On January 9th, people using Claude Code subscription inside of OpenCode, started seeing a message "This credential is only authorized for use with Claude Code".
It wasn't a bug, Anthropic added this restriction on purpose. Here's the explanation by Thariq from Claude Code:
"Yesterday we tightened our safeguards against spoofing the Claude Code harness after accounts were banned for triggering abuse filters from third-party harnesses using Claude subscriptions.
Third-party harnesses using Claude subscriptions create problems for users and are prohibited by our Terms of Service.
They generate unusual traffic patterns without any of the usual telemetry that the Claude Code harness provides, making it really hard for us to help debug when they have questions about rate limit usage or account bans and they don’t have any other avenue for this support."
My personal opinion. It seems logical from business perspective, especially with new tools like Clawdbot, Auto Claude and others appearing and use A LOT of Claude tokens, they were almost forced to make this decision, in my opinion.
Not a pleasant situation, but hey, they control the best LLM at the moment (Opus 4.5) and users are generally happy with Claude Code performance, so it makes sense they would restrict potentially abusive third-party systems, to preserve their own profit margin and keep the system running properly for their direct customers using Claude Code.
Soon, a lot of people reacted to the situation, here are just a few YouTube videos:
- Theo: Anthropic just burned so much trust...
- Better Stack: Anthropic's Latest Move: Why OpenCode Users Are Worried
- Melkey: Anthropic is cracking down...
Also, it became a great opportunity for Anthropic's competitors OpenAI to offer their services here!
So, dax tweeted that in opencode v1.1.11, you can now use your ChatGPT Plus/Pro plans in OpenCode.
