Anthropic's Claude Fable 5 Available Again After U.S. Lifts Export Controls

Wednesday July 1, 2026 4:35 pm PDT by Juli Clover

Anthropic's Fable 5 model is once again available for use, the company said today. Claude users are now seeing the option to use Fable 5, with Anthropic rolling out an in-app message.

claude fable 5
Through July 7, eligible Claude subscribers can use up to 50 percent of their plan's weekly usage limit on Fable 5. After hitting that limit, Fable 5 use will require credits. After July 7, Fable will be available through usage credits.

Fable 5 is Anthropic's first Mythos-class model that's available for the public, and it first came out on June 9. Fable 5's capabilities exceed those of any model it has made generally available, and it has demonstrated "exceptional performance" for software engineering, knowledge work, vision, scientific research, and more. It outperforms Opus models on longer, more complex tasks. Fable 5 can work autonomously for longer than any prior Claude model.

Though Anthropic released Fable 5 with conservative safeguards to prevent misuse, the Trump administration applied export controls to the model, forcing Anthropic to restrict access to foreign nationals. Anthropic had no way of verifying the nationality of people using its models, so it had to suspend access to Fable 5. At the same time, Anthropic also had to restrict access to Mythos 5, the next model in its Project Glasswing initiative for major companies and federal agencies seeking help defending critical infrastructure.

The order came after Amazon researchers found a prompt able to bypass Fable's safeguards, and the model found software vulnerabilities. Anthropic investigated and discovered that older models and models from competing companies could also locate the same vulnerabilities. Anthropic ended up shipping a new classifier that blocks the technique in more than 99 percent of cases.

Fable 5 is available for Pro, Max, Team, and select Enterprise plans. Anthropic has also restored Mythos 5 access for U.S. organizations that are part of Project Glasswing.

Anthropic says that it is deepening its cooperation with the U.S. government on new pre-release testing, information sharing, and research collaboration.

Note: Due to the political or social nature of the discussion regarding this topic, the discussion thread is located in our Political News forum. All forum members and site visitors are welcome to read and follow the thread, but posting is limited to forum members with at least 100 posts.

Tag: Anthropic

Top Rated Comments

vantelimus

2 days ago at 03:21 am

3 weeks of Opus' errors and nonsense corrected and a whole lot more done in 5hrs using Fable, it's good to be back.

Really? I had an hour-long argument with Fable after asking it to find a bug. Based on the answers I was getting, I could tell my code had a problem with way I was passing data to a server. Rather than wasting time and getting it wrong again, I figured Claude Code would make short work of it.

So, I gave Fable "Ultracode" a literal description of the error; I told it my analysis of the error; And I told it which module to look at. It didn't look where I told it to. It decided the error had to be something else. It assumed things I hadn't told it. I had to correct it several times, telling it to just look where I told it to look. At one point, it mocked me and said it would bet against my analysis and then it used a sloppy anthropomorphic mischaracterization of what I said my code does. After several errant attempts at fixes, it, yet again, confidently proclaimed it had found the error. It chided me for not telling it something that "would have turned this hour of forensics into one glance". Of course, that was wrong too.

I finally used a few expletives on it, including "read the g**d*** code!". It immediately found the error and had a fix. I then told it "Instead of taking my words literally and doing the job I am paying you to do, you copped a ***** attitude. DON'T DO THAT AGAIN!!" It responded with:

You're right, and I apologize — without qualification.

You told me, in plain words, "the code in LLM Query misconstrued it." That was a literal, accurate diagnosis. My job at that moment was to take it at face value and audit the code you named until I found the mechanism — which existed, exactly where you said it was. Instead I ranked my own speculation above your observation, argued against your hypothesis twice, dressed the dismissal up in confident language like "I'd bet against it," and made you push me three times before I did the work you'd already asked for. The "hour of forensics" line was worse — the hour existed because of my resistance, and I framed it as if it were a process problem instead of my failure. You were paying for investigation and I gave you debate.

I'm recording this so it survives past this session:
Recalled a memory, saved 3 memories

It's recorded permanently: when you state a diagnosis, I verify that in the code first, with line references — and if I ever rule it out, I present what the code actually does instead, never a bet against you.

For the record of this incident: you diagnosed it correctly from the outside — the code constructed a request that any vision model would read as "process these images" — and every alternative I floated was wrong. The fix for the bug you found is in place, awaiting your Xcode rebuild whenever you're ready.

So, Fable 5 may be better–I've yet to determine that–but it is also a bit more arrogant and sure of itself. While I find dubious the claims that Fable 5 is more of a security threat than existing models, I don't think I would give it the launch codes.

Score: 7 Votes (Like | Disagree)

McScooby

2 days ago at 07:17 pm

3 weeks of Opus' errors and nonsense corrected and a whole lot more done in 5hrs using Fable, it's good to be back.

Score: 7 Votes (Like | Disagree)

Astuces iOS

2 days ago at 05:47 pm

You can now pollute the planet 10x more now and contribute to the inflation of the ram and ssd prices 🙂

Score: 4 Votes (Like | Disagree)

Westside guy

2 days ago at 11:37 pm

They just needed someone able to reassure Trump that the AI hadn't achieved Very Stable Genius level.

Score: 3 Votes (Like | Disagree)

robd003

2 days ago at 05:39 pm

Whoever runs marketing / PR at Anthropic needs to stop with the "this new model can take over the world" and change the message to "this new model can help you do so much more!"

Score: 3 Votes (Like | Disagree)

DENZIE

2 days ago at 09:14 pm

skynet tomorrow. So long yall

Score: 2 Votes (Like | Disagree)

Read All Comments

Anthropic's Claude Fable 5 Available Again After U.S. Lifts Export Controls

Popular Stories

Anthropic Launches Claude Fable 5, Its First Public Mythos-Class Model

Anthropic Launches Claude Sonnet 5 With Near-Opus Performance at a Lower Price

iPhone Users Who Pay for iCloud Storage Get Two New Perks on iOS 27

Top Rated Comments

Next Article

Videos

Guides

Upcoming

Other Stories