Credit: Shutterstock
Anthropic’s two most advanced AI models are back online after the White House reversed an 18-day suspension order.
On July 1, 2026, Anthropic restored public access to Claude Fable 5 and expanded access to Claude Mythos 5 after the U.S. Department of Commerce lifted the export ban.
The reversal ended a standoff between the AI company and the Trump administration that began three weeks earlier, when the government cited national security concerns and ordered Anthropic to block foreign nationals from using the models.
The directive followed a report from Amazon researchers describing a way to bypass Fable 5’s safety measures, a technique commonly called a jailbreak.
Over the following two weeks, Anthropic worked with the Commerce Department, the White House, and outside partners, including Amazon, to address the issue.
The AI company trained an improved safety classifier that blocks the specific jailbreak technique described in the Amazon report in more than 99% of cases. When a request is blocked, it is automatically routed to Anthropic’s Opus 4.8 model instead. Researchers at the National Institute of Standards and Technology reviewed both the original and updated safeguards and found them highly effective, according to Anthropic.
On June 26, Commerce Secretary Howard Lutnick approved renewed access to Mythos 5 for a group of trusted U.S. organizations, including companies that operate and defend critical infrastructure. Four days later, on June 30, the Commerce Department lifted all remaining export controls on both models. Lutnick said the department had worked closely with Anthropic to review Fable 5 and confirm it met government standards.
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5.
We'll begin restoring access tomorrow, and will share an update soon.
We’re grateful to our users for their patience, and to everyone who worked with us on…
— Anthropic (@AnthropicAI) June 30, 2026
Fable 5 became available again on July 1 across the Claude platform, Claude.ai, Claude Code, and Claude Cowork. Anthropic said it would restore access on Amazon Web Services, Google Cloud, and Microsoft Foundry as soon as possible. Subscribers on Pro, Max, Team, and some Enterprise plans will receive up to 50% extra weekly Fable 5 usage through July 7 to make up for the disruption. Mythos 5 continues to expand through Project Glasswing to additional domestic and international partners.
Fable 5 is back. pic.twitter.com/9RTGUCcPHy
— Claude (@claudeai) July 1, 2026
The episode marks one of the most direct uses of U.S. Export Control Authority against a commercially available AI model. It also set a precedent that reached beyond Anthropic. OpenAI limited the initial rollout of its new GPT-5.6 model to a small group of trusted partners at the government’s request around the same time.
Anthropic’s relationship with the Trump administration has been strained in other ways too.
In March 2026, the company sued the Department of Defense after Defense Secretary Pete Hegseth labeled Anthropic a supply-chain risk. That case remains unresolved.
Anthropic said it is working with Amazon, Google, Microsoft, and other Project Glasswing partners on a shared framework for rating the severity of AI jailbreaks. The framework would score each technique based on factors such as how easy it is to discover and how much extra capability it unlocks. Anthropic also agreed to give the government early access to future models that significantly advance capabilities relevant to national security, in line with a recent executive order on frontier AI review.
For now, Fable 5 and Mythos 5 are back in the hands of the users they were built for. Whether this arrangement holds or another jailbreak report triggers a new shutdown remains an open question for the AI industry to watch.
