Claude just dropped its most powerful model yet. Here is exactly what it is best for, when not to touch it, how to turn it on, and the 5 prompts to try on it first. Free until June 22.
Anthropic just released Claude Fable 5, and it is the most capable model they have ever shipped. But "most powerful" does not mean "use it for everything." The people who get the most out of Fable know exactly when to reach for it and when to leave it alone.
This guide is the whole picture: what it crushes, when it is the wrong tool, the two ways to turn it on, three things about how it works that nobody explains, and 5 copy-paste prompts to feel its power on day one.
Try It On The House
Fable 5 is the premium model, but it is free until June 22. That window is the perfect time to throw your hardest, biggest projects at it and see what it can do before you decide whether it earns a spot in your rotation.
The Heavy Lifting
The Hard, Long, Complicated Stuff
Fable is built for the work that makes other models stumble: deep research, long documents, big multi-step projects, and complex builds. Anything where the task has a lot of moving parts and you need it to hold the whole thing in its head and not lose the thread halfway through.
The receipt: in testing, Stripe used Fable to run a code migration in a single day that would have taken a team of engineers over two months by hand. That is the kind of job it was made for. If a task feels too big to hand to AI, that is exactly the task to give Fable.
Don't Overpay For Easy Work
Quick, Simple, Everyday Tasks
Fable is the premium model. It costs about double to run and it burns through your usage faster. For a quick email, a simple rewrite, or a fast question, it is slower and pricier with no real payoff, you are paying for power you are not using.
Keep Sonnet or Opus for everyday work, and save Fable for the heavy lifting. The skill is not "always use the best model," it is "match the model to the size of the job." Reach for Fable when the task is genuinely hard or huge, not when you are firing off a one-liner.
Two Ways In
In The App And In Claude Code
In the Claude app: open the model picker at the top of your chat (where the model name shows) and choose Claude Fable 5. That chat now runs on Fable. Switch back the same way when you are done with the heavy task.
Building in Claude Code? Set your model to claude-fable-5. You can do it for one session with the /model command, or make it a project's default by adding "model": "claude-fable-5" to that project's .claude/settings.json. New to that file? My power-user settings guide walks through it.
It Thinks For You
Adaptive Thinking Is Always On
With older models you had to decide how hard it should reason. Fable handles that itself. Its adaptive thinking is always on, so it decides how deeply to think based on the question, more for a hard problem, less for a simple one. There is nothing to toggle. You just ask, and it calibrates the effort on its own.
It Never Forgets
A 1 Million Token Memory
Fable can hold about 1 million tokens in mind at once. In plain terms, you can feed it huge documents, whole projects, or a year of notes in a single go and it keeps all of it in view while it works. This is why it is so good at the big stuff: it does not lose the early pages by the time it reaches the end.
Not A Glitch, A Feature
The Opus 4.8 Safety Handoff
On a small number of sensitive topics (under 5% of chats), Fable quietly hands the answer to Opus 4.8 instead. If you ever notice the response style shift on a touchy subject, that is what happened. It is a deliberate safety feature, not a bug, and for almost everything you do, you will never see it.
These are built to show off what Fable does that smaller models cannot: hold a mountain of context, reason through complexity, and carry a long job end to end. Switch to Fable 5 first, then paste one in and fill in the brackets.
Prompt 1
Deep Research Report
Fable can research wide and synthesize it into something you would actually pay a consultant for. Great while it is free.
Copy and fill in the brackets
You are a senior research analyst. I want a deep, decision-ready report on: [TOPIC, e.g. "the at-home red light therapy market for women 30-50 in the US, 2026"] Why I need it: [your real goal, e.g. "I am deciding whether to launch a product in this space in the next 6 months"] Do this in order: 1. Map the landscape: the major players, what they sell, their positioning, and rough pricing. 2. Find the real demand signals: who is buying, what they complain about, what they wish existed (pull from reviews, forums, search trends, anything you can reason about). 3. Identify the 3 biggest gaps or openings a new entrant could win. 4. List the top 5 risks and how serious each one is. 5. Give me a clear recommendation: go, wait, or don't, and the single most important reason why. Format: short executive summary up top (5 bullets a busy person can read in 30 seconds), then the detail under clear headers. Flag anything you are unsure about instead of guessing. End with the 3 questions I should answer next.
What To Do With It
Paste it, fill in the topic and your real goal, and let it run. The more honest you are in the "why I need it" line, the sharper the recommendation. Want true source-cited research? Pair this with Claude's research tools, but even on its own Fable gives you a real starting brief.
Prompt 2
Make Sense Of A Giant Document
This is where the 1 million token memory shines. Drop in a long contract, report, transcript, or PDF and let it actually read the whole thing.
Attach your document, then paste this
I have attached a long document: [what it is, e.g. "a 40-page commercial lease," "a 2-hour meeting transcript," "our full Q2 analytics export"]. Read all of it, start to finish, before you answer. Then give me: 1. The 30-second version: what this document is and the 5 things that matter most in it. 2. The details I would miss: anything buried, unusual, risky, or easy to overlook. Quote the exact line and tell me why it matters. 3. The numbers that count: pull every important figure, date, deadline, or dollar amount into a clean list. 4. What I should actually DO: the concrete next steps or decisions this document forces. 5. The questions to ask: what is missing, vague, or worth pushing back on before I sign / act / share this. Be specific and cite the part of the document you are pulling from. If something is genuinely unclear, say so rather than smoothing over it.
What To Do With It
Upload the file first (drag it into the chat or use the attach button), then paste the prompt. Because Fable holds the whole document at once, it catches the buried clause on page 38 that a quick skim would miss. This one alone is worth the free trial.
Prompt 3
Plan And Build A Real Project
Fable can carry a big multi-step build without losing the plot. Hand it the whole thing, not a tiny piece.
Copy and fill in the brackets
I want to build: [the real thing, e.g. "a simple booking site for my studio where clients pick a time and pay a deposit"]. What I have: [your starting point, e.g. "nothing yet," or "a Squarespace site," or "a folder of files I'll share"]. What I know: [your skill level, e.g. "I'm not a developer but I can follow steps"]. Do not start building yet. First: 1. Ask me up to 5 questions you genuinely need answered to get this right. Wait for my answers. 2. Then give me the full plan: the pieces involved, the order to build them, and what each step accomplishes, in plain English. 3. Flag the 2 or 3 spots most likely to trip me up, and how we'll handle them. Once I approve the plan, build it one step at a time. After each step, tell me what you did, what to check, and what's next. Keep the whole project in mind the entire way, do not lose earlier decisions.
What To Do With It
This works in the Claude app for planning, and is even more powerful in Claude Code where Fable can actually build the files. The "ask me 5 questions first" line is the secret, it forces Fable to understand before it acts, which is the whole reason big builds usually go right or wrong.
Prompt 4
Turn A Year Of Notes Into A Plan
Dump everything, the brain dump, the voice-note transcripts, the scattered docs, and let Fable find the patterns you are too close to see.
Paste your notes in, then this
Below (or attached) is a big pile of my notes: [what it is, e.g. "a year of journal entries," "every idea I've dumped in my notes app," "all my customer call notes"]. It is messy and unsorted on purpose. I want you to make sense of it. 1. Read all of it before responding. 2. Tell me the 5 to 7 themes that actually keep showing up, even the ones I might not have noticed myself. Use my own words where you can. 3. Show me the contradictions: where I say I want one thing but my notes point somewhere else. 4. Pull out the genuinely good ideas that got buried, the ones worth acting on. 5. Give me one clear focus for the next 90 days based on what the notes actually reveal, not what sounds nice. Be honest, even if it is a little uncomfortable. I want the truth in here, not a flattering summary.
What To Do With It
Copy your notes into the chat (or attach the files), then paste this under them. Fable's huge memory means it can actually hold a year of material at once and spot the through-line. The "show me the contradictions" line is where it earns its keep, that is the stuff you cannot see on your own.
Prompt 5
The Big Complex Untangle
The Stripe-migration energy, for whatever your version of a giant tangled mess is. Spreadsheets, a messy process, a system nobody understands anymore.
Copy and fill in the brackets
I have a complicated mess I need untangled: [Describe it, e.g. "my business runs on 6 different spreadsheets that don't talk to each other," or "our onboarding process has 22 steps and nobody knows why," or "I have 3 years of finances across 4 tools"]. What "done" looks like for me: [the outcome you want, e.g. "one clean system I actually understand and can keep up."] Work through it like this: 1. First, map the current mess back to me in simple terms so I know you understand it. Where are the overlaps, gaps, and broken handoffs? 2. Show me the ideal version: what this should look like when it's clean. 3. Give me the migration plan to get from here to there, in phases I can do without breaking what's running today. Lowest-risk steps first. 4. For each phase, tell me exactly what to do and how to know it worked. 5. Call out the one thing most likely to go wrong, and the safety net for it. Take your time and keep the whole picture in view. I would rather you think hard once than give me a shallow answer fast.
What To Do With It
Be specific about the mess and about what "done" looks like, that is what lets Fable build a real plan instead of a vague one. This is the prompt that shows you why a model that can hold everything at once is a different kind of tool. Run it on your biggest headache while the trial is free.
The Real Win
Fable 5 is not "a slightly better Claude." It is the model you reach for when a task is too big, too long, or too complex for anything else, and you leave it alone for the quick stuff. Learn that one habit, match the model to the job, and you get the best results without burning your usage. The free window until June 22 is your chance to feel the difference on your hardest project.
The Only AI Masterclass You Need
If this guide helped, but you’re looking to go deeper, I got you!! My 30-Day Challenge takes you from saving AI tips you never use to actually building with AI, step-by-step.
I show you exactly how I automated two e-commerce brands, my social media, and most of my personal life, then hand you the agents, workflows & systems to do the same. I’m teaching you every single thing I know with one lesson and one build a day.
Join the AI Masterclass →© 2026 Mariah Brunner. All rights reserved.