Hacker Newsnew | past | comments | ask | show | jobs | submit | solenoid0937's commentslogin

Or just don't abuse the subscription and use the API instead.

5.4 kind of falls apart in big/large projects.

Amazing how fickle people are. Yes, Anthropic are the baddies for not letting you abuse their loss leading product.

Can you help me understand how using Claude Code isn't abusive, but Opencode is?

('because they said so, isn't a good answer)


Claude Code is a loss leader, you agree to use it under the terms that you don't hijack the OAuth flow to use other clients.

If you don't like those terms you can use the API.

Using Claude Code's auth flow with OpenCode is no different than using a custom client to abuse Gmail/Google Photos free tier as blob storage.

You get a loss leading product under certain good faith terms, if you break those terms you're abusing the product.


You've still not explained why, you've just reasserted "because they said so".

What is the upside to Anthropic if we use ClaudeCode but not OpenCode? If it is such a loss leader, why would they even offer it? By using it, even within their terms, you are still abusing their good will. No?

(You also said the alternative to not liking the terms is to use their API. There is another alternative, which is to keep using it against their ToS and risk a ban. Or use a different provider. So the situation is more nuanced than "this" or "that")


> you've just reasserted "because they said so".

Yes. That is all that matters. That is the contract you've signed with the business, end of story.

They have their reasons (3P clients suck at caching, this is a subsidized tier to create subscription lock in, etc) but that's besides the point. If you sign a contract, you abide by its restrictions or you categorically abusing the offering.

> There is another alternative, which is to keep using it against their ToS and risk a ban.

No one working on a project of value and no sane business would do this. The people doing this are not serious/mature people. Frankly any dev that intentionally does this at a real company would be fired.


Ah, but the ToS I agreed to didn't state it.. they even admitted it wasn't clear and then unilaterally revised it.

And yes, I agree businesses must abide by the ToS, it would be too much of a business risk not to.. but individual users, using for their own purpose can make their own choice.

An individual choosing to not abide by their unfair ToS is perfectly reasonable and doesn't make them unserious or immature people, and it's pretty weak to make it an ad hominem attack.

But if you think their reasoning is solely that opencode has poor caching, then the solution is to make it chew through the quota quicker (which i think it already does), or provide guidance on how to do it better. The arms race of trying to block it will be a war they will eventually lose.


> then the solution is to make it chew through the quota quicker

This is terrible from a product perspective. Right now they can subsidize workflows with poor caching performance.

If OSS hacked clients become a big thing, they can't do this anymore.


How does that make sense?

If Claude code can have great performance by optimised caching and Opencode doesn't.. I'll run out of quota using a third party client and have a terrible experience, and the choose to use Claude code instead because wit is superior.

So why not simple quota counting?


> So why not simple quota counting?

Consider this: you are Anthropic. There are some Claude Code used cases that will have poor caching performance. Let's say these are 10% of your use cases.

You explicitly don't count cache misses right now because it would make the UX poor for these use cases. It's no big deal since the remaining 90% of use cases can subsidize the 10%.

Now open source clients become a thing. Instead of 10% of usage having poor caching, it grows to 50%. You can no longer subsidize those users because the economics don't work.

You have to start counting cache misses and the UX goes to shit for everyone.


It's trash for larger codebases vs Opus unfortunately.

Quite on the contrary for my experience. xhigh is the only model + thinking level that can reliably locate the bug

Yeah, they're so mean for not letting you abuse their loss leading product under the terms you accepted!

They do charge API users less, I pay 50-90% less when structuring my prompts for caching.

The maintaining team is incredibly petty though. Tantrums when they weren't allowed to abuse Claude subscriptions and had to use the API instead. They just removed API support entirely.

> we did our best to convince anthropic to support developer choice but they sent lawyers

https://x.com/i/status/2034730036759339100


Anthropic has zero problems with API billing, there's no chance they told him to rip that out.

Reading through his X comments and GitHub comments he is behaving immaturely. I don't trust what he's saying here. Ripping out Claude API support was just throwing a tantrum. Weird given his age - he's old enough to be more mature.


‘abuse’. The same rate limits apply, the requests still go to the same endpoints.

Even as a CC user I’m glad someone is forcing the discussion.

My prediction: within two years ‘model neutrality’ will be a topic of debate. Creating lock-in through discount pricing is anti-competitive. The model provider is the ISP; the tool, the website.


> The same rate limits apply, the requests still go to the same endpoints.

That is not the point. That is a mere technicality.

You signed a contract. If you don't ignore the terms of the contract to use the product in a way that is explicitly prohibited, you're abusing the product. It is as simple as that.

They offer a separate product (API) if you don't like the terms of the contract.

Also, if you really want to get technical: the limits are under the assumption that caching works as intended, which requires control of the client. 3P clients suck at caching and increase costs. But that is not the overarching point.

> Creating lock-in through discount pricing is anti-competitive.

Literally everyone does this. OpenAI is doing this with Codex, far more than Anthropic is. It's not great but players much bigger than Anthropic are using discount pricing to create an anti-competitive advantage.


> But that is not the overarching point.

Because that could be easily resolved by factoring % cache hits into the usage limits.

> Literally everyone does this.

Never a strong justification, much as I like Anthropic in general.

Why is the 'Mercedes gas station' selling gas 85% cheaper but only to Mercedes drivers?

Why is the 'Apple electric company' selling cheaper electricity to households with Apple devices?

They're not the strongest analogies, I'll admit, but that's what it smells like to me.


> Because that could be easily resolved by factoring % cache hits into the usage limits.

Absolutely not, you are not thinking from a product perspective at all.

You might not want to capture cache % hits in usage limits because there may be some edge cases you want to support that have low hits even with an optimized client. Maybe your caching strategy isn't perfect yet, so you don't count hits to keep a good product experience going.

OSS clients that freeload on the subscription break your ability to support these use cases entirely. Now you have to count cache hits at the expense of everyone else. It is a classic case of some people ruining the experience for everyone.

> Why is the 'Apple electric company' selling cheaper electricity to households with Apple devices?

Why does Netflix not let you use your OSS hacked client of choice with your subscription?


> Literally everyone does this. OpenAI is doing this with Codex, far more than Anthropic is.

And yet, OpenAI have publicly said they welcome OpenCode users to use their subscription package. So how are they being anti-competitive "far more" than Anthropic?


> And yet, OpenAI have publicly said they welcome OpenCode users to use their subscription package.

It's a PR stunt. They'll eat the costs for a bit, once they've cornered the market they'll do the same thing as Anthropic.


Agree, I find it hard to support them when the team is so obnoxious on X.

API support was never removed

Companies are absolutely allowed to lock down their own products. Netflix is a great example, you don't bring your own client for Netflix.

The whining/entitlement in this thread is ridiculous. The API is always there for you to use as you desire.

If you want to use the loss leader on the other hand, you agree to abide by certain terms. But if you don't want to do that, just use the API. It's not that hard.


This just increases the price for everyone. The API is always there if you don't want to use the loss leader. The entitlement in this thread is insane.

This is such an incredibly entitled take

You are given a loss leader product under certain terms for a very cheap price. The ONLY condition is that you respect the terms.

Instead of doing that you go off on this rant about how you shouldn't have to respect the terms and the company is evil for imposing terms at all!

The Claude API is RIGHT THERE if you don't want to use the loss leader. Where is this entitlement coming from!?

Sure Codex lets you do this for now, but VC money is finite and people won't let you abuse their free loss leaders forever.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: