There’s the argument that Anthropic has built Claude Code to use the models efficiently, which the subscription pricing is based on.
Maybe there’s some truth to that, but then why haven’t OpenAI made the same move? I believe the main reason is platform control. Anthropic can’t survive as a pipeline for tokens, they need to build and control a platform, which means aggressively locking out everybody else building a platform.
Alternatively products like openclaw have an outsized impact on Anthropic's infrastructure for essentially no benefit to them. Especially when you're taking advantage of the $200 plan.
OpenAI has never shyed away from burning mountains of cash to try and capture a little more market share. They paid a billion dollars for a vibe coded mess just for the opportunity to associate themselves with the hype.
No, I'm paying $200 a month for a premium product that I expect premium service for. It's the single most expensive IT expense I have. Taking advantage my foot.
Can you imagine paying the actual cost of it, or a subscription cost that at least ballpark matched it? I don't think I have a single friend or acquaintance who realistically would.
You are simply a bit too entitled. It's not a premium product and honestly not that expensive in my opinion either (though that is going to depend on your location).
You may want to learn the difference between someone being able to pay API rates and someone willing to pay API rates. I'm sure many people on HN are able to pay API rates and almost all of them aren't willing to pay API rates. The providers know this hence why subscriptions exist. API is almost solely used by companies as almost no private person would be willing to pay that.
“You may want to learn” such choice way to introduce your position which is really not much of one.
If you are going to come and complain about a $200 subscription that gives you $400 worth of API tokens there is only so much room to complain. Only so many lemons can be squeezed. Hope that was a helpful for you.
It is not a premium service, it simply is buying you more tokens. Those $200 gives you at least $400 in API cost tokens.
Don't confused price with "premium service". It was not that long ago that folks would be spending $100-200 on their cable service bundle. You are buying a subsidized product when using the plan and the more you spend the more tokens you get, has nothing to do with being a premium service.
I think it's a training data thing. They can only gather valid training data from real human interactions, so they don't want to subsidize tokens for purely automated interactions.
> Why were third party harnesses banned? Surely they'd want sticking power over the ecosystem.
Third-party harnesses are the exact opposite of stickiness!
Ditching Claude Code for a third party harness while using the Claude Code subscription means it's trivial to switch to a different model when you {run out of credits | find a cheaper token provider | find a better model}.
To be clear they weren’t banned from Claude usage, they were required to use the API and API rates rather than Claude Max tokens.
Claude code uses a bunch if best practices to maximize cache hit rate. Third party harnesses are hit or miss, so often use a lot more tokens for the same task.
I'm watching a conference talk right now from 2 weeks ago: "I Hated Every Coding Agent So I Built My Own - Mario Zechner (Pi)", and in the middle he directly references this.
He demonstrates in the code that OpenCode aggressively trims context, by compacting on every turn, and pruning all tool calls from the context that occurred more than 40,000 tokens ago. Seems like it could be a good strategy to squeeze more out of the context window - but by editing the oldest context, it breaks the prompt cache for the entire conversation. There is effectively no caching happening at all.
They are working with the same tools and knowledge like Anthropic does as Caching practices are documented. And they have as much incentive as Anthropic does to not waste compute. Can we stop acting like people who build harnesses be it Opencode oder Mario Zechners Pi are dumbfucks who don't understand caching?
Yep, that's the reason for the new Extra Credit feature in Claude Code. Some people were wiring up "Claude -p" with OpenClaw, so now Anthropic detects if the system prompt contains the phrase OpenClaw, and bills from Extra Credit if that happens:
Claude Code was the best harness from roughly around release to January this year. Ever since then, it's become more and more bloated with more and more stuff and seemingly no coherent plan or vision to it all other than "let's see what else that sounds cool we can cram in there."
1. openclaw like - using the LLM endpoint on subscription billing, different prompts than claude code
2. using claude cli with -p, in headless mode
The second runs through their code and prompts, just calls claude in non-interactive mode for subtasks. I feel especially put off by restricting the second kind. I need it to run judge agents to review plans and code.
Maybe there’s some truth to that, but then why haven’t OpenAI made the same move? I believe the main reason is platform control. Anthropic can’t survive as a pipeline for tokens, they need to build and control a platform, which means aggressively locking out everybody else building a platform.