Claude subscription changes coverage of `claude -p`

https://x.com/i/trending/2054617957440143639

by ramoz • 2 months ago

60 50 2 months ago

x.com

ramoz5• 2 months ago

The wording in the press is very confusing. Not sure if deliberate.

If you're an active `claude -p` user, it will now cost you API rates vs being able to user your subscription.

UPDATE: https://x.com/lydiahallie/status/2054650920768807313?s=20

Still confused.

aselimov3• 2 months ago

Where are you seeing that info?? The link you posted says nothing about -p

paulddraper6• 2 months ago

It's literally there.

ramoz5• 2 months ago

I wasn't able to post the official links because it was already posted by simple reposters who didn't understand, and titled their HN posts as "you get credits" basically

this is the original thread https://x.com/ClaudeDevs/status/2054610152817619388?s=20

teg4n_• 2 months ago

I mean it does cost you API rates, you just get a certain amount of credit by having a subscription.

solenoid09375• 2 months ago

You also get $200 in monthly credits so it's not bad.

gcr4• 2 months ago

Ya but that monthly usage doesn't refill every five hours or every week the way your subscription usage does. Once you're through the $200, you're done until next month.

throawayonthe• 2 months ago

hahahahahahaha

paulddraper6• 2 months ago

Title is misleading. (EDIT: Has been updated)

https://x.com/ClaudeDevs/status/2054610152817619388

You can claim a monthly credit that covers programmatic (`claude -p`, etc) usage.

So a Claude subscription does cover it, but at a lesser amount.

ramoz5• 2 months ago

Happy to change the title if there is explicit clarity on what my `claude -p` usage costs me today & it not differing from what it'll cost me once the change is in effect.

puglr2• 2 months ago

It's a bit disheartening that this is generating so little discussion (this thread seems to be the one with the most comments, currently at 8).

99% of my max plan usage is non-interactive, and this post-June 15 pricing will far, far exceed what I can afford. I assume this applies to a great deal of us.

mkw5053• 2 months ago

Out of curiosity, how are you using it and for what?

puglr2• 2 months ago

Lots and lots of automation, along with long-running multi-instance headless tasks. My usage, which I was on the verge of increasing via a second Max plan, would cost 3 figures per day, rather than per month. I already know this because my initial tooling was prototyped against direct API usage, and that was the cost of my usage patterns.

That is not sustainable for me. I understand that Anthropic can't subsidize all of us forever, but this will force me away from claude which is unfortunate. A number of the people I work with are similarly affected.

paulddraper6• 2 months ago

Yeah, it's a pretty wild change.

It's one thing for Anthropic to ban subscription usage of OpenCode etc of their backend.

It's another thing to use their tools and still not get the full usage.

Claude's recent one 9 of uptime [1] might have something to do with it.

[1] https://status.claude.com/

solenoid09375• 2 months ago

It's not bad at all. You get $200 in monthly extra usage credits. Unless you are a deeply unprofitable user this change is no big deal.

sigseg1v• 2 months ago

is using a Ralph loop for all tasks with "claude -p" and using my weekly limit up to 100% considered some kind of unprofitable outlier? It's a command line tool, it would be ridiculous to expect that a large number of users don't do this. I never launch "claude" interactively by itself.

My understanding is that now with this workflow I will pay the same amount but get much less usage before getting to 100% for the week. How is that not bad?

brianwawok• 2 months ago

The $200 plan is easily providing $2000 of AI usage. So with this change your bill goes from $200 to $200 + $2000 -$200 = $2000. That’s a 10x jump.

Stuff like gas town is dead in the water

user342832• 2 months ago

After the recent doubling of usage limits Opus 4.7 via claude -p barely offers enough usage on the Pro plan to review changes I make via Codex.

I assume that with API pricing it will run out in the first week and I might as well unsubscribe.

paulddraper6• 2 months ago

Unless you are a deeply unprofitable user

Well..........

That was the point of the subscription. It gave you extremely discounted pricing, in exchange for recurring revenue.

For a normal subscription user, they would get multiple X of what they would if paying on-demand usage.

solenoid09375• 2 months ago

Before the doomers come in, you get $200 in API credits every month for claude -p usage. Usage counts against those API credits.

This is a nothing burger.

ramoz5• 2 months ago

This is much of a something burger for users who actively use `claude -p` under their subscription. Users will have to do their own math, but that 200 could come and go quite fast and then you're hitting normal API rates versus what you had previously been hitting.

https://x.com/jeremyphoward/status/2054682882753597603?s=20

solenoid09375• 2 months ago

Sure, but if you spend that many tokens you're probably a pretty big net loss for the company anyways. No company will subsidize that level of compute for you indefinitely.

gcr4• 2 months ago

You're not understanding the difference between API billing and subscirption billing.

Subscription usage refills every five hours. API billing doesn't.

Shadowmist• 2 months ago

Before we got $0 for API usage and banned if caught trying to use a subscription for API stuff, but now there is monthly credit for API.

paulddraper6• 2 months ago

This is definitely not a nothing burger.

$200 of on-demand usage credits is much, much, much less than what they were getting with $200 subscription.

Maybe "good," maybe "bad," but definitely, definitely not a nothing burger.

luckystarr• 2 months ago

So what does that mean? Claude within ACP within my editor is billed differently than Claude via CLI?

gcr4• 2 months ago

As a fellow zed user, I fear this could affect us (though i'm not 100% confident). Zed uses their own adapter to implement claude's ACP support, and it's likely using `claude -p` (the agent SDK) under the hood.

Hoping the Zed team will clarify.

mswphd• 2 months ago

it is using the agent SDK, see

https://github.com/agentclientprotocol/claude-agent-acp/blob...

gcr4• 2 months ago

A better link: https://support.claude.com/en/articles/15036540-use-the-clau...

ed_mercer• 2 months ago

I guess Openclaw can update their docs once again.

alyxya• 2 months ago

This could end up becoming a cat-and-mouse game where users programmatically try to turn their non-interactive usage of Claude Code to appear interactive and Anthropic tries to detect and charge that under API pricing. I don't know if there's a proper solution here because there will always be borderline use cases like using Claude Code on a cloud VM, where it would be nicer to interactively do work through sending and receiving messages on a custom frontend rather than SSHing and using the CLI.

9wzYQbTYsAIc• 2 months ago

Next thing to go will be loops and scheduled tasks, if they keep needing to trim usage to fit in the available compute, I suspect, if ‘claude -p’ is essentially gone, now.

bluesnowmonkey• 2 months ago

https://news.ycombinator.com/item?id=48126438

melonamin• 2 months ago

I wonder how this cat-and-mouse game will end. I've been using my own wrapper around Claude CLI that overcomes some 'claude -p' limitations, and now I have even more reasons to.

But inevitably, this will end, ultimately making AI a bit less accessible for consumers.

2001zhaozhao2• 2 months ago

I mostly get this change from their side except for the extremely misleading framing. I think in response to this change, I might write an open-source Claude Code GUI wrapper to wrap over the TUI and allow accessing it from a GUI interface.

Still interactive (conforms to spirit of Anthropic's new rule), and runs Claude Code via the actual CLI (conforms to letter of Anthropic's rule), without even using the JSON output flag. It would just read the outputs directly from the terminal like a user would, and then translates the user's actions directly into actions to the Claude Code TUI.

Tradeoffs: the thinking blocks are lost, and file changes from edit tools might have to be reconstructed after-the-fact using VCS commands because the TUI doesn't display them when accept-edits mode is enabled. Requires underlying terminal to have a giant width/height in order to reliably capture the outputs by reading the terminal alone. Interactive tools like AskUserQuestion will need to work via detecting that such a prompt is open and exposing the original CLI interface to the user temporarily.

But overall it seems like it could give users most of the benefits of an interactive GUI interface (scrollable history, much higher info density, easy to copy text, browse features with mouse) while staying compliant with Anthropic's new rules both in letter and spirit. You can then build a worktree manager or whatever above this agent GUI layer. This way us interactive users can have our good tools back (and leverage the new claude -p credit for occasional automation features) while the people who are actually abusing the plan with 24/7 dark factories or openclaw are still locked out.

(the only way Anthropic would not agree to this is if they had the ulterior motive of lock-in in mind...)

skeledrew3• 2 months ago

I'd really love a proper CC GUI myself.

Tradeoffs [...]

Sounds like you're thinking of scraping the raw terminal output. Consider using a terminal library (pyte[0] comes to mind) for interaction and processing the session files for tool use data, etc.

[0] https://pyte.readthedocs.io/en/latest/

2001zhaozhao2• 2 months ago

Yeah i've been thinking of hooks and reading the session file as possible ways for getting tool use data.

Also I managed to get a VSCode Claude Code wrapper working last night. It launches instances of browser-based VSCode (via Coder's code-server) with Claude Code plugin pre-installed, then hides all toolbars and opens the CC window using another bundled custom plugin. Still have a few integration problems to solve, but in theory this should be perfectly allowed by Anthropic, give you a pretty good UI, and still allow integration into an agent orchestrator using hooks/session files to get the agent data.

zitoshi• 2 months ago

i don't quite understand the change. Does it impact purely claude code users?

skeledrew3• 2 months ago

It doesn't.

chatmasta• 2 months ago

In other news, tmux send-keys is still free.

skeledrew3• 2 months ago

These Twitter/X links are killing me, especially when they don't work with XCancel which seems to be happening more frequently. This one just gave me a summary by Grok, and I have no idea now if I'm seeing the same thing that others are commenting on.

frabcus• 2 months ago

Agreed. All I see is a grok summary of a lot of X posts. The original link is not suitable. Anyone have a link to a proper announcement?

paulddraper6• 2 months ago

https://twitterwebviewer.com/?tweet=2054610152817619388

LinXitoW• 2 months ago

It's really important to note that the programmatic vs. interactive framing is a little misleading. For example, if you're using some IDE integrations, that is still interactive, that is still the same usage pattern as using it in the Claude Code CLI. BUT with these new rules, it'll count against this special "programmatic" usage.

Considering what kind of fuckups happened up until now everytime Anthropic vibe codes a horrible anti-automation "fix" (like billing extra usage just because the string "hermes" exists somewhere in the prompt), this will get funny/horrible really fast. After all, you can very easily script tmux to use Claude Code "interactively".

What crazy shenanigans are gonna happen? Are people that type too fast, or people that copy paste too much, or people that output to markdown/json too often going to wake up to a 800$ extra usage bill or a banned account?

Claude subscription changes coverage of `claude -p`

Related Stories