Anthropic banned a Claude Code account routed through a proxy to OpenAI

The Information reports that Anthropic shut down a Claude Code account within 15 minutes of the developer routing it to OpenAI's GPT-5.6 Sol through a code proxy. Reporter Alix Coutures writes that Boris Cherney, who heads Claude Code at Anthropic, became part of the online argument that followed. Only three facts from the piece are used here because the article is behind The Information's paywall.

What the developer did, and what happened next

Alex Getman built a proxy in code that let him type into Claude Code and have the requests answered by OpenAI's GPT-5.6 Sol. Fifteen minutes after his first coding request was sent, Anthropic ended the account, according to the piece. Getman's posts about the ban got a million views within hours, which is why the story became visible to anyone outside the small group actually running this setup.

The Information describes the practice as a way to cut costs. Developers are running Claude Code with cheaper non-Anthropic models to save money, since the tool includes the parts a coding session needs (a file reader, a shell runner, a codebase search, a parallel task runner) and does not, as a matter of code, require Anthropic's own models to answer the questions.

Why the split matters

Claude Code as a piece of software has two independent parts that are easy to confuse. One is the harness: the parts that read files, run shell commands, search code, and coordinate parallel tasks. The other is the model that answers when the harness asks a question. The harness has value on its own, which is what Getman and others are trying to get without paying Anthropic's model prices.

Anthropic's terms of service treat that separation as a boundary, and the ban is the first widely-visible confirmation that the enforcement is fast and automated enough to catch a proxy inside the first few minutes of use. Fifteen minutes is the timescale of a real-time telemetry check on outbound traffic, or a check on the request format, which changes when the model is swapped.

What this means for a team using Claude Code

A team paying for Claude Code today has to make a decision it did not have to make yesterday. Routing Claude Code through a proxy to a cheaper model is against Anthropic's terms, and Anthropic will now find that setup fast when it looks. A subscription that a team also uses for its daily work can be lost before the money saved by switching models covers a week of costs.

A legitimate version of the same idea is to run a coding harness that supports several model providers by design. Several open-source harnesses work that way, and swapping models is what they are for. The piece does not name a preferred alternative, and this story is not the place for a comparison. What it does establish is that people were quietly using this setup until last week, and there is now a public example of the result: the account is closed.

Source

The Information: Developers Find Ways to Use Claude Code Without Anthropic Models by Alix Coutures, 15 September 2026. Getman's own post on the ban, linked from the article.