Lots of arguing about semantics of what the subscription is actually intended for.
Claude Code, as a coding assistant, isn't even mediocre, it's kind of crap. The reason it's at all good is because of the model underneath - there's tons of free and open agent tools that are far better than Claude Code. Regardless of what they say you're paying the subscription for, the truth is the only thing of value to developers is the underlying AI and API.
I can only think of few reasons why they'd do this: 1. Their Claude Code tool is not simply an agent assistant - perhaps it's feeding data for model training purposes, or something of the sorts where they gain value from it. 2. They don't want developers to use competitor models in any capacity. 3. They're offloading processing or doing local context work to drive down the API usage locally, making the usage minimal. This is very unlikely.
I currently use Opus 4.5 for architecting, which then feeds into Gemini 3 Flash with medium reasoning for coding. It's only a matter of time before Google competes with Opus 4.5, and when they do, I won't have any loyalty to Anthropic.
The other harnesses would arguably give them even richer data and product insights.
For AI companies the access to the interaction is very valuable, that explains the price difference. It is data that the competition does not have access to. Of course they are storing that data for model training purposes, that's the whole reason this exists in the first place. They are subsidizing until they get their quality up to the point that the addiction is so strong you won't be able to get through your workday without it. And then surprise the per month access fee will start to rise.