Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw
by firloop on 4/3/2026, 10:55:24 PM
Received the following email from Anthropic:<p>Hi,<p>Starting April 4 at 12pm PT / 8pm BST, you’ll no longer be able to use your Claude subscription limits for third-party harnesses including OpenClaw. You can still use them with your Claude account, but they will require extra usage, a pay-as-you-go option billed separately from your subscription.<p>Your subscription still covers all Claude products, including Claude Code and Claude Cowork. To keep using third-party harnesses with your Claude login, turn on extra usage for your account. This will be enforced April 4 starting with OpenClaw, but this policy applies to all third-party harnesses and will be rolled out to more shortly (read more).<p>To make the transition easier, we’re offering a one-time credit for extra usage equal to your monthly subscription price. Redeem your credit by April 17. We’re also introducing discounts when you pre-purchase bundles of extra usage (up to 30%).<p>We’ve been working to manage demand across the board, but these tools put an outsized strain on our systems. Capacity is a resource we manage carefully and we need to prioritize our customers using our core products. You will receive another email from us tomorrow where you’ll have the ability to refund your subscription if you prefer.
Comments
by: jesse_dot_id
There seem to be a ton of people who don't understand how subscription services work. Every single one of them oversells their capacity. The power users that use the services a lot are subsidized by those who don't use it as much, which tends to be the vast majority of the user base. OpenClaw is an autonomous power user. The growing adoption of this walking attack surface was either going to A) cause the cost of Claude to go up or B) get banned to protect the price of the service for actual users.
4/4/2026, 12:02:06 AM
by: jklm
The main reason I find myself using Opus is because it's a better communicator. (Yes, I know it's better in some areas like frontend vs. others but this is not significant enough for my purposes.)<p>So this change has actually forced a reckoning of sorts. Maybe the best option is to outsource the thinking to another model, and then send it back to Opus to package up.<p>Ironically this is how the non-agent works too to an extent.
4/4/2026, 1:59:47 AM
by: yalogin
Oh that is the crux of it, I was wondering why they are leading with the free credit in their email and what the catch is. I guess for someone that doesn’t use openclaw it doesn’t matter.
4/4/2026, 2:00:00 AM
by: g-mork
My answer to this is simply rolling back to the pro plan for interactive usage in the coming month, and forcefully cutting myself over to one of the alternative Chinese models to just get over the hump and normalise API pricing at a sensible rate with sensible semantics.<p>Dealing with Claude going into stupid mode 15 times a day, constant HTTP errors, etc. just isn't really worth it for all it does. I can't see myself justifying $200/mo. on any replacement tool either, the output just doesn't warrant it.<p>I think we all jumped on the AI mothership with our eyes closed and it's time to dial some nuance back into things. Most of the time I'm just using Opus as a bulk code autocomplete that really doesn't take much smarts comparatively speaking. But when I do lean on it for actual fiddly bug fixing or ideation, I'm regularly left disappointed and working by hand anyway. I'd prefer to set my expectations (and willingness to pay) a little lower just to get a consistent slightly dumb agent rather than an overpriced one that continually lets me down. I don't think that's a problem fixed by trying to swap in another heavily marketed cure-all like Gemini or Codex, it's solved by adjusting expectations.<p>In terms of pricing, $200 buys an absolute ton of GLM or Minimax, so much that I'd doubt my own usage is going to get anywhere close to $200 going by ccusage output. Minimax generating a single output stream at its max throughput 24/7 only comes to about $90/mo.
4/4/2026, 12:03:55 AM
by: firloop
This is slightly different from what OpenCode was banned from doing; they were a separate harness grabbing a user’s Claude Code session and pretending to be Claude Code.<p>OpenClaw was still using Claude Code as the harness (via claude -p)[0]. I understand why Anthropic is doing this (and they’ve made it clear that building products around claude -p is disallowed) but I fear Conductor will be next.<p>[0]: See “Option B: Claude CLI as the message provider” here <a href="https://docs.openclaw.ai/providers/anthropic#option-b-claude-cli-as-the-message-provider" rel="nofollow">https://docs.openclaw.ai/providers/anthropic#option-b-claude...</a>
4/3/2026, 11:47:38 PM
by: dnw
To give credit where it is due: Boris actually submitted a few PRs this week to OpenClaw to increase prompt cache hits. You can see them here: <a href="https://github.com/openclaw/openclaw/pullsq=is%3Apr+author%3Abcherny+is%3Aclosed" rel="nofollow">https://github.com/openclaw/openclaw/pullsq=is%3Apr+author%3...</a><p>I think the usage patterns of a lot of harnesses are pushing against their planned capacity. I would say they can certainly explain themselves a lot better.
4/4/2026, 1:55:40 AM
by: nfw2
I don't understand exactly what is being banned. I have a vibe coded context manager + chat thread UI that I use to manage multiple claude code cli sessions simultaneous. Is this allowed? If not how would this get identified vs other cli usage? How is this different than openclaw?
4/4/2026, 1:22:33 AM
by: 2001zhaozhao
There are going to be a lot of tools coming soon that are "agent-agnostic", i.e. can run on CLIs including Claude Code. I am personally experimenting with using a combo of MCP + custom UI layer to provide custom tools with bespoke UX and thus turn Claude Code (or any other CLI agent for that matter) into whatever I want. I wonder how they'll deal with that.<p>For a good existing example developed by a known company, check Cline Kanban: <a href="https://cline.bot/kanban" rel="nofollow">https://cline.bot/kanban</a><p>They don't have the MCP-bundling idea that I'm experimenting with, however.
4/3/2026, 11:27:42 PM
by: password4321
GitHub Copilot supports Anthropic models with any client but they have a monthly usage cap after which it is pay-per-prompt.<p><a href="https://news.ycombinator.com/item?id=46936105">https://news.ycombinator.com/item?id=46936105</a> Billing can be bypassed using a combo of subagents with an agent definition<p>> <i>"Even without hacks, Copilot is still a cheap way to use Claude models"</i><p>20260116 <a href="https://github.blog/changelog/2026-01-16-github-copilot-now-supports-opencode/" rel="nofollow">https://github.blog/changelog/2026-01-16-github-copilot-now-...</a><p><a href="https://github.com/features/copilot/plans" rel="nofollow">https://github.com/features/copilot/plans</a> $40/month for 1500 requests; $0.04/request after that<p><a href="https://docs.github.com/en/copilot/concepts/billing/copilot-requests#model-multipliers" rel="nofollow">https://docs.github.com/en/copilot/concepts/billing/copilot-...</a> Opus uses 3x requests
4/3/2026, 11:57:21 PM
by: noritaka88
This feels less like a pricing issue and more like a structural mismatch.<p>Subscriptions assume “human usage” — bursty, limited, mostly interactive. Agent systems are closer to autonomous infrastructure load running continuously.<p>OpenClaw is a good example of this. Once agents operate freely, they don’t behave like users — they behave like infrastructure.<p>That’s why this kind of restriction isn’t too surprising.<p>Long term, it seems likely this pushes things toward: - API-first usage - or local / open models<p>rather than agents sitting on top of subscription-based UIs.
4/4/2026, 12:44:58 AM
by: figmert
Can they actually realistically do this? Nothing technical can stop a client from masquerading as another, and with the right level of dedication, this wouldn't be very hard to do. And since they're mostly targeting power users, seems like they're barking up the wrong tree. Have I missed something?
4/4/2026, 1:41:13 AM
by: Multiplayer
Big Giant Million Dollar Question: Where does having Openclaw using Claude Code via ACP fall? It's using the Claude Code harness, not the model directly.<p>If you are not aware, ACP creates a persistent session for steering rather than using the models directly.
4/3/2026, 11:46:06 PM
by: datahack
Ok. Someone explain to me why they would f themselves this hard with software engineers when they are absolutely winning. This just seems like a bad move.<p>Is it infrastructure? Are they unable to control costs?<p>Everyone else is spending like money is water to try to get adoption. Claude has it and is dialing back utility so that its most passionate users will probably leave.<p>I don’t understand this move.
4/4/2026, 12:23:30 AM
by: alasano
"these tools put an outsized strain on our systems"<p>AKA when you fully use the capacity you paid for, that's too much!
4/3/2026, 11:01:55 PM
by: anizan
Using Xiaomi’s mimo pro on openrouter via hermes agent
4/4/2026, 1:56:20 AM
by: jeffpersonified
Less than 24hr notice on a Friday: either Anthropic is dropping S tier next week or they massively fumbled over the past 2 months in self owns and outages.
4/4/2026, 1:49:29 AM
by: djhope99
Personally I appreciate the clarity and technical enforcement vs banning accounts.<p>I switched OpenClaw to MiniMax 2.7. This combined with Claude over telegram does enough for me.<p>OpenClaw used to burn through all my Claude usage anyway.
4/4/2026, 12:36:44 AM
by: rohansood15
This email gives out the endgame - eventually, Claude subscription would be ~30% cheaper than API costs.<p>Our engineering team averages 1.5k per dev per month on credit costs, without busting Max limits today.
4/4/2026, 1:47:20 AM
by: zephyreon
Yah well I'll be downgrading my subscription to the $20/month plan for the light chats I have with AI outside of using custom harnesses and will figure out a better provider for the agentic tooling.
4/3/2026, 11:36:01 PM
by: Seattle3503
Am I still allowed to invoke cc in a bash script, or is that out too? Interactive sessions only.
4/3/2026, 11:51:05 PM
by: crawshaw
Based on this and recent product releases, Anthropic seems keen on building a closed ecosystem around their excellent model. That is their business choice, I suspect it will work well. But I cannot say I am particularly excited to have my entire development stack owned by one company.
4/4/2026, 1:26:06 AM
by: arewethereyeta
Marketing geniuses. They had 2 options here:<p>1. Make a better product/alternative to Openclaw and start eating their userbase. They hold the advantage because the ones "using their servers too much" are already their clients so they could reach out and keep trying to convert. Openclaw literally brought them customers at the door.<p>2. Do everyone royally and get them off their platform - with a strong feeling of dislike or hatred towards Anthropic.<p>Let's see how 2 goes for them. This is not the space to be treating your clients this way.
4/4/2026, 12:00:54 AM
by: gnabgib
Discussion (655 points, 1 month ago, 793 comments) <a href="https://news.ycombinator.com/item?id=47069299">https://news.ycombinator.com/item?id=47069299</a>
4/4/2026, 12:53:24 AM
by: loveparade
That's why I am using Codex. I slightly prefer Claude in terms of code quality, but it's close, but not being able to use my subscription with other CLIs and apps ruins Claude for me.
4/3/2026, 11:41:27 PM
by: evbogue
How does Anthropic detect that a person is using OpenClaw vs using Claude Code?<p>Forgive me if someone asked this already and I can't find it in the comments.
4/4/2026, 1:02:28 AM
by: SkyPuncher
Just give me a subscription tier where I’m not being blocked out every afternoon.<p>Im hitting rate limits within 1:45 during afternoons.<p>I can’t justify extra usage since it’s a variable cost, but I can justify a higher subscription tier.
4/3/2026, 11:21:25 PM
by: causal
Their whole business model seems built around selling you limits that you will never be able to utilize: limit you to tools that will never run long.<p>Claude Code seems designed to terminate quickly- mine always finds excuses to declare victory prematurely given a task that should take hours.
4/4/2026, 12:13:50 AM
by: _pdp_
The solution as usual is open source.<p>For example...<p>We recently moved a very expensive sonnet 4.6 agent to step-3.5-flash and it works surprising well. Obviously step-3.5-flash is nowhere near the raw performance of sonnet but step works perfectly fine for this case.<p>Another personal observation is that we are most likely going to see a lot of micro coding agent architectures everywhere. We have several such cases. GPT and Claude are not needed if you focus the agent to work on specific parts of the code. I wrote something about this here: <a href="https://chatbotkit.com/reflections/the-rise-of-micro-coding-assistants" rel="nofollow">https://chatbotkit.com/reflections/the-rise-of-micro-coding-...</a>
4/3/2026, 11:40:08 PM
by: christopher8827
This is why people are switching over to Codex
4/3/2026, 11:31:12 PM
by: 8note
> We’ve been working to manage demand across the board, but these tools put an outsized strain on our systems. Capacity is a resource we manage carefully and we need to prioritize our customers using our core products.<p>but couldn't i use this in off times only?
4/3/2026, 11:48:24 PM
by: hombre_fatal
If OpenClaw is just "claude -p", then how do they know when you're using OpenClaw?
4/4/2026, 12:46:49 AM
by: mogili1
What about when you use Claude agent SDK on your laptop?<p>Extra usage is very sneaky you don't get any notice that you are using extra usage and could end up with unnecessary costs in case you would have preferred to wait an hour or so.
4/3/2026, 11:42:57 PM
by: ramoz
Super confusing email. Not sure why I received. Am i to assume my account was flagged? I only use my subscription for Claude Code.<p>UPDATE:<p>reply on x Thariq @trq212 only flagged accounts, but you can still claim the credit
4/3/2026, 11:53:41 PM
by: Robdel12
I believe the capacity about 30%. They did just spend the entire last month of feature releases in Clade Code replacing "claw" features.<p>So, to me its a "we built it into our world use ours"<p>Edit: FWIW I am an avid hater of all claw things, they're security nightmare.
4/4/2026, 12:39:12 AM
by: skyberrys
Is this going to nuke all bring your own API 3rd party tools? I've been casually using fewshell <a href="https://github.com/few-sh/fewshell" rel="nofollow">https://github.com/few-sh/fewshell</a> with my Claude api key, I really hope it's going to keep working. I've just finally managed to turn myself into a reasonable devops team with it.
4/4/2026, 12:05:17 AM
by: buremba
I get why they block OpenClaw and it makes sense but I wonder if they can actually detect OpenClaw calling Claude Code CLI using something like acpx.<p>It's simply identical to how people use Claude Code locally.
4/4/2026, 12:47:25 AM
by: janalsncm
I got fed up with Claude code limits and have been using a combination of qwen3-coder, gemma4, and qwen3-vl locally. Gets me 90% of the way there and CC is still around for now if I need it.<p>Btw even at insane markups $200/mo means GPUs break even pretty fast.
4/4/2026, 12:29:25 AM
by: lrvick
They also forced OpenCode to remove support as well. Thankfully there is always self hosting and a shit ton of competitors that let you use whatever local software you want.
4/4/2026, 12:47:56 AM
by: Animats
Oh, it's a billing thing. Not fear that Claude coupled to something that can actually <i>do</i> things is dangerous.
4/4/2026, 1:01:27 AM
by: pikdum
Does this mean I can't use `claude -p` in bash scripts now?
4/4/2026, 12:10:14 AM
by: eagleinparadise
Anthropic measures your usage based on token consumption<p>We are paying for a certain amount of token consumption<p>Why then, is this an outsized strain on your system Anthropic?<p>It's like buying gasoline from Shell, and then Shell's terms of services forcing you to use that gas in a Hummer that does 5 MPG, while everyone else wants to drive any other vehicle.
4/3/2026, 11:03:39 PM
by: raincole
So is Codex the only SOTA that welcomes third-party harness?
4/4/2026, 12:02:13 AM
by: chrisjj
And so it begins...
4/3/2026, 11:05:21 PM
by: jonwinstanley
What are people doing with OpenClaw? Are there any places that try to log best uses and new ideas?
4/4/2026, 12:19:07 AM
by: Sinidir
Does anyone know. How would that relate to simply wrapping claude code as a subprocess?
4/4/2026, 12:24:38 AM
by: zem
I wonder if this also applies to tools that interact with the claude code tui through tmux's capabilities.
4/3/2026, 11:58:46 PM
by: HellsMaddy
I received it too. I wonder if they sent this to all pro/max subscribers or only those who they’ve flagged as having used a third party harness.
4/3/2026, 11:13:00 PM
by: zer00eyz
"We dont crash ever" -- the social network.<p>If you haven't been paying attention anthropic burned a lot of their developer good will in the last 2 weeks, with some combination of bugs and rate limits.<p>But the writing is on the wall about how bad things are behind the scenes. The circa 2002 sentiment filter regex in their own tool should have been a major clue about where things stand.<p>The question every one should be asking at this point is this: is there an economic model that makes AI viable. The "bitter lesson" here is in AI's history: expert systems were amazing, but they could not be maintained at cost.<p>The next race is the scaling problem, and google with their memory savings paper has given a strong signal what the next 2 years of research are going to be focused on: scaling.
4/4/2026, 1:34:43 AM
by: cute_boi
Idk why people are complaining when they know subscription are currently heavily subsidized. If they don't like they can always choose alternative service.
4/4/2026, 1:31:37 AM
by: seamossfet
Honestly, this is a good thing. OpenClaw as a concept was rather silly to run such a heavy model for. If you want something like OpenClaw to work you really need to figure out how to do it with an economical model.
4/4/2026, 12:50:34 AM
by: benn67
Haha, I almost expected this.<p>Say goodbye to my 600$/ month Anthropic.
4/4/2026, 12:00:59 AM
by: randall
Does anyone have a link to the "read more"?
4/4/2026, 12:05:15 AM
by: beanjuiceII
i think i'll no longer be giving my money to anthropic
4/4/2026, 12:53:26 AM
by: nekusar
Wellll, that rug aint gonna pull itself, now is it?<p>Ive been calling for local LLM as owning the means of production. I aint wrong.
4/4/2026, 1:15:40 AM
by: j45
Inefficient token use will have to tighten up.
4/4/2026, 1:15:08 AM
by: stavros
Looks like I'm going to be switching to OpenAI. I know the whole "well those are the terms" Stockholm syndrome argument, but no, those weren't the terms when I signed up. If one of the parties decided to unilaterally change terms in any other everyday situation, nobody would think it was acceptable, but we've become so resigned to corporations having enough money to make the law suit them that we think it's moral behavior.<p>No, Anthropic, just because you added a clause that says "we can change these terms whenever" doesn't make it right. I'm paying you a set amount of money a month for a set amount of tokens (that's what limits are), and I should be able to use these tokens however I want.<p>Luckily, there are alternatives.
4/3/2026, 11:44:00 PM
by: tinyhouse
I really started to like Pi. That's unfortunate that I won't be able to use it with Opus (way too expensive without a subscription). I'm optimistic that open source coding models will be able to keep up. AI is too important, we're shooting ourselves in the foot if we don't adopt open source tools and models. The more adoption the better it will become.
4/4/2026, 1:08:47 AM
by: supliminal
Since the OpenClaw creator is posting on HN I’d like to hear some commentary from him directly.
4/3/2026, 11:54:10 PM
by:
4/3/2026, 11:55:07 PM
by: mccoyb
Why not use datacenter of geniuses to increase capacity? Grug confused.
4/4/2026, 12:31:59 AM
by: cat-turner
Doesn't this unfairly impact startups? Why not instead allow issuance of API keys with usage caps? It seems like a money grab.
4/3/2026, 11:20:38 PM
by: saltyoldman
Is anyone even getting anything out of a $20/mo sub for Anthropic?<p>I'm doing a side-by-side with GPT-5.4 for $20/mo and Sonnet for $20/mo and I can tell you that all my 5 hour tokens are eaten in 30 minutes with Claude. I still haven't used my tokens for OpenAI.<p>Code quality seems fine on both. Building an app in Go
4/3/2026, 11:41:59 PM
by: Traubenfuchs
You can cancel your subscription, there are like 5 competitors you can pick instead and anthropic offers an API plan where you can find out how many tokens circus tools like claws really consume compared to coding tasks.
4/3/2026, 11:39:20 PM
by: kjuulh
Anthropic should calm down, I get that they're trying to either build a moat, or simply curb what is essentially subsidized tokens. It is technically true that when you've got a claude code subscription you pay for the product with its terms, and those terms doesn't include you grabbing the token and using it for another application. They're also trying to build a competitor to openclaw so it makes sense they're trying to crush it. But it feels like such a feeble moat, that it looks silly. Claude Code is nice, but it is not <i>that</i> nice.
4/3/2026, 11:37:02 PM
by: SevenTGK
mysterious anthropic win???
4/4/2026, 1:16:33 AM
by: yieldcrv
I like how the best way to protest this is by doing what everyone should have been doing to begin with: running a great open source model on rented hardware
4/4/2026, 12:11:20 AM
by: winterrx
So now what happens to startups and ADE's orientated around Claude like Conductor.. no more Claude for them I guess back to Codex!
4/3/2026, 11:33:10 PM
by: rvz
> To make the transition easier, we’re offering a one-time credit for extra usage equal to your monthly subscription price. Redeem your credit by April 17. We’re also introducing discounts when you pre-purchase bundles of extra usage (up to 30%).<p>The Anthropic casino wants you to continue gambling tokens at their casino only on their machines (Claude Code) only by giving more promotional offers such as free spins, $20 bets and more free tokens at the roulette wheels and slot machines.<p>But you cannot repurpose your subscription on other slot machines that are not owned by Anthropic and if you want it badly, they charge you more for those credits.<p>The house (Anthropic) always wins.
4/3/2026, 11:01:10 PM
by:
4/3/2026, 11:42:14 PM
by: jasonlotito
Yes, this was made clear a while back and should not be a surprise. (Honestly, I had to double-check the date/time to see if this was actually posted today.<p>You can use your Claude Code subscription with third-party tools, but you have to use the Claude Code harness. Or, you use the API. OpenClaw could use the Claude Code harness, but they don't.
4/3/2026, 11:26:25 PM
by: Vivolab
[dead]
4/3/2026, 11:57:40 PM
by: heavyset_go
[dead]
4/3/2026, 11:53:44 PM
by: devkarev
[dead]
4/3/2026, 11:43:38 PM
by: charcircuit
You never have been able to. It's against ToS.
4/3/2026, 11:30:51 PM
by: entropoem
Anthropic and OpenAI are the clearest examples of why, in an organization of specialists, the experts themselves should not be the CEO or the final decision-maker once the company’s challenges extend beyond just the product.<p>Just look at how Sam Altman has led OpenAI step by step to dominate—and choke out—Anthropic, a company founded by the group of engineers who were once part of the turmoil at OpenAI.<p>Anthorpic's product thinking is terrible even though it is technically very good.
4/4/2026, 12:23:25 AM