✓ Verified on October 21, 2026⏱ 4 min read✓ done
Claude's three modes
🎯 Example — Preparing for a Board meeting
Chat: "Analyze this memo and identify the top 5 risks."
Cowork: "Take the Q1 data, build an Excel dashboard and a 10-slide deck for the Board."
Code: "Deploy a web dashboard connected to our internal API."
Cowork: "Take the Q1 data, build an Excel dashboard and a 10-slide deck for the Board."
Code: "Deploy a web dashboard connected to our internal API."
Which one to choose? — decision table
The question isn't "which is best" but "which one for which situation." Simple rule: choose based on the deliverable and the level of autonomy you expect.
| Your need | Mode | Why |
|---|---|---|
| Think, analyze, draft, get an opinion | 💬 Chat | A quick conversation, no file to produce. Your default reflex. |
| Produce a deliverable from your files (Excel, PPT, doc, folder) | ⚡ Cowork | Claude accesses your files and executes the task end to end. |
| Chain several apps / automate a recurring task | ⚡ Cowork | Multi-tool orchestration (email, calendar, SaaS) + scheduled tasks. |
| Build or deploy a custom tool (app, script, integration) | ⌨️ Code | Terminal access, version-controlled code, deployment. For technical teams only. |
| You're away from your desk but a task is running | 📱 Claude mobile app | Follow, redirect or start a task from your phone; tasks that use files or apps on your computer need Claude Desktop open. |
📌 The right reflex
Start in Chat. The moment you catch yourself copy-pasting a result into a file, switch to Cowork: that's the sign a deliverable needs to be produced. Reserve Code solely for development projects handed to your technical teams.
Which model? — the guide's single rule
A "model" is the brain you select at the top of the conversation. Remember one rule, valid everywhere in this guide:
Sonnet 5.5Everyday work: emails, notes, routine analysis. Fast, inexpensive, open on every plan.
Opus 5.5Heavy files: reasoning, long assignments, agents. Fable 5.1-level on most tasks, and it verifies its own work.
Fable 5.1The summit: multi-hour missions and the most demanding reasoning, when Opus 5.5 is no longer enough. 2.5 times its price: use it deliberately.
| Model | Working memory | What for |
|---|---|---|
| Fable 5.1 ✦ | 1M tokens ≈ 555,000 words | The most powerful (Mythos class): thick files, long assignments, strategic analysis, autonomous agents |
| Opus 5.5 ✦ | 1M tokens | Fable 5.1-level on most tasks, 40% cheaper than Opus 5 and 30% faster. On every paid plan. The best value for heavy work |
| Sonnet 5.5 ✦ 🆕 | 1M tokens | Everyday work: emails, notes, routine analysis. More than 30% faster than Sonnet 5 and up to 30% cheaper per task, within 2 points of Opus 5.5 on GDPval-AA (real professional tasks), per Anthropic. Open to everyone, Free included |
| Haiku 5.5 🆕 | 1M tokens | Small high-volume tasks (sorting, summaries, classification): about 75% cheaper than Haiku 4.5, and far more capable. Open to everyone, Free included |
| Previous generations | 1M tokens (Haiku 4.5: 200K) | Opus 5, Opus 4.8, Sonnet 5, Haiku 4.5, Fable 5: legacy, still available. Opus 4.8 and Sonnet 5 take over on some sensitive topics |
📌 Three useful details
Opus 5.5 gets to the point (less jargon, key information first) and Fable 5.1 formats less: ask explicitly for headings and lists when you want them. On sensitive topics (cybersecurity, biology), both automatically fall back to an earlier Opus — you are told, and nothing is billed. Sonnet 5.5 does the same on cybersecurity, falling back to Sonnet 5: you can turn this off in Settings → Capabilities. And stop adding "check your work" to your prompts: these models already verify themselves, the instruction only burns tokens.
Access by plan
Sonnet 5.5 and Haiku 5.5 are open to everyone, Free included. Opus 5.5 is available on every paid plan ($4 / $20 per million tokens on the API), and five-hour limits have been raised on Pro, Max, Team and Enterprise. Fable 5.1: available without restriction on the API and usage-based Enterprise ($10 / $50 per million tokens). Max and Team Premium: Fable included up to 50% of your weekly limits. Pro and Team Standard: access through paid usage credits. Announced on October 7 and rolling out gradually, monthly API credits also come with Max and Team ($100 or $200 on Max, up to $500 pooled on Team). Detailed prices are in the Pricing appendix. [Terms may change — check claude.com/pricing]
AskUserQuestion — Claude asks you
A key new feature: Claude no longer guesses when information is missing. With AskUserQuestion, it asks you targeted questions (clickable buttons) before getting started, rather than producing an approximate result based on assumptions.
🎯 Why it's a game-changer
Instead of missing the mark for lack of context, Claude clarifies: "For this report, who's your audience — the executive committee, investors, or an internal team?" You click, and it produces the right deliverable the first time. Fewer back-and-forths, more precision.
🛠️ Your turn — 5 minutes
Ask the same thing twice: once in Chat on claude.ai ("analyze this text"), once in the Desktop app pointing at a file. Note what differs.
Expected result : You can say in one sentence when to stay in Chat and when to delegate to Cowork.