Anthropic says OpenClaw-style Claude CLI usage is allowed again

No, it's just that it's confusing, because there are two ways of using Claude Code credentials:

1. Take the oauth credentials and roll your own agent -- this is NOT allowed

2. Run your agentic application directly in Claude Code -- this IS allowed

When OpenClaw says "Open-Claw style CLI usage", it means literally running OpenClaw in an official Claude Code session. Anthropic has no problems with this, this is compliant with their ToS.

When you use Claude Code's oauth credentials outside of the claude code cli Anthropic will charge you extra usage (API pricing) within your existing subscription.

> No official statement and not even a tweet?

Release notes and announcements are a well-known agentic anti-pattern.

If you're doing them, you're doing agentic wrong. /s-ish-also-cry

I think this is consistent with the Anthropic announcement. I do not see anything on this page that says it will NOT be charged as extra usage.

The most recent Anthropic announcement was not that people would be banned for using subscriptions with OpenClaw, but that it would be charged as extra usage. I think the reason this was changed three days after that announcement is that being charged for extra usage meant people would not be banned for using their subscription OAuth tokens directly against the Anthropic API with a third party harness, as they had been before. But rather both that usage, and the more recent claude -p usage both be charged as extra usage.

This is called FUD, amplify negativity, silence positivity

> Switching to other providers is the best way to go, if you want to keep your insanity.

Best and most applicable typo ever ʕ ´ • ᴥ •̥ ` ʔ

This is such a strange way for this to be announced. Why is openclaw telling us this? I wouldn't even trust it until Anthropic says so themselves.

The most recent Anthropic announcement was not that people would be banned for using subscriptions with OpenClaw, but that it would be charged as extra usage. I think the reason this was changed three days after that announcement is that being charged for extra usage meant people would not be banned for using their subscription OAuth tokens directly against the Anthropic API with a third party harness, as they had been before. But rather both that usage, and the more recent claude -p usage both be charged as extra usage.

I don't see anything on this page that claims something different from that, or that addresses that claim at all.

> Switching to other providers is the best way to go, if you want to keep your insanity

I remember when I’d periodically rage quit from Uber One to Lyft Pink and back again every time I had a terrible customer-service experience. In the end, I realized picking a demon and getting familiar with its quirks was the better way to go.

I’m currently sticking with Claude, in part because I’m not exposed to this nonsense due to OpenClaw, in larger part because of the Hegseth-Altman DoD nonsense. More broadly, however, I’m not sure if any of Google, Anthropic or OpenAI are coming across as stars in AI communication and customer service.

you know how s bunch of IT people are trying to "escape the permanent underclass" well it seems like anyone building their tools on cloud providers is doing the opposite. theyre willingly bexoming the underclass in hopes it trickles down

> until they all or sudden update their policy tomorrow that retracts everything.

Oh no. They won't update the policy. Boris or Thariq will casually mention in a random off-hand commebt on Twitter that this is banned now, and then will gaslight everyone that this has always been the case.

If you want LLMs to continue to be offered we have to get to a point where the providers are taking in more money than they are spending hosting them. And we still aren't there (or even close).

Boiling the frog is an art form. You've got to know when to turn up the heat and when to let it simmer.

Would you please think of the shareholders

Aren't they just doing what Hacker News was trying to tell them to do? That AI is useful but not sure if sustainable. Now they're increasing prices and decreasing tokens and you guys are pissed off.

It's almost like they want me to switch to the Chinese clones - which they consider malicious actors.

They said from the beginning it was compute constraint and that OpenClaw was causing way more usage than they could handle

Wait, how?

I had an idea on a whim to vibe-engineer an irccloud replacement for myself.

Started with claude web + Opus 4.7 and continued with Claude Code. Ate up two full cycles of my quota in maybe 6-10 prompts.

Then I iterated on that with pi.dev+codex for HOURS, managed to use 50% of my Codex Pro subscription.

Consider Z.ai if you need "bulk" usage, GLM is now very good. They still have the occasional API brown out however.

I used to use GLM mostly and had a Claude Pro subscription for occasional review and clean up.

Now I just use GLM.

I do think Claude Max is value for money. But it's more value than I personally need and I like Anthropic less and less.

GPT-5.4 brutally consumptive for sure. It's not very verbal, but gpt-5.3 codex is wildly smart about coding & planning, and way way less token hungry.

I’ve been using Codex Pro since they lobotomized Opus 4.6. Codex is so much better, GPT 5.4 xhigh fast is definitely the smartest and fastest model available.

For a while there I had both Opus 4.6 and Codex access and I frequently pitted them against each other, I never once saw Opus come out ahead. Opus was good as a reviewer though, but as an implementer it just felt lazy compared to 5.4 xhigh.

One feature that I haven’t seen discussed that much is how codex has auto-review on tool runs. No longer are you a slave to all or nothing confirmations or endless bugging, it’s such a bad pattern.

Even in a week of heavy duty work and personal use I still haven’t been able to exhaust the usage on the $200 plan.

I’ll probably change my mind when (not IF) OpenAI rug pull, but for spring ‘26, codex is definitely the better deal.

I left anthropic a while ago because of the similar shenanigans they had earlier. I went with opencode & zen.

I still have their subscription, but am using pi now, mainly because something happened that made my opencode sessions unusable (cannot continue them, just blanks out, I assume something in the sqlite is fucked), and I cannot be bothered to debug it.

For what I use the agents, the Chinese models are enough

I also cancelled my 20x and switched to Codex. At this point even the Codex CLI seems to perform better than Claude Code... And so far I'm on the OpenAI Pro plan and haven't even needed to upgrade to their $100/mo plan. I'm getting more value for almost 10x cheaper.

Same, I am from 5x plan and cancel and switched to codex as I want to use Pi.

I switched to Droid+Opus (with Claude Max) many months ago and it was my favorite combo.

Had to stop because they don't like us proxying requests anymore.

My experience is the opposite of this thread's consensus. Context: Full time SWE, working on large and messy codebase. Not working on crazy automations, working on fixing bugs, troubleshooting crashes, implementing features.

Anthropic models write much better code, they are easy to follow, reasonable and very close to what I would done if I had the time... OpenAI's on the other hand generate extremely complex solutions to the simplest problems.

I was so disappointed by non-Anthropic models, that for a couple of weeks I only used Anthropic models, but based on this thread, I'll go back and give it another try. It's good to go back and try things again every couple of weeks.

Of course, I was annoyed that they lobotomized 4.6, the difference was day and night, and Anthropic is certainly not a company I trust. In my opinion, it shows their willingness to rugpull, so I'm looking at other approaches. Since 4.7, things went back to normal, things you'd expect to work just work.

> I wonder how many other people recently did the same.

Some negative signal for better overall view on things: I'm still with Anthropic and will probably stay with them for the foreseeable future.

I think after DoD/DoW shenanigans (which in of itself felt like a reasonable take on the part of Anthrpic) they got a bunch of visibility and new users, so them hitting some scaling limits is pretty much inevitable - so some service disruption is inevitable. Couple this with the tokenizer changes and seeming decrease in model performance (adaptive thinking etc.), and lots of people will be rightfully pissed off, alongside increased downtime (doesn't matter that much for me, definitely does matter for anything time-sensitive).

At the same time, in practice I've only seen it do stupid things across 8 million tokens about 5 times (confusing user/assistant roles, not reading files that should be obvious for a given use case, and picking trivially wrong/stupid solutions when planning things), alongside another 4 times that tests/my ProjectLint tool caught that I would have missed. The error rate is still arguably lower than mine, though I work in a very well known and represented domain (webdev with a bunch of DevOps and also some ML stuff, and integration with various APIs etc.).

At the same time, the 85 EUR they gave to me for free has been enough to weather the instability in regards to pricing changes and peak usage. They've fixed most of the issues I had with Claude Code (notably performance), and the sub-agent support is great and it's way better than OpenCode in my experience. They also keep shipping new features that are pretty nice, like Dispatch and Routines and Design, those features also seem nice and not like something completely misdirected, so that's nice. The Opus 4.7 model quality with high reasoning is actually pretty nice as well and works better than most of the other models I've tried (OpenAI ones are good, I just prefer Claude phrasing/language/approaches/the overall vibe, not even sure what I'd call it exactly, all the stuff in addition to the technical capabilities).

At the same time, if they mess too much with the 100 USD tier, I bet I could go to OpenAI or try out the GLM 5.1 subscription without too many issues. For now they're replacing all the other providers for me. Oh also I find the subscription vs API token-based payment approach annoying, but I guess that's how they make their money.

Because the Harness is the Moat and key IP not the Models themselves that is the why! now for both OpenAI and Anthropic with all their money raised and the compute they acquire and have in the books of course no one can easily replicate, whom can afford all those datacenters and Nvidia GPUs interconnected is why OpenAI throws you a bone and gives you an Open Source SDK Harness but not the one they actually use for ChatGPT. But now both of them have to deliver and do all the bull-shet they said this models can do... truth is they cannot. So now the bubbles burst and we will see what happens. We all have to buy iPhones or MacBooks so that makes sense, we all use Chrome or Google Search, Instagram, TikTok.

All these models and agents are shortcuts for all of us to be lazy and play games and watch YouTube or Netflix because we use them to work-less, well the party will be over soon.

Is the tail end of the bubble, is just ridiculous things now. Models cannot made leap-improvements and now you have the enterprise to deal with and for enterprise is not about disruption so you can't break the wheel, you just need to make everyone work less.

But the bills comes thru, one has to pay AWS cause you need the servers, but pay AI agents that make mistake and everyone hopes they work just by typing and saying do x or y. And now they actually invented and engineering and deploy something called Adaptive Thinking and the models can allocate allocate zero reasoning tokens. Its game over, but it was over regardless, there is nothing special about models and they trained them now even with YouTube and soon to be Twitter(X), TikTok and bullshit. Now all those Nvidia GPUs interconnected via NVLink definitely powerful super computers, but the "software" let alone the "AI" is not there yet and OpenAI is worth close to 1 Trillions Dollars ... I mean come on!

Same thing happened to me in January. Never heard back from them after submitting the google form. A few weeks ago I went through the subscription flow again and the 'account disabled' message was no longer there. Didn't go through with the payment so it's possible I would have been blocked at that point but it looked like my account had been re-enabled. I think you just have to play the waiting game unfortunately.

Almost seems like business leaders have to balance different aspirations and make tradeoffs. Unbelieveable.

What's puzzling or schizophrenic about that? Those seem like two very natural factors that would be in tension with one another and have to be balanced.

Many people likely objected to the original restriction because it seemed as though Anthropic was trying to impede the development of competing tools.

If I'm paying for compute, why should it matter whether I use Anthropic's harness (e.g., Claude Code) or a 3rd-party harness?

Yes, exactly.

And then recommends to use an API key, which as far as I know was never restricted, it was trying to use the subscription that was prohibited/limited.

I'm confused by the comments being full of people swearing off Claude, feels like real HN bubble stuff.

(That's implied by the sitename to the right of the title)

ai garbage

I'm trying out codex for first time as well cause something up with Claude for sure, 4.7 has been super frustrating. For other models, highly recommend trying MiniMax 2.7, using it with Hermes is actually pretty good, and their token subscription plans include a lot of usage for $10.

Same here. I've been on the Claude Max 20x plan for a while. Now I'm really giving codex a try and looking at the cheaper models as well.

Enshittification 101, codex is undergoing the same thing on a 3 month lag.

Or Claw-like harnesses that we make ourselves? It takes honestly like 15 minutes to roll your own, so I did it thinking "well, hopefully it's not considered third party"

More people flocked to Codex and found out that it's not worse, and sometimes superior.

[flagged]