reasoning, Sonnet for balanced work, Haiku for fast, cheap, high-volume tasks.

## Why the CCAR-P exam tests this

The exam checks that you pick a model by matching task complexity, latency, and cost rather than defaulting to the largest model everywhere.

## Definition

Claude ships in a family of tiers that trade **capability** against **speed and cost**. **Opus** is the most capable tier for deep reasoning, long multi-step agentic work, and hard analysis. **Sonnet** is the balanced tier — strong reasoning at lower latency and cost, the usual default for production. **Haiku** is the fastest and cheapest tier, built for high-volume, latency-sensitive, or simpler tasks like classification, extraction, and routing.

Selection is an engineering decision, not a status ranking. The right move is to profile the task: a simple label or a short extraction rarely needs Opus, while a nuanced multi-file refactor or a long agent loop may justify it. A common production pattern is **routing** — a cheap model triages or classifies, and only the hard cases escalate to a larger tier.

Model names are **versioned** (a tier plus a generation/date), so "Sonnet" alone is ambiguous — always pin the specific version string in code. Never assume a fixed price or context window from memory; look up the current model card, since these change across releases.

## Exam trap

Do not treat "biggest model = best answer" as the safe default; over-provisioning Opus for trivial tasks wastes latency and cost and is a wrong answer on cost/latency-sensitive scenarios.

## Commonly confused with

- **no-customer-fine-tuning** — Picking a tier is not the same as customizing a model — you cannot fine-tune Claude to your data, you can only choose a tier and steer it.

## Related

- no-customer-fine-tuning
- extended-thinking
- prompt-caching

---

Source: Claude Cert Prep — an independent, unofficial CCAR-P study resource (domain P2). Not affiliated with Anthropic.