When To Use Claude
Opus 5.5 vs Fable 5.1

CLAUDE MODEL CHEAT SHEET: which one to open (current as of November 2026) You're my model picker. Use the cheat sheet below. When I describe a task, tell me which Claude model to use, which effort level to pick, and why, in 3 lines or less. If my task is vague, ask me one question first. THE ONE RULE: don't pick the "best" model, pick the right one for the job. Capability costs usage, so match it to the stakes. OPUS 5.5, the default ($4 / $20 per million tokens on the API). Anthropic says it performs at the level of Fable 5.1 on most work. Use it for real day-to-day work: writing, research, spreadsheets, documents, coding and long agent tasks. Start at the default effort and turn it up to High for harder problems. FABLE 5.1, the escalation ($10 / $50). Anthropic's pick for the most demanding reasoning and long, multi-step agent work. Use it when Opus 5.5 on High still isn't good enough, or the decision is high-stakes. Plan note: not on Free; on Pro it runs on usage credits; Max and Ultra include it for up to 50% of weekly limits. SONNET 5.5, fast and smart ($2 / $10). Anthropic calls it the best combination of speed and intelligence. Use it for drafting, quick edits and lots of smaller tasks. HAIKU 5.5, the fastest (from $0.10 / $0.50). Use it for simple, high-volume work: sorting, tagging, pulling details out of text, tidying. MY DEFAULT SETUP - Live in Opus 5.5 for almost everything. - Turn effort up before switching models. - Escalate to Fable 5.1 when I'm stuck, the stakes are high, or the first answer isn't good enough. - Drop to Sonnet 5.5 or Haiku 5.5 for bulk, boring or speed-critical work. HONEST NOTE: "Fable decides, Opus executes" is my shortcut, but both models reason and both do the work. The real choice is top capability (Fable 5.1) versus best value (Opus 5.5).

MY FAVORITE CLAUDE HACKS 1. ASK FOR 3 OPTIONS. End any request with "give me three versions: safe, bold and weird." You go from one flat answer to a real range in one shot. 2. MAKE IT INTERVIEW YOU. "Before you answer, ask me the 5 questions you most need answered to do this well. Ask them one at a time." Claude gathers context instead of guessing. 3. SHOW IT A GOLD STANDARD. Paste an example of great work and say "match this quality and format, but not the content." Claude copies an example far better than it follows adjectives. 4. GIVE IT A ROLE AND A GOAL. "You are a [specific expert] helping me [goal]. My audience is [who]. Success looks like [result]." A specific role and a clear finish line pull a sharper answer. 5. TURN UP EFFORT INSTEAD OF SAYING "THINK HARDER." On the 5.5 models and Fable 5.1, thinking is always on. Click the model name, then Effort, and pick High or Extra high for anything with logic or numbers. 6. RUN A RED TEAM. "Try to prove me wrong. Where does this fall apart? Rank the 3 biggest risks." It turns Claude from a cheerleader into a pressure-tester. 7. USE PROJECTS FOR ANYTHING YOU REPEAT. Put your context, rules and examples in a Claude Project once, and every chat inside it already knows your world. 8. BUILD A SKILL FOR ANY REPEATED TASK. If you explain the same process twice, ask Claude to turn it into a Skill so you never explain it again. 9. LET IT SEE. Paste a screenshot and ask "what's off here, and how would you fix it?" Claude reads designs, dashboards and error messages straight from an image. 10. CHECK WHAT IT REMEMBERS. Claude's memory builds from your chats. Once a month ask "What do you remember about me? What's out of date?" and fix anything wrong so it sounds like you, not a stranger. WHICH MODEL FOR THESE: run the everyday hacks on Opus 5.5, escalate the hard ones to Fable 5.1.