Task statement 3.2 · Product and model selection

3.2 · Claude Model Families

In Wrenfield Housing, the course example, two officers in the operations team sent Claude the same prompt, the message that asks for the work, and got noticeably different replies. One of them had switched the model selector to a different model family for an earlier job and forgotten, so the gap came from the model, not from the wording.

Why it's tested

When two people get different replies to the same prompt, the natural move is to blame the wording and start rewriting it. That cannot help when the replies came from different model families, because each family is built for different work and answers at its own speed and depth. The opposite mistake is to treat the most capable family as right for everything, which ignores that it is also the slowest and costs the most.

KnowledgeThree families, one trade-off

A model is the trained system that writes Claude's replies, and Anthropic releases its models in families. The exam guide names three: Haiku, Sonnet and Opus. The families trade capability against speed and cost. Opus is the most capable of the three and the slowest. Haiku is the fastest and lowest-cost. Sonnet sits between them, and Anthropic's models overview calls it the best combination of speed and intelligence. Anthropic's price list charges per token, a small piece of text that models read and are billed in. Opus costs more per token than Sonnet, and Sonnet costs more than Haiku. In the Claude apps you pay through your plan instead, and the model you chat with is one factor in how fast you use up your usage limit. So choosing a family means choosing how much capability each reply gets, and what you give up for it. That rules out any answer that treats the families as one model at three prices.

Anthropic's models overview and its guide to choosing a model describe each family by the work it is built for:

Haiku

The fastest and lowest-cost family. Built for high-volume tasks where a quick reply matters, such as classification (sorting items into set categories), extraction and routing.

Described forQuick, simple tasks repeated many times.

Sonnet

Fast, and capable enough for most everyday work. The docs list data analysis and content creation among its uses, and Anthropic calls it a faster, lower-cost complement to Opus.

Described forEveryday writing, analysis and summaries.

Opus

The most capable of the three, at moderate speed and the highest cost. Built for long-running knowledge work, complex reasoning and tasks that need nuanced understanding.

Described forHard, multi-step work where depth matters most.

Each family also has newer and older models. A model's full name is its family plus a version number, and the models overview lists the current model in each family next to older ones that are still available. Version numbers change with every release, so this course names families only, and says "the newest Sonnet model" for the current one. On the exam, tell the families apart by their place in the trade-off, never by a version number.

Interactive · one prompt, three families

The operations team's prompt at the top, with an arrow down to each of three model families: Haiku, the fastest and lowest-cost; Sonnet, fast with a balance of speed and capability; Opus, the most capable, at moderate speed and the highest cost. Each family has an arrow down to the reply it gives. A scale at the bottom runs from faster and lower cost on the left to more capable, slower and higher cost on the right. The family in the selector is solid and labelled in the selector; the others are dashed and labelled not selected. THE SAME PROMPT, SENT IN EACH CHAT Summarise the weekly repairs backlog export for the Monday team meeting. Flag anything that needs action. SENT TO Haiku fastest lowest cost IN THE SELECTOR NOT SELECTED REPLIES back in seconds open jobs by type nothing flagged SENT TO Sonnet fast speed and capability IN THE SELECTOR NOT SELECTED REPLIES quick counts, then damp and mould flagged: act first SENT TO Opus most capable moderate speed, highest cost IN THE SELECTOR NOT SELECTED REPLIES slower the same points, more depth more than a weekly summary needs FASTER, LOWER COST MORE CAPABLE, SLOWER, HIGHER COST RELATIVE TO EACH OTHER, NOT TO SCALE

Choose the family in the selector and follow the operations team's prompt to the reply it gets.

Haiku: the reply arrives fastest and at the lowest cost, but it is brief. It lists open jobs by type and flags nothing for action.

The newest Sonnet model: still quick, and capable enough to read across the counts, so the reply flags the damp and mould wait as the first thing to act on.

Opus: the most capable family covers the same points in more depth, but more slowly and at a higher cost than a weekly summary needs.

Solid and labelled IN THE SELECTOR: the family that answers. Dashed and labelled NOT SELECTED: families the prompt never reached.

KnowledgeSeeing and switching the model in the apps

In the Claude apps the model is a setting of the conversation, not of your prompt. The model you are chatting with is shown next to the send button on the web and desktop, and at the top of the screen on mobile. You can change it at any point in a chat, and the change applies from Claude's next response. So a switch made for one quick job stays in place for every later message in that chat, until you switch back. Which families you can pick depends on the plan: the Free plan offers Sonnet and Haiku, while paid plans, Team included, add Opus. An administrator may also have set the model every new chat starts on, but you can still change it within a chat. So when a reply surprises you, read the model name before you change the prompt:

  1. Read the model name next to the send button, or at the top of the screen on mobile.
  2. Click it to open the model selector; "More models" shows further options.
  3. Choose the family the task was meant for.
  4. Send the request again. The new family answers from the next response on.

SkillWorked example: one prompt, two replies

Two officers in Wrenfield's operations team, officer A and officer B, each asked Claude to summarise this week's export of the repairs backlog for Monday's team meeting. The export holds job type, estate, date reported and status, and no tenant names or addresses. They sent the same prompt in their own chats, and the replies came back very different:

# the same prompt in two chats
Summarise this week's repairs backlog export for Monday's team meeting.
Flag anything that needs action.
# officer A's chat, selector: Haiku → open jobs by type, nothing flagged
# officer B's chat, selector: the newest Sonnet model → the same counts, plus
#   "damp and mould: 112 jobs, median wait 41 days, act on these first"

Officer A first thought that officer B had written a better prompt, but the two prompts were word for word the same. The cause sat next to the send button. Earlier that morning officer A had switched that chat to Haiku to sort a long list of contractor job codes quickly, and every later message in that chat went to Haiku too. Neither reply was a fault: Haiku gave the fast, short answer it is built for, while the summary needed a judgement about which jobs matter most, the everyday analysis Sonnet is described for. Officer A switched back to the newest Sonnet model and sent the prompt again, and the team now reads the model name before comparing replies. The team also noted where Opus fits: their hardest work, such as checking the regulator's 38-page complaints guidance against Wrenfield's own process. Choosing a family for each task by cost, speed and quality is 3.3.

More precise than the guide. Anthropic's models overview lists a fourth current family, Fable, above Opus, for demanding reasoning and long-horizon work. In the apps it is on paid plans only. On the Team plan, premium seats include it within part of their weekly limits, and standard seats pay for it with usage credits (checked 2026-10-15). Exam answer: the guide's three families, with Opus as the most capable of them.

Ask one question: before you judge or compare a reply, which model family wrote it? The family you meant → judge the reply on its content. A different family → switch in the model selector and send the request again first.
Takeaway
  • Haiku, Sonnet and Opus trade capability against speed and cost: Opus is the most capable, Haiku the fastest and lowest-cost, and Sonnet the balance between them.
  • In the apps the model is a setting of each chat, shown next to the send button, and a switch lasts until you change it back.
  • On the exam, compare families by their place in the trade-off; a version number tells you only which model in a family is newer.

check yourself

0 / 3 answered

A team lead is writing a short note for new staff about the three Claude model families on their plan. The lead's draft says: "Haiku, Sonnet and Opus give the same answers. The higher-cost ones are just faster."Which correction most accurately describes how the families differ?

Select one.

Two paralegals on their firm's Team plan send Claude the same request to summarise a short lease. One gets a long, careful reply after a noticeable wait; the other gets a brief one in seconds. Their manager wants the cause found before anyone changes the prompt.Which TWO steps most directly find and remove the cause?

Select two.

An operations manager on their company's Team plan must work through three suppliers' contracts with conflicting renewal and penalty terms, and recommend which to renegotiate first. The analysis has many linked steps, and the manager is happy to wait longer for the most thorough reasoning the three families offer.Which choice in the model selector best fits this work?

Select one.

sources

  1. Claude Platform Docs, "Models overview": each family's description (Haiku for high-volume, latency-sensitive tasks such as classification, extraction and routing; Sonnet the best combination of speed and intelligence; Opus for long-running knowledge work); comparative latency and price per token for each family; legacy models still available; the fourth family, Fable. Checked 2026-10-15.
  2. Claude Platform Docs, "Choosing the right model": capabilities, speed and cost as the criteria; the selection matrix of use cases per family; complex reasoning and nuanced understanding for the capability-first start. Checked 2026-10-15.
  3. Anthropic, Claude Sonnet page: Sonnet as a faster, lower-cost complement to Opus. Checked 2026-10-15.
  4. Claude Help Center, "Change the model, effort, and thinking settings": the model next to the send button; "More models"; changes at any point in a chat apply from Claude's next response; an administrator may set the model new chats start on; effort and thinking in the same menu. Checked 2026-10-15.
  5. Claude Help Center, "Get started with Claude": the current model shown below the text input on web and desktop and at the top of the screen on mobile; click it to switch. Checked 2026-10-15.
  6. Claude Help Center, "How do usage and length limits work?": the model you are chatting with is one factor in your usage. Checked 2026-10-15.
  7. Claude, "Plans & pricing": Sonnet and Haiku on the Free plan; Opus, Sonnet and Haiku on Pro, Max, Team and Enterprise; Fable on paid plans only. And Claude Help Center, "Claude Fable models on your plan": Fable within part of the weekly limits on Team premium seats, usage credits on standard seats. Checked 2026-10-15.
  8. Officers A and B, their repairs backlog summary and the forgotten switch to Haiku are this course's example.