Get the top HN stories in your inbox every day.
dfabulich
danmaz74
> More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.)
"Should have" for what reason? I would be happy if they open sourced Claude Code, but the reality is that Claude Code is what makes Anthropic so relevant in the programming more, much more than the Claude models themselves. Asking them to give it away for free to their competitors seems a bit much.
mrbungie
Well OpenCode already exists and you can connect it to multiple providers, so you could just say that the agentic CLI harness business model as a service/billable feature is no more. In hindsight I would say it never made sense in the first place.
xpe
The above does not prove that it is irrational for Anthropic to keep the Claude Code source code closed. There are many reasons I can see (and probably some I can’t) for why closed source is advantageous for A\. One such (mentioned in various places) is the value-add of certain kinds of analytics and or telemetry.
Aside: it is pretty easy to let our appreciation* of OSS turn into a kind of confirmation bias about its value to other people/orgs.
* I can understand why people promote OSS from various POVs: ethics, security, end user control, ecosystem innovation, sheer generosity, promotion of goodwill, expressions of creativity, helping others, the love of building things, and much more. I value all of these things. But I’m wary of reasoning and philosophies that offer merely binary judgments, especially ones that try to claim what is best for another party. That's really hard to know so we do well to be humble about our claims.**
**: Finally, being humble about what one knows does not mean being "timid" with your logic or reasoning. Just be sure to state it as clearly as you can by mentioning your premises and values.
sbarre
Branding and customer relationships matter as much or more than the "billable service" part of Claude Code.
It's not unheard of for companies that have strong customer mindshare to find themselves intermediated by competitors or other products to the point that they just became part of the infrastructure and eventually lose that mindshare.
I doubt Anthropic wants to become a swappable backend for the actual thing that developers reach for to do their work (the CLI tool).
Don't get me wrong, I think developers should 100% have the choice of tooling they want to use.
But from a business standpoint I think maintaining that direct or first-party connection to the developer is what Anthropic are trying to protect here.
danmaz74
When I compared OpenCode and Claude Code head to head a couple of months ago, Claude Code worked much better for me. I don't know if they closed the gap in the meantime, but for sure Claude Code has improved since then.
zachncst
Disagree, this is like terraform for Hashicorp. Give the cow away for free and no one will want to buy the milk. Claude code is a golden cow they should not give away.
rovr138
Except that the cost is better with their harness and looks like people don’t want to fork 5x.
Adoption is how one wins. Look at all the crappy solutions out there that are still around.
tom_m
Nah, I think Opus is fantastic but not Claude Code. Their models are way better.
udntwanthesmok
I have the rehydrated version, should I publish it
idonotknowwhy
Rehydrated version of what? And what does that mean?
altmanaltman
> the reality is that Claude Code is what makes Anthropic so relevant in the programming more, much more than the Claude models themselves
but Claude Code cannot run without Claude models? What do you mean?
boh
Relative to their competitors who also have comparable models, Anthropic's design choices in effectively managing context with a very well thought out and coherent design, makes them stand out.
Daviey
Yes, it can.
reactordev
Claude code is nothing more than a loop to Opus.
sirtaj
I use Q/aka kiro-cli at work with opus and it's clearly inferior to CC within the first 30s or so of usage. So no, not quite
giancarlostoro
Yeah, I've heard of people swapping out the model that Claude Code calls and apparently its not THAT much of a difference. What I'd love to see from Anthropic instead is, give me smaller LLM models, I don't even care if they're "open source" or not, just pull down a model that takes maybe 4 or 6 GB of VRAM into my local box, and use those for your coding agents, you can direct it and guide it with Opus anyway, so why not cut down on costs for everyone (consumer and Anthropic themselves!) by just letting users who can run some of the compute locally. I've got about 16GB of VRAM I can juice out of my Macbook Pro, I'm okay running a few smaller models locally with the guiding hand of Opus or Sonnet for less compute on the API front.
motbus3
Anthropic might have good models, but they are the worse. I mentioned in another thread how they do whatever they can to bypass bot detection protection to scrap content.
labcomputer
So, like, why don’t people just use the better-than-Claude OpenCode CLI with these other just-as-good-as-Claude models?
tacoooooooo
not sure there are any models yet that you can get the quality out you need to do this and run on your mbp
stingraycharles
What part of a TOS is ridiculous? Claude Code is obviously a loss leader to them, but developer momentum / market share is important to them and they consider it worth it.
What part of “OpenCode broke the TOS of something well defined” makes you think it’s all Anthropic’s fault?
landl0rd
It's probably not a "loss-leader" so much as "somewhat lower margin". Their bizdev guys are doubtless happy to make a switch between lower-margin, higher-multiple recurring revenue versus higher-margin, lower-multiple pay-as-you-go API billing. Corporate customers with contracts doubtless aren't paying like that for the API either. This is not uncommon.
Ajedi32
When you have a "loss leader" whose sole purpose is to build up market share (e.g. put competitors out of business) that's called predatory pricing.
anamexis
Every loss leader's purpose is to build up market share.
ForHackernews
Do you think Anthropic followed all the ToS of every website on the internet when scraping them for training data?
rovr138
You justify a wrong thing by attacking something else? Is that the only argument?
mnky9800n
My guess is that ultimately the use of Claude code will provide the training data to make most of what you do now in Claude code irrelevant.
FuckButtons
My guess is that ultimately the use of Claude code will provide the training data to make most of what you do irrelevant.
FTFY.
epolanski
I keep hearing those claims that's they lose money on it, but I have more and more doubts about this being true.
GPU compute cost has falled down in the last two years a lot.
fc417fc802
Poor behavior is still poor behavior even if the relevant ToS aligns with it.
anamexis
Why is it poor behavior though?
casparvitch
I guess one issue is that you pay $200/month whether you use it or not. Potentially this could be better for Anthropic. What was not necessarily foreseeable (ok maybe it was) back when that started was that users have invented all kinds of ways to supervise their agents to be as efficient as possible. If they control the client, you can't do that.
vidarh
I can easily get Claude Code to run for 8-10 hours unsupervised without stopping with sub-agents entirely within Claude Code.
I think it is more likely that if you stick with Claude Code, then you are more likely to stick with Opus/Sonnet, whereas if you use a third party CLI you might be more likely to mix and match or switch away entirely. It's in their interest to get you invested in their tooling.
KronisLV
> if you use a third party CLI you might be more likely to mix and match or switch away entirely.
I really like doing this, be it with OpenCode or Copilot or Cline/RooCode/KiloCode: I do have a Cerebras Code subscription (50 USD a month for a lot of tokens but only an okayish model) whereas the rest I use by paying per-token.
Monthly spend ends up being somewhere between 100-150 USD total, obviously depending on what I do and the proportion of simple vs complex tasks.
If Sonnet isn’t great for a given task, I can go for GPT-5 or Gemini 3.
mlrtime
On the flip side I started using Claude with other LLMs (openai) because my Pro sub gets maxed out quickly and I want a cheaper alternative to finish a project.
I just use claude code proxy or litellm and set the ANTHROPIC_BASE_URL to my proxy and chose another LLM.
j45
Multi model is the way of the future though as much as I like and prefer Anthropic.
dabernathy89
I've yet to come up with a workflow where I would want Claude to do this much work... unless I had an extremely detailed spec defined for it. How do you ensure it doesn't go off the rails?
labcomputer
> I guess one issue is that you pay $200/month whether you use it or not.
I can easily churn through $100 in an 8 hour work day with API billing. $200/month seems like an incredibly good deal, even if they apply some throttling.
isolli
Why is supervising one's agents to be as efficient as possible a problem for Anthropic?
dpark
When people say efficient here, they mean cost efficient, extracting as much work per dollar from Anthropic as possible. This is the opposite of Anthropic’s view of efficiency, which would be providing the minimal amount of service for the most amount of money.
casparvitch
More inference = more cost (to Anthropic)
moltar
To extend your all you can eat analogy. It’s similar to how all you can eat restaurants allow you to eat all you can within the bounds of the restaurant, but you aren’t allowed to bring the food out with you.
hshdhdhj4444
Another analogy is that it’s a takeout but anthropic is insisting you only eat at home with the plastic utensils they’ve provided rather than the nice metal utensils you have at home.
Another analogy is that it’s a restaurant that offers delivery and they’re insisting you use their own in house delivery service instead of placing a pickup order and asking your friendly neighbor to pick it up for you on their way back from the office.
savanaly
The all you can eat buffet analogy makes way more sense to me, because it speaks to the aspect of it where the customer can take a lot of something without restriction. That's the critical thing with the Anthropic subscription, and the takeout analogy or delivery service don't contain any element of it.
jbstack
It's not really a fair analogy. Restaurants don't want you taking food away because they want to limit the amount you eat to a single meal, knowing that you'll stop when you get full. If you take food out you can eat more by waiting until the next meal when you're hungry again.
You don't "get full" and "get hungry again" by switching UIs. You can consume the same amount whether you switch or you don't switch.
dpark
> You don't "get full" and "get hungry again" by switching UIs. You can consume the same amount whether you switch or you don't switch.
This is actually a compelling argument for Claude Code getting the discount but not extending it to other cases. Claude Code, being subsidized by the company, is incentivized to minimize token usage. Third parties that piggyback on the same flat rate subscription, are not. i.e. Claude code wants you to eat less.
Of course, I don’t believe at all that this is why Anthropic has blocked this use case. But it is a reasonable argument.
samrolken
Claude Code does a lot of work in optimizing context usage, how much output is included by tools and how that's done, and when to compact. This very well may make the cost of providing the subscription lower to Anthropic when Claude Code is used. It's well within the realm of possibility if not likelihood that other tools don't have the same incentive to optimize the buffet usage.
Not sure where that goes in the analogies here but maybe something about smaller plates.
mrgoldenbrown
The UI absolutely could influence the backend usage.
Think about a web browser that respects cache lifetimes vs one that downloads everything everytime. As an ISP I'd be more likely to offer you unlimited bandwidth if I knew you were using a caching browser.
Likewise Claude code can optimize how it uses tokens and potentially provide the same benefit with less usage.
undefined
dfabulich
Not really. At a buffet restaurant, if you could take the food out with you, you'd takeaway more food than you can eat at one sitting. OpenCode users and Claud Code™ CLI users use tokens at approximately the same rate.
This is more like an all-you-can-eat restaurant requiring you to eat with their flimsy plastic forks, forbidding you to bring your own utensils.
samrolken
Claude Code does a lot regarding optimizing context usage, tool output, sub-agent interactions, context compaction, and stuff like that. I don't imagine OpenCode has the same financial incentive to decrease the token cost Anthropic takes on under the subscriptions.
snackdex
yes with the whole goal to make the utensils better
whatsupdog
Why is this being downvoted? This is the perfect analogy.
darepublic
anthropic should not be criticizing the gluttony of others whilst licking its fingers surrounded by buckets full of fried chicken
baby
Aren't you happy that you can use claude code unlimited for only 200/month? I don't really get your point tbh
Aurornis
I’d bet almost everyone who opts to buy the $200 plan is happy with the deal they’re getting relative to API pricing.
I think some people get triggered by the inconsistency in pricing or the idea of having a fixed cost for somewhat vague usage limits.
In practice it’s a great deal for anyone using the model at that level.
piokoch
It is not unlimited, being not careful with your context management, you hit the limits quickly.
abhijat
Isn't the context window the same for all plans, 200k? You would hit usage limits?
mhast
Even at the Max plan it's not unlimited. IIRC they say the limit is something like 20x the $20 plan.
With "normal use" you're unlikely to hit the limit though, unless you only use the Opus model and do things in parallell.
gejose
> Everything about this is ridiculous, and it's all Anthropic's fault. Anthropic shouldn't have an all-you-can-eat plan for $200 when their pay-as-you-go plan would cost more than $1,000+ for comparable usage
Hard disagree. Companies can and do subsidize products to gather market share. It's just a loss leader [1]. The big money for them is likely satisfied software engineers pushing their employers to pay for more Anthropic products in an enterprise setting.
3abiton
> Why is Anthropic offering such favorable pricing to subscribers? I dunno. But they really want you to use the Claude Code™ CLI with that subscription, not the open-source OpenCode CLI.
Because they are harvesting all the data they can harvest through CLI to train further models. API access in contrast provides much more limited data
dfabulich
As far as I know, OpenCode sends (has to send) the same data to Anthropic as Claude Code™ CLI (especially if they're going to successfully imitate CC™ in order to access cheap subscription pricing).
NitpickLawyer
There are additional signals that a client can send as telemetry that they lose if you use a 3rd party app. Things like accepted vs rejected sessions and so on.
ehsanu1
But I doubt you can opt in to them training on that data coming in via OpenCode.
eli
Claude Code only trains on data if you opt in
NitpickLawyer
They've recently switched to opt-out instead. And even then, if you read the legalese they say "train frontier models". That would (probably) allow them to train a reward model or otherwise test/validate on your data / signals without breaking the agreement. There's a lot of signal in how you use something (e.g. accepted vs. rejected rate) that they can use without strictly including it in the dataset for training their LLMs.
adastra22
They switched to opt out, with some extra dark patterns to convert people who already opted out into opting in.
CSSer
I used to be less cynical, but I could see them not honoring that, legal or not. The real answer, regardless of how you feel about that conversation, is that Claude Code, not any model, is the product.
whalesalad
Claude code cli and api vs subscription are tangential. You can use Claude code with an api token.
onel
That is not true, though. You have to opt in for them to train on your data
OGEnthusiast
> More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.)
Isn't the whole thesis behind LLM coding that you can easily clone the CLI using an LLM? Otherwise what are you paying $200/mo for?
underdeserver
In some sense that's what OpenCode is, and Anthropic's not having that.
OGEnthusiast
This whole thing just seems like a "I never thought the leopards would eat my face" by all the people who have been shilling LLMs non-stop.
dboon
This is an unusual L for Anthropic. The unfortunate truth is that the engineering in opencode is so far ahead of Claude Code. Obviously, CC is a great tool, but that's more about the magic of the model than the engineering of the CLI.
The opencode team[^1][^2] built an entire custom TUI backend that supports a good subset of HTML/CSS and the TypeScript ecosystem (i.e. not tied to Opencode, a generic TUI renderer). Then, they built the product as a client/server, so you can use the agent part of it for whatever you want, separate from the TUI. And THEN, since they implemented the TUI as a generic client, they could also build a web view and desktop view over the same server.
It also doesn't flicker at 30 FPS whenever it spawns a subagent.
That's just the tip of the iceberg. There are so many QoL features in opencode that put CC to shame. Again, CC is a magical tool, but the actual nuts and bolts engineering of it is pretty damning for "LLMs will write all of our code soon". I'm sorry, but I'm a decent-systems-programmer-but-terminal-moron and I cranked out a raymarched 3D renderer in the terminal for a Claude Wrapped[^] in a weekend that...doesn't flicker. I don't mean that in a look-at-me way. I mean that in a "a mid-tier systems programmer isn't making these mistakes" kind of way.
Anyway, this is embarrassing for Anthropic. I get that opencode shouldn't have been authenticating this way. I'm not saying what they are doing is a rug pull, or immoral. But there's a reason people use this tool instead of your first party one. Maybe let those world class systems designers who created the runtime that powers opencode get their hands on your TUI before nicking something that is an objectively better product.
[^1] https://github.com/anomalyco/opentui
[^2] From my loose following of the development, not a monolith, and the person mostly responsible for the TUI framework is https://x.com/kmdrfx
IgorPartola
My favorite is running CC in a screen session. There if I type out a prompt and then just start holding down the backspace key to delete a bunch of characters, at some point they key press refresh rate outruns CC’s brains and it just starts acting like it moved the cursor but didn’t delete anything. It is an embarrassing bug, but one that I suspect wouldn’t be found in automated testing.
visarga
Talking about embarrassing bugs, Claude chat (both web and iOS apps) lately tend to lose the user message when there is a network error. This happens every day to me lately. It is frustrating to retype a message from memory, first time you are "in the flow" second time it feels like unjust punishment.
With all the Claude Code in the world how come they don't write good enough tests to catch UI bugs? I have come to the point where I preemptively copy the message in clipboard to prevent retyping.
prodigycorp
This is an old bug. I cant believe they haven't fixed it yet. My compliments for the Claude frontend start and end at artifacts.
BoorishBears
Ctrl Z usually recovers the missing text, even across page refreshes
dotancohen
If you want to work around this bug, Claude Code supports all the readline shortcuts such as Ctrl-W and Ctrl-U.
BoiledCabbage
> Anyway, this is embarrassing for Anthropic.
Why? A few times in this thread I hear people saying "they shouldn't have done this" or something similar but not given any reason why.
Listing features you like of another product isn't a reason they shouldn't have done it. It's absolutely not embarrassing, and if anything it's embarrassing they didn't catch and do it sooner.
gpm
Because the value proposition that has people pay Anthropic is that it's the best LLM-coding tool around. When you're competing on "we can ban you from using the model we use with the same rate limits we use" everyone knows you have failed to do so.
They might or might not currently have the best coding LLM - but they're admitting that whatever moat they thought they were building with claude code is worthless. The best LLM meanwhile seems to change every few months.
They're clearly within their rights to do this, but it's also clearly embarrassing and calls into question the future of their business.
casparvitch
Is it that it's the best coding tool or the best model? I still get the best (most accurate) results out of anthropic models (but not out of CC).
matt-p
I think in fairness to anthropic they are winning in llms right? Since 3.7 they have been better than any other lab.
OGEnthusiast
> Because the value proposition that has people pay Anthropic is that it's the best LLM-coding tool around.
Why not just use a local LLM instead? That way you don't have to pay anyone.
dboon
It is embarrassing to restrict an open source tool that is (IMO) a strictly and very superior piece of software from using your model. It is not immoral, like I said, because it's clearly against the ToC; but it's not like OC is stealing anything from Anthropic by existing. It's the same subscription, same usage.
Obviously, I have no idea what's going on internally. But it appears to be an issue of vanity rather than financials or theft. I don't think Anthropic is suffering harm from OC's "login" method; the correct response is to figure out why this other tool is better than yours and create better software. Shutting down the other tool, if that's what's in fact happening, is what is embarrassing.
BoiledCabbage
> It is embarrassing to restrict an open source tool that is (IMO) a strictly and very superior piece of software from using your model.
> Shutting down the other tool, if that's what's in fact happening, is what is embarrassing.
To rephrase it different as I feel my question didn't land. It's clear to me that you think it's embarrassing. And it's clear what you think is embarrassing. I'm trying to understand why you think it's embarrassing. I don't think it is at all.
Your statements above are simply saying "X is embarrassing because it's embarrassing". Yes I hear that you think it's embarrassing but I don't think it is at all. Do you have a reason you can give why you think it's embarrassing? I think it's very wise and pretty standard to not subsidize people who aren't using your tool.
I'm willing to consider arguments differently, but I'm not hearing one. Other than "it just is because it is".
ehnto
As a user it is because I can no longer use the subscription with the greater tooling ecosystem.
As for Anthropic, they might not want to do this as they may lose users who decide to use another provider, since without the cost benefit of the subscription it doesn't make sense to stay with them and also be locked into their tooling.
what
The subscription is for their products? If you want to use their models in another product you can pay for the API usage.
undefined
rockatanescu
The Claude plans allow you to send a number of messages to Anthropic models in a specific interval without incurring any extra costs. From Anthropic's "About Claude's Max Plan Usage" page:
> The number of messages you can send per session will vary based on the length of your messages, including the size of files you attach, the length of current conversation, and the model or feature you use. Your session-based usage limit will reset every five hours. If your conversations are relatively short and use a less compute-intensive model, with the Max plan at 5x more usage, you can expect to send at least 225 messages every five hours, and with the Max plan at 20x more usage, at least 900 messages every five hours, often more depending on message length, conversation length, and Claude's current capacity.
So it's not a "Claude Code" subscription, it's a "Claude" subscription.
The only piece of information that might suggest that there are any restrictions to using your subscription to access the models is the part of the Pro plan description that says "Access Claude Code on the web and in your terminal" and the Max plan description that says "Everything in Pro".
wiseowise
It is embarrassing, because it means they’re afraid of competition. If CC was so great, at least a fraction of they sell it, they wouldn’t need to do it.
anhner
"Leave the multibillion dollar company alone!"
llmslave2
[flagged]
dcre
I've used both CC and OpenCode quite a bit and while I like both and especially appreciate the work around OpenTUI, experience-wise I see almost no difference between the two. Maybe it's because my computer is fast and I use Ghostty, but I don't experience any flickering in CC. Testing now, I see typing is slightly less responsive in CC (very slightly: I never noticed until I was testing it on purpose).
We will see whether OpenCode's architecture lets them move faster while working on the desktop and TUI versions in parallel, but it's so early — you can't say that vision has been borne out yet.
xpe
Update: Ah, I see this part: "This credential is only authorized for use with Claude Code and cannot be used for other API requests."
Old comment for posterity: How do we know this was a strategy/policy decision versus just an engineering change? (Maybe the answer is obvious, but I haven't seen the source for it yet.) I skimmed the GitHub issue, but I didn't see discussion about why this change happened. I don't mean just the technical change; I mean why Anthropic did it. Did I miss something?
jcheng
An engineer on my team who is working on TUI stuff said that avoiding the flicker is difficult without affecting the ability to copy/paste using the mouse (something to do with "alternate screen mode"). I haven't used OpenCode (yet) but Google does turn up some questions (and suggested workarounds) around copy/paste.
createaccount99
> unusual L for Anthropic
Not unusual, not for Anthropic.
cat-whisperer
I am curious, I haven't faced any major issues using claude code in my daily workflow. Never noticed any flickering either.
Why do you think opencode > CC? what are some productivity/practical implications?
azuanrb
Opencode has a web UI, so I can open it on my laptop and then resume the same session on the web from my phone through Tailscale. It’s pretty handy from time to time and takes almost zero effort from me.
The flickering is still happening to me. It's less frequent than before, but still does for long/big sessions.
kristianp
Interesting that [1] is 30% zig as well as mostly typescript. That's a lot of native code for something that runs in a terminal (i.e. no graphical code required).
lemming
This will piss a lot of people off, and seems like a strange move. I get that this was always a hack and against the ToS. But I've been paying Anthropic money every month to do exactly what I would have done with Claude Code, but in another harness that I like better. All they've achieved here is that I am no longer giving them money. Their per-token pricing is really expensive compared to OpenAI, and I like the results from the OpenAI models better too, they're just very slow.
Here's a good benchmark from the brokk team showing the performance per dollar, GPT-5.1 is around half the price of Opus 4.5 for the same performance, it just takes twice as long.
https://brokk.ai/power-ranking?dataset=openround&models=flas...
So as of today, my money is going to OpenAI instead of Anthropic. They probably don't care though, I suspect that not many users are sufficiently keen on alternative harnesses to make a difference to their finances. But by the same token (ha ha), why enforce this? I don't understand why it's so important to them that I'm using Claude Code instead of something else.
gbear605
Presumably Claude Code is a loss leader to try to lock you into their ecosystem or at least get you to exclusive associate “AI” with “Claude”. So if it’s not achieving those goals, they’d prefer if you use OpenAI instead.
wiether
That's my understanding and that's what I see happening at some places.
People got a CC sub, invest on the whole tooling around CC (skills and whatnot) and once they're a few weeks/months in, they'll need a lot of convincing to even try something else.
And given how often CC itself changes and they need to keep up with it, that's even worse. It's not just not wanting to get out of your confort zone, it's just trying to keep up with your current tools. Now if you also have to try a new tool every other day, the 10x productivity improvements claimed won't be enough to cover the lack of actual working hours you'll be left with in a week.
pluralmonad
I think most if not all of my CC customizations (skills, MCP config, CLAUDE.md) are quite easily portable to another agent. They are just text files. I may need to adjust one or two Claude specific things like thinking level instruction verbiage, but otherwise I don't see that as very sticky.
fragmede
> it just takes twice as long.
but time is also money. Personally if I could pay more money to get answers faster, I'd pay double.
oldhead
This headline is misleading. EDIT: Or rather was, at it has now been edited to be accurate.
You can still bring your own Anthropic API key and use Claude in OpenCode.
What you can no longer do is reverse engineer undocumented Anthropic APIs and spoof being a Claude Code client to use an OAuth token from a subscription-based Anthropic account.
This really sucks for people who want a thriving competitive market of open source harnesses since BYOK API tokens mean paying a substantial premium to use anything but Anthropic's official clients.
But it's hard to say it's surprising or a scandal, or anything terribly different from what tons of other companies have done in the past. I'd personally advise people to expect everything about using frontier coding models becoming much more pay-to-play.
planckscnst
The API key is not a subscription. The title says subscriptions are blocked from using third-party tools. Or am I misunderstanding?
oldhead
Headline's been edited since my post. It previously said something along the lines of "Anthropic bans API use in OpenCode CLI"
barnabee
The ideal endgame is that AI lets us build tools that make it impossible to tell what application or device is using their APIs and everything becomes open to third party clients whether they like it or not.
weird-eye-issue
The API is not banned only using the Claude Code subscription is
I actually tried this several months back to do a regular API request using the CC subscription token and it gave the same error message
So this software must have been pretending to be Claude Code in order to get around that
A Claude Code subscription should not work with other software, I think this is totally fair
creativeSlumber
> A Claude Code subscription should not work with other software.
why not though? aren't you paying for the model usage regardless of the client you use?
cortesoft
No, you are paying to use Claude code… it uses the model underneath, but you aren’t paying for raw model usage. For whatever reason, Anthropic thinks this is the best way to divide up their market.
They want to charge more for direct access to the model.
JimmaDaRustla
> No, you are paying to use Claude code
Why would anyone pay a subscription for barebones LLM agent?
You can beat that drum all you want, but you know it's bullshit. People pay the subscription for the AI, not the tool that consumes it. That tool being crap is why everyone started using third-party tools.
The reason they are blocking third-party usage is they want developers to use only their models and no competitors.
weird-eye-issue
That's not up to you or me. I think it's pretty clear by the phrase "Claude Code subscription" that it's meant for only "Claude Code". Why are you confused?
This could be so easily abused by companies who spend thousands of dollars per month for API costs you could just reverse engineer it and use the subscription tokens to get that down to a few hundred
gpm
That phrase isn't the official one. It's "The Max Plan" which "combines Claude Desktop and mobile apps and Claude Code in one subscription".
iwontberude
It’s like saying Netflix is wrong to require an official Netflix client to access their service. Total dud of an argument if you ask me.
bandrami
Can I script and scrape Claude Code to provide the exact same data for consumption by the banned client? (This sounds like an interesting challenge for Claude Code to try...)
potamic
I don't think they are confused. They are simply challenging the assertion that the model should not work with other software. Which is fair because there is a lot of precedent around whether a service can dictate how it must be consumed. It's not a simple answer and there are good reasons for both sides. Whichever path we take will have wide consequences and shape our future in a very distinct way. So it is an important decision, and ultimately up to us, as a society to influence and guide.
casparvitch
IDK if Anthropic wants to offer a service at below cost, I don't think they should gate keep which client you access that service over. Or in other terms, I won't use a service that locks me into a client I don't like.
conception
But they get telemetry, feedback, good will, etc. That’s one reason why usage is discounted to a subscription fee.
adastra22
They don't get any telemetry or feedback data from me, as I've turned all that off. So why should I be limited to CC?
CuriouslyC
Good will, huh?
nebezb
> aren't you paying for the model usage
No, you’re paying for “Claude Code” usage.
protocolture
>A Claude Code subscription should not work with other software, I think this is totally fair
Strongly disagree. They are just trying to moat.
iwontberude
It’s a private API. What part of this is hard to understand? This is why you don’t code against undocumented APIs with no contract. It’s self destructive.
nextaccountic
Is Claude Code still available on IDEs through ACP?
lemming
Should be, yes - ACP is basically just a different way of invoking the agent, so you're still using Claude Code. It's alternative clients like OpenCode, the CharmBracelet one and pi which will be affected - they basically reimplement the agent part and just call the API directly.
Syzygies
Yes. I've been using it today with Zed (a mind-blowing editor, by the way).
One must use an API key to work through Zed, but my Max subscription can be used with Claude Code as an external agent via Zed ACP. And there's some integration; it's a better experience than Claude Code in a terminal next to file viewing in an editor.
JimmaDaRustla
> A Claude Code subscription should not work with other software, I think this is totally fair
Why the hell not? What an L take - if I pay a subscription fee for an API, I should be able to use that API however I want. If they're forcing users to only consume their APIs with a proprietary piece of software, it really begs what's in that software that makes it valuable to them. Seems like there's something nefarious involved.
undefined
sfmike
but if something is used in CLI it makes sense it would be in order to be used with other things in the CLI
hsbauauvhabzb
Yeah, you shouldn’t infringe the copywrite of a tool written by a company which is built off of copywrite infringement.
weird-eye-issue
First of all you mean "copyright". Second of all this has literally nothing to do with copyright
misternugget
Engineer working on Amp here.
I'm very surprised that it took them this long to crack down on it. It's been against the terms of service from the start. When I asked them back in March last year whether individuals can use the higher rate limits that come with the Claude Code subscription in other applications, that was also a no.
Question is: what changed? New founding round coming up, end of fiscal year, planning for IPO? Do they have to cut losses?
Because the other surprise here is that apparently most people don't know the true cost of tokens and how much money Anthropic is losing with power users of Claude Code.
cmdtab
Yeah. If my claude code usage was on API directly, it would be in thousands. I know this because I have addon credits on top of the max plan because I run into weekly limits often
ramoz
You think anthropic is losing money now with the weekly limits? And while hitting the gas on mass market?
Esophagus4
I thought inference was relatively cheap - no?
bazhand
FWIW this isn’t new, using a Claude/Max subscription auth token as a general-purpose “API key” has been known (and blocked) for ages. OpenCode basically had to impersonate the official Claude Code client to make that work, and it always felt like a loophole that would get patched eventually.
This is exactly why (when OpenCode and Charm/Crush started diverging) Charm chose not to support “use your Claude subscription” auth and went in a different direction (BYOK / multi-provider / etc). They didn’t want to build a product on top of a fragile, unofficial auth path.
And I think there’s a privacy/policy reason tightening this now too: the recent Claude Code update (2.1-ish) pops a “Help improve Claude” prompt in the terminal. If you turn that ON, retention jumps from 30 days to up to 5 years for new/resumed chats/coding sessions (and data can be used for model improvement). If you keep it OFF, you stay on the default 30-day retention. You can also delete data anytime in settings. That consent + retention toggle is hard to enforce cleanly if you’re not in an official client flow, so it makes sense they’re drawing a harder line.
artdigital
Yea exactly, I’m surprised people are calling this “drama”. It was from the beginning against the ToS, all the stuff supporting it just reverse engineered what Claude Code is doing and spoof being a client.
I tried something similar few months back and Claude already has restrictions against this in place. You had to very specifically pretend to be real Claude Code (through copying system prompts etc) to get around it, not just a header.
Max-Limelihood
It’s bad that this is against the TOS in the first place, and reeks of anticompetitive behavior. Why does Anthropic care what frontend I use as long as I pay for their model?
brainless
I know this will sound strange, but SOTA model companies will eventually allow subscription based usage through third-party tools. For any usage whatsoever.
Models are pretty much democratized. I use Claude Code and opencode and I get more work done these days with GLM or Grok Code (using opencode). Z.ai (GLM) subscription is so worth it.
Also, mixing models, small and large ones, is the way to go. Different models from different providers. This is not like cloud infra where you need to plan the infra use. Models are pretty much text in, text out (let's say for text only models). The minor differences in API are easy to work with.
MeetingsBrowser
Wouldn't this mean SOTA model companies are incentivized not to allow subscriptions through third parties?
If all the models are interchangeable at the API layer, wouldn't they be incentivized to add value at the next level up and lock people in there to prevent customers from moving to competitors on a whim.
Majromax
> If all the models are interchangeable at the API layer, wouldn't they be incentivized to add value at the next level up
Just the other day, a 2016 article was reposted here [https://news.ycombinator.com/item?id=46514816] on the 'stack fallacy', where companies who are experts in their domain repeatedly try and fail to 'move up the value chain' by offering higher-level products or services. The fallacy is that these companies underestimate the essential compexities of the higher-level and approach the problem with arrogance.
That would seem to apply here. Why should a model-building company have any unique skill at building higher-level integration?
If their edge comes from having the best model, they should commoditize the complement and make it as easy as possible for everyone to use (and pay for) their model. The standard API allows them to do just this, offering 'free' benefits from community integrations and multi-domain tasks.
If their edge does not come from the model – if the models are interchangeable in performance and not just API – then the company will have deeper problems justifying its existing investments and securing more funding. A moat of high-level features might help plug a few leaks, but this entire field is too new to have the kind of legacy clients that keep old firms like IBM around.
brainless
I do not know what that next level is to be honest. Web search, crawler, code execution, etc. can all be easily added on the agent side. And some of the small models are so good when the context is small that being locked into one provider makes no sense. I would rather build a heavy multi-agent solution, using Gemini, GLM, Sonnet, Haiku, GPT, and even use BERT, GlinER and other models for specific tasks. Low cost, no lock-in, still get high quality output.
thorum
AI labs are not charities and there is no way to make money offering unlimited access to SOTA LLMs. Even as costs drop, that will continue to be true for the best models in 2027, 2028 etc. - as demonstrated by the fact that CPU time still costs money. The current offerings are propped up by a VC bubble and not sustainable.
brainless
I agree but that is not the issue. See the really "large" models are great at a few things but they are not needed for daily tasks, including most coding tasks. Claude Code itself uses Haiku for a lot of tasks.
The non-SOTA companies will eat more of this pie and squeeze more value out of the SOTA companies.
substackreader
They already do it’s called the API
deveworld
The fix has been merged in https://github.com/anomalyco/opencode-anthropic-auth/pull/11, and PR https://github.com/anomalyco/opencode/pull/7432 is open to bump the version.
Until it's released, here's a workaround:
1. git clone https://github.com/anomalyco/opencode-anthropic-auth.git
2. Add to ~/.config/opencode/opencode.json: "plugin": ["file:///path/to/opencode-anthropic-auth/index.mjs"]
3. Run: OPENCODE_DISABLE_DEFAULT_PLUGINS=true opencode
meeq
Anthropic shot themselves in the foot with this decision. It‘s a PR nightmare and at the same time the open source community will always find a way. They just wasted everyone‘s time and likely lost a bunch of users while doing so.
Thank you for sharing this!
mike_hearn
The open source community won't always find a way. Remote attestation isn't a new concept (it doesn't have to be hardware backed, the concept is general).
The industry has enough experience with this by now to know how it goes, and open source projects are always the first to drop out of the race. The time taken to keep up becomes much too high to justify doing on a voluntary basis or giving away the results, so as the difficulty of bypassing checks goes up the only people who can do it become SaaS providers.
BluRay BD+ was a good example of that back in the day. AACS was breakable by open source players. Once BD+ came along the open source doom9 crowd were immediately wiped out. For a long time the only breaks came from a company in Antigua that sold a commercial ripper, which was protected from US law enforcement by a WTO decision specific to that island.
You also see this with stuff like Google YouTube/SERP scraping. There currently aren't any open source solutions that don't get rapidly blocked server side, AFAIK. Companies that know how to beat it keep their solutions secret and sell bypasses as a service.
codesparkle
counterpoint: yt-dlp
cmrdporcupine
Apparently this has already been stopped in its tracks?
Anthropic seems determined to plug the hole.
touristtam
has opencode repo moved organisation from under sst to anomalyco?
tietjens
yes, anomalyco now comprises of sst, opencode, etc.
mcast
I’m not surprised they closed the loophole, it always felt a little hacky using an Anthropic monthly sub as an API with a spoofed prompt (“You are Claude Code, Anthropic's official CLI for Claude”) with OpenCode.
Google will probably close off their Antigravity models to 3P tools as well.
JimmaDaRustla
Lots of arguing about semantics of what the subscription is actually intended for.
Claude Code, as a coding assistant, isn't even mediocre, it's kind of crap. The reason it's at all good is because of the model underneath - there's tons of free and open agent tools that are far better than Claude Code. Regardless of what they say you're paying the subscription for, the truth is the only thing of value to developers is the underlying AI and API.
I can only think of few reasons why they'd do this: 1. Their Claude Code tool is not simply an agent assistant - perhaps it's feeding data for model training purposes, or something of the sorts where they gain value from it. 2. They don't want developers to use competitor models in any capacity. 3. They're offloading processing or doing local context work to drive down the API usage locally, making the usage minimal. This is very unlikely.
I currently use Opus 4.5 for architecting, which then feeds into Gemini 3 Flash with medium reasoning for coding. It's only a matter of time before Google competes with Opus 4.5, and when they do, I won't have any loyalty to Anthropic.
jacquesm
For AI companies the access to the interaction is very valuable, that explains the price difference. It is data that the competition does not have access to. Of course they are storing that data for model training purposes, that's the whole reason this exists in the first place. They are subsidizing until they get their quality up to the point that the addiction is so strong you won't be able to get through your workday without it. And then surprise the per month access fee will start to rise.
ramoz
The other harnesses would arguably give them even richer data and product insights.
viraptor
And it already has a workaround. https://github.com/anomalyco/opencode/issues/7410#issuecomme...
I really don't understand why they thought this is a good idea. I mean I know why they wish to do this, but it's obviously not going to last.
szundi
[dead]
Get the top HN stories in your inbox every day.
For folks not following the drama: Anthropic's $200/month subscription for Claude Code is much cheaper than Anthropic's pay-as-you-go API. In a month of Claude Code, it's easy to use so many LLM tokens that it would have cost you more than $1,000 if you'd paid via the API.
Why is Anthropic offering such favorable pricing to subscribers? I dunno. But they really want you to use the Claude Code™ CLI with that subscription, not the open-source OpenCode CLI. They want OpenCode users to pay API prices, which could be 5x or more.
So, of course, OpenCode has implemented a workaround, so that folks paying "only" $200/month can use their preferred OpenCode CLI at Anthropic's all-you-can-eat token buffet.
https://github.com/anomalyco/opencode/issues/7410#issuecomme...
Everything about this is ridiculous, and it's all Anthropic's fault. Anthropic shouldn't have an all-you-can-eat plan for $200 when their pay-as-you-go plan would cost more than $1,000+ for comparable usage. Their subscription plans should just sell you API credits at, like, 20% off.
More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.)