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

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.

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.

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.

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.

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.

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.

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.

[0]: See “Option B: Claude CLI as the message provider” here https://docs.openclaw.ai/providers/anthropic#option-b-claude...

> for third-party harnesses

What's the exact definition of third-party harnesses? They have an Agent SDK in Claude Code that can be used. Are they trying to say that only Anthropic products can use pro/max plans?

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.

For a good existing example developed by a known company, check Cline Kanban: https://cline.bot/kanban

They don't have the MCP-bundling idea that I'm experimenting with, however.

GitHub Copilot supports Anthropic models with any client but they have a monthly usage cap after which it is pay-per-prompt.

https://news.ycombinator.com/item?id=46936105 Billing can be bypassed using a combo of subagents with an agent definition

> "Even without hacks, Copilot is still a cheap way to use Claude models"

20260116 https://github.blog/changelog/2026-01-16-github-copilot-now-...

https://github.com/features/copilot/plans $40/month for 1500 requests; $0.04/request after that

https://docs.github.com/en/copilot/concepts/billing/copilot-... Opus uses 3x requests

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?

This feels less like a pricing issue and more like a structural mismatch.

Subscriptions assume “human usage” — bursty, limited, mostly interactive. Agent systems are closer to autonomous infrastructure load running continuously.

OpenClaw is a good example of this. Once agents operate freely, they don’t behave like users — they behave like infrastructure.

That’s why this kind of restriction isn’t too surprising.

Long term, it seems likely this pushes things toward: - API-first usage - or local / open models

rather than agents sitting on top of subscription-based UIs.

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?

"these tools put an outsized strain on our systems"

AKA when you fully use the capacity you paid for, that's too much!

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.

If you are not aware, ACP creates a persistent session for steering rather than using the models directly.

$200 is a lot of money per month. I just bought this much in OAI API credits and I expect them to last me until August or so.

If you started plugging tools into GPT5.4 you may soon discover that you don't need anything beyond a single conversation loop with some light nesting. A lot of the openclaw approach seems to be about error handling, retry, resilience and perspectives on LLM tool use from 4+ months ago. All of these ideas are nice, but it's a hell of a lot easier to just be right the first time if all you need is a source file updated or an email written. You can get done in 100 tokens what others can't seem to get done in millions of tokens. As we become more efficient, the economic urgency around token smuggling begins to dissipate.

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.

Is it infrastructure? Are they unable to control costs?

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.

I don’t understand this move.

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: https://github.com/openclaw/openclaw/pullsq=is%3Apr+author%3...

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.

Personally I appreciate the clarity and technical enforcement vs banning accounts.

I switched OpenClaw to MiniMax 2.7. This combined with Claude over telegram does enough for me.

OpenClaw used to burn through all my Claude usage anyway.

I always thought this was the case since they declared war against Opencode and its users.

The lines drawn by their consumer vs commercial TOS was clear and I never subscribed because of it.

Claude usage limits are insane. I love their models but had to cancel my personal plan because I would burn through my weekly limits in 2 days. I use them for work but I spend like $30-50 __per day__. Not something I'd pay for myself.

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.

I guess they're only sending this to people who use tools like OpenClaw. I don't, and haven't gotten an email. And I guess also won't get the free extra usage credit offer. Ah well.

This is the classic car wash subscription scheme. You sign up a bunch of people for $40 a month to wash their car. Most people only go to wash their car once or twice a month (or even less), which offsets those few folks that do it three times a week or more.

The problem Anthropic is running into is that OpenClaw made it easy for everyone to become one of those folks that washes their car three times a week or more.

I’m sure they were losing money on subscriptions in general but now they are really losing money. Shutting off OpenClaw specifically probably helps stem some of the bleeding.

Am I still allowed to invoke cc in a bash script, or is that out too? Interactive sessions only.

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.)

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.

Ironically this is how the non-agent works too to an extent.

I don’t understand why they’re catching any flak here lol if you want to use the frontier model more then pay for it?

Graceful handling from Anthropic

Marketing geniuses. They had 2 options here:

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.

2. Do everyone royally and get them off their platform - with a strong feeling of dislike or hatred towards Anthropic.

Let's see how 2 goes for them. This is not the space to be treating your clients this way.

The solution as usual is open source.

For example...

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.

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: https://chatbotkit.com/reflections/the-rise-of-micro-coding-...

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.

Just give me a subscription tier where I’m not being blocked out every afternoon.

Im hitting rate limits within 1:45 during afternoons.

I can’t justify extra usage since it’s a variable cost, but I can justify a higher subscription tier.

Claude is a great model. But anthropic’s user hostile practices have forced me to terminate my sub with them. Right now I am all in on GitHub copilot and that’s primarily how I get my opus tokens.

Given the sheer amount of logging that happens in Claude Code based on the leak, I'm not surprised. This isn't about load, this is merely about cost.

Claude Code is subsidized because of data collection.

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.

Claude Code seems designed to terminate quickly- mine always finds excuses to declare victory prematurely given a task that should take hours.

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.

Discussion (655 points, 1 month ago, 793 comments) https://news.ycombinator.com/item?id=47069299

This is why people are switching over to Codex

How does Anthropic detect that a person is using OpenClaw vs using Claude Code?

Forgive me if someone asked this already and I can't find it in the comments.

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.

This email gives out the endgame - eventually, Claude subscription would be ~30% cheaper than API costs.

Our engineering team averages 1.5k per dev per month on credit costs, without busting Max limits today.

> 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.

but couldn't i use this in off times only?

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.

What about when you use Claude agent SDK on your laptop?

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.

Super confusing email. Not sure why I received. Am i to assume my account was flagged? I only use my subscription for Claude Code.

UPDATE:

reply on x Thariq @trq212 only flagged accounts, but you can still claim the credit

Is this going to nuke all bring your own API 3rd party tools? I've been casually using fewshell https://github.com/few-sh/fewshell 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.

If OpenClaw is just "claude -p", then how do they know when you're using OpenClaw?

I believe the capacity about 30%. They did just spend the entire last month of feature releases in Clade Code replacing "claw" features.

So, to me its a "we built it into our world use ours"

Edit: FWIW I am an avid hater of all claw things, they're security nightmare.

This is exactly why building daily workflows on top of proprietary API wrappers is a ticking time bomb. The moment your tooling becomes an outsized strain, they just flip the switch on you.

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.

Btw even at insane markups $200/mo means GPUs break even pretty fast.

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.

It's simply identical to how people use Claude Code locally.

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.

Using Xiaomi’s mimo pro on openrouter via hermes agent

Anthropic measures your usage based on token consumption

We are paying for a certain amount of token consumption

Why then, is this an outsized strain on your system Anthropic?

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.

Oh, it's a billing thing. Not fear that Claude coupled to something that can actually do things is dangerous.