Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw • Hacker News Board

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#391

Post by Fogest » Sat, Apr 04, 2026, 3:30 AM UTC

noritaka88 wrote: post #161

[flagged]

I am pretty sure Claude Code limits were being hit so fast recently because there was an increasing amount of OpenClaw style usage on the subscription. From tweets from the people in charge it sounded like they were having more usage than they expected which was causing them to have to be more aggressive on the rate limits. They said they were working to address it soon. I have a feeling this is what they were working on changing. I bet OpenClaw was the reason for the rate limiting being so bad lately.

I'm hoping with this change we see the rate limits start to not be as rough.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#392

Post by goosejuice » Sat, Apr 04, 2026, 3:31 AM UTC

hombre_fatal wrote: post #377

goosejuice wrote: post #225

Earlier quoted context omitted.

Well earnest here just means using Claude code directly or the Claude app. Both that just happen to support using tokens while you sleep!

Defining earnest (placeholder word btw) is the hard part of the trade-off, though. When your least automated, most interactive users are competing for capacity with fully-automated tools, let's say, you're forced to define some sort of periphery between these groups. OpenClaw is a self-directed, automated loop that sits on a server. It's wowing its owner by shitposting on moltbook and doing any number of crazy storie…

Claude code has /loop. Claude app has scheduled tasks. The leaked source has a proactive mode.

I'm sorry but this framing just doesnt make sense.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#393

Post by nl » Sat, Apr 04, 2026, 3:32 AM UTC

wigglewoggle wrote: post #379

nl wrote: post #374

I suspect people are misdiagnosing the root cause of why Anthropic is doing this a bit. I don't think this is particularly about the financial impact of people using OpenClaw - they can adjust the amount of tokens in a subscription quite easily. I think the root cause is that Anthropic is capacity constrained so is having to make choices about the customers they want to serve and have chosen people who use Claude Cod…

I'm at large company and pretty much everyone has settled on opus or sonnet 4.6. We would absolutely not allow something like OpenClaw on our network so your point kinda fits here where, if capacity is constrained, then by setting focus away from OpenClaw you're essentially prioritising the enterprise clients. Just spitballing of course

Yes exactly.

I doubt they actually want to do this.

They clearly see having a wide set of paying customers as valuable (otherwise they'd just raise prices) but if you are stuck having to make hard choice then I can see the attraction of this approach.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#394

Post by wat10000 » Sat, Apr 04, 2026, 3:32 AM UTC

neonstatic wrote: post #273

colechristensen wrote: post #192

Earlier quoted context omitted.

I don't understand this perspective. I can't imaging a point where I won't want to ask "what's the weather like?" "please turn off the lights" "what is the airspeed of an unladen swallow?" likewise chatting through directing it to build something or solve a problem, voice or typing will each have their place. And video calling did take off, plenty of people use facetime and almost everybody working in an office uses…

> I can't imaging a point where I won't want to ask "what's the weather like?" "please turn off the lights" To help with understanding that perspective, I cannot imagine a scenario where I would ask a device connected to the internet to turn off the lights. I literally never wanted this. A physical switch is a 100% non negotiable for me. I feel the same way about non-mechanical car doors. Perhaps due to that outlook…

You don't watch Iron Man and want a JARVIS? Current systems are pretty far away from that, but that's the overall draw.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#395

Post by davesque » Sat, Apr 04, 2026, 3:38 AM UTC

I'm honestly completely in favor of this. Anthropic obviously budgets their capacity based on projected human usage patterns coming through their native app suite (Claude Cowork, Claude Code, etc.). They should not be expected to shoulder the burden of community tools like OpenClaw that are effectively designed to strategically max out usage windows on the plan. That has clearly caused issues with uptime in the past couple of months and I've gotten pretty fed up with the degraded service quality while I'm just trying to use Claude Code as it's intended to be used. I'm happy to see they're doing something about this. Seems like a totally fair move to me. I'd rather that Claude Code functions well when I'm using it according to its design.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#396

Post by dimmke » Sat, Apr 04, 2026, 3:38 AM UTC

what wrote: post #349

dimmke wrote: post #285

Earlier quoted context omitted.

If people are finding new ways to use AI, they should change how they bill. Banning third party harnesses is bad for a lot of reasons - it looks like they're trying to force people to use their software. Strategically it might make sense - gives them a tiny moat if their models ever slip - but it discourages the breakneck pace of innovation and the long term effect is that their customers (largely highly skilled with…

They don’t need to change how they bill. Your subscription is for Claude app/code. Otherwise you pay per token. It’s always been this way.

Claude Code is a subscription tier explicitly designed for agentic, automated, heavy usage. So the 'subscriptions are for human use, API is for automation' line is already blurry by their own offerings.

If the actual concern is use pattern, enforce that directly. What we have instead is metered usage + behavioral restrictions + product fragmentation across three separate offerings.

That's not a clean billing philosophy, it's layers of control stacked on top of each other with no coherent logic tying them together.

If subscriptions are for humans and API is for automation, fine. But then don't meter the human product arbitrarily and don't sell a subscription tier for automation while also restricting automation. Pick a lane.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#397

Post by gbear605 » Sat, Apr 04, 2026, 3:40 AM UTC

goosejuice wrote: post #392

hombre_fatal wrote: post #377

Earlier quoted context omitted.

Defining earnest (placeholder word btw) is the hard part of the trade-off, though. When your least automated, most interactive users are competing for capacity with fully-automated tools, let's say, you're forced to define some sort of periphery between these groups. OpenClaw is a self-directed, automated loop that sits on a server. It's wowing its owner by shitposting on moltbook and doing any number of crazy storie…

Claude code has /loop. Claude app has scheduled tasks. The leaked source has a proactive mode. I'm sorry but this framing just doesnt make sense.

Even with those tools, the usage of Claude Code with all of them turned on is going to trend much lower than OpenClaw usage. Everyone that I've seen with OpenClaw will intentionally waste tokens just to make sure they hit the cap, even if they're doing useless stuff with it. And it can be going 24/7, every minute constantly, while the intended purpose with scheduled tasks is to use them at a set rate but not nearly constantly.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#398

Post by Wowfunhappy » Sat, Apr 04, 2026, 3:40 AM UTC

Claude is a UNIX command line tool with an SDK. Yes there's an interactive mode, but it can be invoked as a normal utility too, and piped to other tools and so on.

In that context, I don't understand the difference between a "third party harness" and a shell script.

How are they even detecting OpenClaw?

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#399

Post by jmalicki » Sat, Apr 04, 2026, 3:42 AM UTC

fluoridation wrote: post #383

Yokohiii wrote: post #372

Earlier quoted context omitted.

Those yottabytes of VRAM are also consuming electricity constantly.

The difference being that an LLM request is not an operating system. Since they're compartmentalized and ephemeral, you can very easily distribute requests among your available hardware so that you can switch off machines during periods of low activity.

Your capital costs for buying those machines don't go away.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#400

Post by gbear605 » Sat, Apr 04, 2026, 3:42 AM UTC

dimmke wrote: post #285

rovr138 wrote: post #248

Earlier quoted context omitted.

>They have to be honest about what they can offer for $200 Their expectation must have been a human using the service at a human capacity. This is different from an automated agent orchestrating a ton of different agents at the same time doing a lot of things. There is a difference.

If people are finding new ways to use AI, they should change how they bill. Banning third party harnesses is bad for a lot of reasons - it looks like they're trying to force people to use their software. Strategically it might make sense - gives them a tiny moat if their models ever slip - but it discourages the breakneck pace of innovation and the long term effect is that their customers (largely highly skilled with…

They already have the way that you're supposed to bill for usages like this, the API usage. The purpose of the subscription plan is strictly for the cases where you are using few enough tokens on average that it's not a money pit for them.