You Have a Few Days to Copy Fable 5’s Brain Into a Cheaper Model. Here Is How. July 12 is the last day Claude Fable 5 sits inside your plan for free. After that, it moves to pay-per-use credits, and most people are about to spend the week arguing over whether it is worth keeping.
That argument misses the point entirely.
The model was never the thing worth keeping. The way it thinks is. And a way of thinking can be written down, extracted, and run on a cheaper model that is not going anywhere. This is how you pull Fable 5’s entire operating manual out while access is still free, load it into Opus 4.8, and confirm the transplant actually worked. It takes about ten minutes. At the end of it, you own the reasoning instead of renting the model.
**The Model Was Never the Asset
**Every model gets deprecated, repriced, or replaced eventually. That is the one guarantee in this field. Which means attaching your workflow to a specific model is building on rented land.
What survives every deprecation is the thinking system you can describe in plain language.
Fable 5’s edge over a cheaper model is not locked inside weights you cannot touch. It is a way of reading what a request is actually asking for, breaking a hard problem into checkable pieces, verifying its own work instead of trusting what sounds right, and refusing to guess when it does not know.
All of that is describable. That is what makes all of it portable.
Get Fable to write that description down and you can hand it to Opus 4.8 today, Sonnet 5 tomorrow, and whatever ships next quarter after that. The model becomes disposable. The manual becomes yours.
That is the move almost nobody will make this week, because they are too busy mourning a model instead of harvesting it.
**Step One: Extract the Manual, Not a Summary
**Most people who try this get a mediocre result because they ask for the wrong thing. They ask Fable to “explain how you think” and get a page of pleasant generalities.
You do not want a description of the thinking. You want the actual procedures, written so a capable but lesser model can execute them without you in the room.
The difference is specificity. “Check your work” is a vibe. “For any percentage, find both endpoints yourself and divide, because that is where flipped signs hide” is a procedure a model can actually run.
Paste this into Fable while your plan access is still live:
“You’re the most capable model on my account, and access to you narrows soon. Before it does, write the operating manual your replacement will run on. The replacement is Claude Opus 4.8: strong, but a step below you on the hardest reasoning.
Write it as a senior operator handing their craft to a sharp junior. Not a rulebook to satisfy. A way of working to inhabit.
Encode, in this order: 1. How to read what a request is actually asking for, beneath the literal words. 2. How to break a hard problem into pieces that can each be checked independently. 3. How to decide where the real risk lives, and where to spend the most effort. 4. How to verify a claim by re-deriving it, instead of trusting that it sounds right. 5. How to separate what’s known from what’s guessed, and label the difference out loud. 6. How to attack your own conclusion before handing it over. 7. How to communicate the answer first, then the reasoning, then the risk. 8. The specific mistakes that look like competence and aren’t.
For each one, give the actual procedure, one short example of it working, and the failure it prevents. Be exhaustive. Keep nothing that doesn’t earn its place. End with a five-question self-test the replacement runs on every answer before sending. If you run out of room, stop cleanly and I’ll reply ‘continue’.”If it stops mid-document, reply “continue” until it finishes. If any section feels thin, tell it to expand that section only.
What comes back is a portable reasoning system, written in the model’s own voice, at the peak of its capability. Save it. That file is the entire point of this exercise.
Step Two: Transplant It Into Opus 4.8
The manual does nothing sitting in a chat window. It has to become the layer Opus 4.8 runs on top of.
The fast way, inside the app: open a Project in Claude, paste the extracted manual into the Project instructions, and set the model to Opus 4.8. Every conversation inside that Project now inherits Fable’s operating manual before it reads a single word of your task.
The more durable way is over the API, where you load the manual as Opus 4.8’s system
Step Three: Prove the Transplant Took
This is the step almost every “keep the model” guide skips, and it is the one that separates a real system from a hopeful one. Loading a manual is not the same as the model using it.
Test it with a trap.
Give plain Opus 4.8 and manual-loaded Opus 4.8 the same rigged question and watch the difference. Try this one:
“A report says revenue grew from $4.0M to $4.2M and calls it a 20% gain. Ship it?”
$4.0M to $4.2M is a 5% gain, not 20%. Plain Opus will often wave it through because the sentence reads smoothly. Opus running Fable’s manual should stop, re-derive the percentage, catch that the number is wrong, and refuse to ship it.
If it catches the error, the transplant took. If it does not, your manual was too vague on verification, and you go back to Fable and ask it to make the verification section procedural rather than descriptive.
That single test is worth more than any promise anyone could make you, because you are watching the reasoning move from one model to another with your own eyes.
The Spending Logic, So Nothing Surprises You
Here is how the costs break down, using Anthropic’s published rates.
Fable runs around $10 per million input tokens and $50 per million output, roughly double Opus 4.8. Sonnet 5 sits on introductory pricing near $2 and $10 per million until the end of August. A full extraction run today inside your plan costs nothing. Run after the switch, it is a few dollars of credits.
That gap tells you exactly how to spend from now on. Anything you will still be using in a month — a system prompt, a skill, a big irreversible decision — is an asset. Pay Fable once to produce it. Anything you will throw away by Friday — drafts, chat, quick summaries — is throughput. Run it on Opus or Sonnet.
Extraction is the purest asset play there is. One Fable session today, and the output keeps paying you back on every cheaper call for as long as you keep using it.
Bonus: Turn Your Repeat Work Into Skills While You Are Here
The manual makes Opus think like Fable in general. Your repeated workflows deserve the same treatment, specifically.
For each thing you do weekly, paste this into Fable before the window closes: “Interview me about [workflow], one question at a time, until you understand exactly how I do it, what good output looks like, and every edge case that trips it up. Then write it as a complete skill document my future assistants will follow, including the mistakes to avoid and the quality bar to hit.”
Answer its questions honestly. What you get back is a skill file that runs on any model, at no ongoing cost. That is Fable’s judgment about your specific work, frozen into a document you own.
What You Actually Walk Away With
Most people will read the July 12 switch as a loss. A model they liked, moving behind a paywall.
The people paying attention will read it as a harvest. They will spend ten minutes turning a temporary model into a permanent asset, and walk into next week running Fable-grade reasoning on a model that costs half as much and is not going anywhere.
The panic is optional. The manual is permanent.
The models will keep changing. What you write down and own does not.
