Claude Code removed from Anthropic's Pro plan

Posted by JamesMcMinn 2 hours ago

Counter298Comment184OpenOriginal

Comments

Comment by robertkarl 1 hour ago

I don't think I've ever been on such a rollercoaster with a company's reputation in the developer space. I started in January on the $20 plan, essentially my first agentic AI programming. I quickly started hitting limits developing several apps at the same time. I went up to the $200 plan after seeing the value.

After seeing my own issues with 4.6 and the mega-post on Github about declining metrics in a decent dataset of claude chats by Stella Laurenzo at AMD (https://github.com/anthropics/claude-code/issues/42796), I downgraded to the $100 plan. Hallucinations. Laziness. Lack of thinking. The responses on those mega-threads from Anthropic rubbed me the wrong way in a "you're holding it wrong" kinda way.

In the past week, I downgraded back to the $20 plan because the Codex $20 plan on 5.4 was working so well for me.

Then throw in other oddball events like the source code leak, and the super positive Anthropic events like their interactions with the current administration. It's a wild ride.

I can't understand removing Claude Code from $20. I'm interested to see whether this is confirmed or not.

I'm a career engineer and I went from being one of their most outspoken proponents (at least within my circle) and now.... I'm not.

Comment by jmcodes 1 hour ago

Same loved them, told my team about them, got them to switch off of cursor, now I'm telling them to swap to Codex.

Anthropic really pissed me off with their harness crap. They're well within their rights but their communication over it was enough to get me to swap. I don't need extra hurdles when there's a perfectly valid alternative right there. They don't have the advantage they think they do.

Comment by operatingthetan 1 hour ago

I think we are inevitably heading to using the cheap Chinese models like Kimi, GLM, and Minimax for the bulk of engineering tasks. Within 3-6 months they will be at Opus 4.6 level.

Comment by kzisme 9 minutes ago

How challenging are these to setup locally and have them running?

Comment by robertkarl 1 hour ago

This was literally my task today, to try out Qwen 9B locally on my, albeit a bit memory-constrained at 18GB, macbook with pi or opencode. Before reading this update.

Comment by operatingthetan 1 hour ago

Minimax coding plan is $10 a month for roughly 3x the $20 Claude Pro CLI usage allowed. That would be good place to start. 200k context though.

Comment by jorjon 1 hour ago

MiniMax has its own issues. Server overloads, API errors, and failure to adhere to even the system prompt. It can happily work for hours and get no job done.

Comment by someuser54541 1 hour ago

Please report back, would be very interested in your findings.

Comment by robertkarl 5 minutes ago

For what it's worth: here's my experience in the first 10 minutes of using Qwen locally to write some code. https://github.com/robertkarl/local-qwen-first-10-minutes it includes some token generation numbers and steps to repro.

Comment by sshine 19 minutes ago

I ran OpenCode + GLM-5.1 for three weeks during my vacation. It’s okay. It thinks a lot more to get to a similar result as Claude. So it’s slower. It’s congested during peak hours. It has quirks as the context gets close to full.

But if you’re stuck with no better model, it’s better than local models and no models.

I have to say, OpenCode’s OpenUI has taught me what modern TUIs can be like. Claude’s TUI feels more like it’s been grown than designed. I’m playing around with TUI widgets trying to recreate and improve that experience

Comment by taikon 6 minutes ago

To be clear, was OpenCode a better in your opinion compared to ClaudeCode?

Comment by TacticalCoder 4 minutes ago

> I have to say, OpenCode’s OpenUI has taught me what modern TUIs can be like. Claude’s TUI feels more like it’s been grown than designed.

Claude's TUI is not a TUI. It's the most WTF thing ever: the TUI is actually a GUI. A headless browser shipped the TUI that, in real-time, renders the entire screen, scrolls to the bottom, and converts that to text mode. There are several serious issues and I'll mention two that do utterly piss me off...

1. Insane "jumping" around where the text "scrolls back" then scrolls back down to your prompt: at this point, seen the crazy hack that TUI is, if you tell me the text jumping around in the TUI is because they're simulating mouse clicks on the scrollbar I would't be surprised. If I'm not mistaken we've seen people "fixing" this by patching other programs (tmux ?).

2. What you see in the TUI is not the output of the model. That is, to me, the most insane of it all. They're literally changing characters between their headlessly rendered GUI and the TUI.

> Claude’s TUI feels more like it’s been grown than designed.

"grown" or "hacked" are way too nice words for the monstrosity that Claude's TUI is.

Codex is described as a: "Lightweight coding agent that runs in your terminal". It's 95%+ Rust code. I wonder if the "lightweight" is a stab at the monstrosity that Claude's TUI is.

Comment by hank2000 1 hour ago

how was it? I'm doing this today

Comment by robertkarl 1 hour ago

I will report back... but I have to recommend this comment on a post about Qwen 3.6 https://news.ycombinator.com/item?id=47843466 by daemonologist

it goes into detail about llama-server args; quants to try; and layer/kv cache splits. I plan to try the techniques there.

Comment by try-working 1 hour ago

Kimi K3 in July-September is the big one.

Comment by robertkarl 1 hour ago

One thing I enjoy about Cursor and Codex mac apps is the embedded preview window. I know it's not as hardcore as the terminal/tmux but it's hella convenient. But Cursor bugs me with the opacity around what model I'm using. It seems deliberately to be routing requests based on its perceived complexity. What draws you to codex vs cursor?

Comment by eleventen 1 hour ago

Matches my experience very well. All the goodwill earned from taking a stand against the DoD seemingly forgotten in a month. Coincidentally, I canceled my pro subscription and got set up with OpenCode and OpenRouter last night.

Comment by alwillis 1 hour ago

> I can't understand removing Claude Code from $20

Not according to their webpage: "Claude Code is included in your Pro plan. Perfect for short coding sprints in small codebases with access to both Sonnet 4.6 and Opus 4.7." [1]

[1]: https://claude.com/product/claude-code

Comment by eleventen 58 minutes ago

There are clear contradictions across their marketing site. As others have pointed out, it's being removed from some help articles and the pricing chart now shows it revoked. Confusing signals, but they seem to be changing all pages in this direction and haven't updated that one yet.

See https://news.ycombinator.com/item?id=47854478

Comment by Yizahi 59 minutes ago

LLM monsters are deeply unprofitable, going by the industry hearsay (which is the only thing we have, given ultra secrecy of the LLM corporations). The only two LLM companies which disclosed their finances without lies, were two Chinese corporations and they, unsurprisingly, were deeply in red.

Remember the old saying about boiling a frog? LLM corporations need to make most of their users pay hundreds per month, asap. This is Anthropic increasing temperature regulator under the pot just a tiny little bit. Not the first and not the last time.

Comment by zormino 1 hour ago

I think removing Claude Code from the $20 tier is a terrible idea, I never would've gone from nothing right into the $100/200 tier. The $20 plan let me get my feet wet and see how good it could be, and in less than a week I was on the $100 plan.

I think they need to at least have a 1 month introductory rate for the max plan at $20, or devs that decide to try out agentic coding just won't go to Anthropic.

That leads to downstream impacts, like when a company is deciding which AI coding tools to provide and the feedback management hears everyone is already used to (e.x.) Codex, then Anthropic starts losing the enterprise side of things.

Comment by siva7 42 minutes ago

They're not losing anything. They have much more demand than they could ever fulfill to care anymore about promotional or subsidized user groups.

Comment by elschneider 1 hour ago

I had a similar ride, but disagree with your conclusion. Opus 4.7 is so incredibly powerful from my experience, that nothing else really matters and I think at Anthropic they know it. People will pay a lot for access to this model.

Comment by bdelmas 15 minutes ago

Opus 4.7 may be incredible but for how long? And they may have Mythos but I feel like they will put it out if pressed too much by their competitors. And again for how long will they keep the advantage?

At the speed everything is advancing I don’t think it’s such an advantage. They all catch each other up pretty fast. That’s why I prefer to pay Cursors and have access to all of them instead of being lock to a single one (even if that means to lose some discounted credits). If they opened Mythos today at a good price that would be something else.

Comment by operatingthetan 1 hour ago

>Opus 4.7 is so incredibly powerful from my experience,

I'm not challenging your opinion, but this is an outlier in the general current public opinion about it.

Comment by elschneider 1 hour ago

Yea, I've seen a lot of whining online, because its more expensive, but from the interactions I've had I'd say, that it's well worth it. To me it feels like another step change, similar to when 4.5 was introduced. Definitely a different beast.

EDIT: it is also surprising to me that everyone seems to believe the people at Anthropic are simply incompetent and recklessly risking their good reputation, while very few consider the possible good reasons they might have for taking such drastic measures. And I don't think it's because of financial pressures in their case

Comment by 15 minutes ago

Comment by user34283 1 hour ago

I can’t say I’ve used it extensively enough to draw a conclusion, but it did seem similar to GPT 5.4 in Codex.

When I threw it at a difficult issue in an iOS app, it like GPT came up with wrongly guessed explanations. It only found the issue after I had it instrument the app and add extensive logs. Usually GPT 5.4 is the same.

Only that with GPT 5.4 it’s at least included in my subscription, while sending 3-4 messages to Opus 4.7 for this blew through my $20 plan limits and consumed $10 of extra usage on top. At that point I can’t help but bring up how much more expensive it is.

Comment by adam_th 58 minutes ago

This is one of the most civil disagreements I've ever seen on the internet and I intend to start using this myself

Comment by cjbconnor 1 hour ago

I've had completely the opposite experience. I've asked for it to research things and it's just told me to "paste xyz into google". Just now I revisited a chat that's 5 days old and asked it to check again (because what I was looking for might have changed), and it said "no".

Comment by elschneider 55 minutes ago

It's funny how experiences can be so different. I wonder if this comes down to context. My interactions so far were fairly high-level and in some cases it having a strong opinion was actually super beneficial to the outcome. To me it seemed opinionated, but in a very good way. I can see how this could backfire though and have heard similar reports.

Comment by cjbconnor 53 minutes ago

Curious to know what plan you're on? I was on the max 5x plan, but downgraded to pro a few days before the opus 4.7 release.

Comment by elschneider 51 minutes ago

I'm on max 5x

Comment by Oras 1 hour ago

Incredible, powerful, but I couldn't believe how fast I hit the limits compared to how it was with Opus 4.6. They removed Opus 4.6 completely from CC. I would prefer it with the previous limits.

That's not how you keep your customers. None of these agents have a moat, I moved away from Cursor when they started doing what Anthropic is doing now, and never went back even when I was a paying customer since the start.

Comment by sidrag22 1 hour ago

they need the devs on board for that to matter, i can get whatever i want done with lesser models already. It is quite literally about just who is not gonna give me the shittiest experience, and at anthropic it sure seems they are determined to annoy everyone since they started gaining in popularity.

Comment by strangattractor 1 hour ago

[flagged]

Comment by hannahstrawbrry 1 hour ago

FWIW their "Fin" agent on their web page tells me: "Claude Code is not included in the standard Pro plan. It's only available with premium seats on Team and Enterprise plans. However, Pro plans do include improved coding capabilities through our GitHub integration, which lets you connect code repositories directly to Claude. You also get access to code execution and file creation features in the Claude apps. For the full Claude Code terminal experience, you'd need to upgrade to a Team or Enterprise plan with premium seats"

Comment by strangattractor 1 hour ago

Even odder. I asked: Are you sure?

Yes, confirmed directly from Anthropic's website. Claude Code is included in the Pro plan, described as perfect for short coding sprints in small codebases with access to both Sonnet 4.6 and Opus 4.7. Claude

You said: Is claude code included with the pro subscription Is claude code included with the pro subscription

3:11 PM Claude responded: Yes, Claude Code is included with the Pro plan ($20/month). Yes, Claude Code is included with the Pro plan ($20/month). You can use it in the terminal, desktop app, VS Code, JetBrains, and on the web.

The main caveat is that Claude Code draws from the same usage limits as your regular Claude chat — so heavy coding sessions can eat into your quota faster. If you find yourself hitting limits often, the Max plans ($100–$200/month) offer significantly more headroom.

Thats a head scratcher:)

Comment by 1 hour ago

Comment by ricardobeat 1 hour ago

The $20/month, which is now $17, should give you a hint? Models have a knowledge cut-off and will not reflect up to date information unless you trigger a web search.

Comment by operatingthetan 1 hour ago

That's just a billing trick.

>$17 Per month with annual subscription discount ($200 billed up front). $20 if billed monthly.

Comment by civvv 1 hour ago

Do you understand how LLM's work and that they are always behind in their knowledge? Unless Claude does a network call to check its own website, it will give you outdated information. Its a prediction model, its not magic.

Comment by EstanislaoStan 1 hour ago

Claude often doesn't know the truth about Claude Code etc. lol

Comment by strangattractor 1 hour ago

I got down voted by 4 people just for pointing that out. lol

Comment by wrxd 1 hour ago

This is a risky move. I might have paid $20/month for my personal projects but the Max subscription is a bit steep.

Now I'm going to learn more about local models. I don't need to be as good as a frontier model. Good enough and free from all this drama is a win for me

Comment by CrimsonShadow 6 minutes ago

Same, I'm currently unemployed and the $20 help me to initiate many small projects. The recent taxing in the token made me start testing local models on my machine. Tho, Claude works better for the front end part imo.

Comment by Xunjin 1 hour ago

"free of this drama" and free is great option for companies, of course most use API billing but let's not forget that there are places that budget is limited and being good enough is just perfect.

Comment by peab 1 hour ago

the cursor 20$ a month plan has been working great for me. You can use most models, and unlimited use of composer 2, which is surprisingly good

Comment by redrix 13 minutes ago

Next they’ll slowly reduce how much CC usage you can get out of the $100 Max plan, then introduce a new $300 “Max Plus” plan with “40x” usage. “You asked, and we listened: Introducing Max Plus, our biggest plan yet, designed for those…” blah blah

Comment by JamesMcMinn 2 hours ago

I can't find an announcement yet, however the pricing page now shows it's not included, and various support articles have removed any mention of the the Pro plan including access to claude code.

See [1] and [2] for an example of a support article that's had claude code removed as a Pro feature.

I guess this is the beginning of the end for subsidised model access, at least from Anthropic.

[1] https://support.claude.com/en/articles/8325606-what-is-the-p... [2] https://web.archive.org/web/20260420065828/https://support.c...

Comment by _aavaa_ 2 hours ago

It’s now being explicitly shown as unavailable on the pro plan, scroll down to the comparison matrix.

Comment by UncleOxidant 1 hour ago

Claude Code is a freely downloadable CLI Agent. Why would they not let you use that anymore?

Comment by _--__--__ 1 hour ago

Because 'claude -p' is a backdoor for any third party client to use subsidized token pricing, and they've flipped course again to decide they do want the OpenClaw type users as long as they're on the $100 plan.

Comment by skeledrew 1 hour ago

> Because 'claude -p' is a backdoor for any third party client to use subsidized token pricing

Wasn't this obvious from day 1 though? Can't see how anyone could've missed that.

Comment by _--__--__ 1 hour ago

It was obvious, which is why their earlier decision to attempt to restrict 3p access was hugely unpopular. They're now trying to walk that back but on the condition that those users need to be on the higher plan.

Comment by skeledrew 1 hour ago

Now they're hurting their popularity with those who actually don't mind using Claude Code. I've been quietly swallowing a lot of performance degradation over the past few weeks as I get the resource crunch, but I'm definitely not going back to copy-pasting between browser and editor. And I have no intention of upgrading to Max or doing per token usage.

Comment by riffraff 54 minutes ago

It seems they were losing money on pro subscriptions with code so if people stop using them it's actually ok for them.

They have now moved to be enterprise providers and don't need the cheap pro users as loss leaders anymore.

Comment by SpicyLemonZest 1 hour ago

The question isn't whether anyone could have missed it, but whether Claude Code has release gates that allow people to require that obvious problems should be resolved. From their release velocity it's pretty clear that they do not.

Comment by ezfe 1 hour ago

You have to login and authorize it? It costs money to process tokens.

Comment by foolswisdom 1 hour ago

Because including it in a plan results in un-metered usage?

Comment by UncleOxidant 1 hour ago

My usage of Claude Code in the pro plan is definitely metered. Every couple hours I have to wait an hour or two and the last few weeks I've hit my weekly limit on Wednesday.

Comment by thebiblelover7 2 hours ago

And this page as well, showing how to use Claude Code on the Max plan: https://support.claude.com/en/articles/11145838-using-claude...

Comment by tmp10423288442 2 hours ago

5 minutes ago, I was seeing the old version of the page in which Claude Pro included Claude Code. I refreshed and now see that it does not.

Comment by evil-olive 10 minutes ago

if this is accurate, and not some "oops we made a vibe-coding mistake updating our website" I am going to hit the "cancel subscription" button so hard that my desk will break in half.

I have an unlimited-usage API billing plan through my dayjob, but for obvious reasons they don't allow piggybacking personal usage onto that. so I paid for the $20/mo personal plan as an easy and relatively cheap method of professional development / keeping my skills current. I don't particularly mind paying $20/mo, but I'm absolutely not paying $100/mo.

also, part of the reason I didn't mind paying for the personal subscription is that I liked having consistency between the tools I use for my dayjob and the ones I use for side projects. if that goes away, then I might as well switch away from Claude usage at work as well. I very much doubt Anthropic's revenue predictions for this change are taking things like that into account.

making a change like this without an announcement, just sneaky updates to product pages, is also an absolutely unforgivable thing to do, in terms of me trusting them as a company.

Comment by danielspace23 1 hour ago

With GLM and Kimi getting better and better, with both still providing low-cost coding plans with higher quotas, and with how trivial it is to switch to them even within Claude CLI, I'm not sure what makes Anthropic think their users would rather pay 5x than switch to the competition.

Comment by UncleOxidant 1 hour ago

I signed up for a 3 month plan with Z.ai so I could try out GLM-5.1. That was a few weeks ago when it was still $27 for 3 months, now it's $48 for 3 months. I hit limits at least as much as I do with Claude. I hit a weekly limit at one point and it said I wasn't going be able to get access again for 6 days so I must've somehow hit their weekly limit on day one of the week. And that after several timeouts.

Comment by zozbot234 1 hour ago

Never mind GLM and Kimi, even GPT 5.4 offers a great plan for $20/mo. Even if it gets increased rate limits after May, it's still quite likely that casual users won't be hitting them on a regular basis.

Comment by mudkipdev 1 hour ago

The GLM coding plan price increased dramatically

Comment by akucharczyk 50 minutes ago

It cracks me up when I hear takes like - 'if you're not using more than $20, the product isn't for you because you're not a real user.' If you use CC as an assistant rather than a replacement for your own thinking, follow SDD, and use the tool thoughtfully, you deliver a lot more and you don't need the 5x or 20x limit. It's a different story if you're vibe coding, but then we're not really talking about AI-assisted work - your three prompts barely count as doing any work. I've been on Pro for 2 years, but if this is how things are going, I'll look for an alternative. Luckily, there's plenty to choose from.

Comment by chewz 2 hours ago

Makes sense.

It is over for the little guy - home enthusiasts and vibe coders. Too many of them saturating resources for Max users.

IF you cannot afford few hundred dollars subscription go out and breathe fresh air. But if you can, watch where the ball is rolling - few thousand dollars subscriptions and even less programmers.

Comment by rustyhancock 1 hour ago

Hear HN tell of it, Claude pays for itself 3× over.

Something tells me congitively it's making us misjudge how productive it's making us.

It's clearly massively increasing output, but did the market already soak up all that productivity and now it's not compensated?

If your salary is 50k. And Claude makes you 2x as productive, why aren't you earning 100k?

Why is it anyone can't afford $200/mo if it's truely increasing worker productivity?

There seems to be a paradox here.

Personally I switched to Z.ai and GLM quite some time ago. I've not noticed any decrease in quality or quantity of my work.

Comment by pcurve 11 minutes ago

yeah the more people who us it means less competitive edge you have. Benefits get devalued. And you're back to square one.

Comment by npunt 52 minutes ago

Agree about psychological impact outpacing likely actual impact, but that’s a relatively temporary phenomena as we are all adapting to the new way things work.

Productivity wise employment is far more than code production productivity in a vacuum, and productivity gains are rarely captured by employees (see famous chart on worker productivity where that correlation changed around 1970). I wouldn’t expect to see much in the next 1-2 years besides noticing effective teams increasing velocity of features.

I think people in forums like complaining about things and aren’t representative of the broader set of people who are just using the tools, so no real paradox. For vast majority of tech jobs, $200/mo is still an absolute steal in terms of what these tools offer. Only the dullest of companies would not realize this.

Fwiw in the 80s-90s computers also didn’t really register in productivity metrics. Qualitative changes occur long before accurate measurement catches up.

Comment by zormino 57 minutes ago

Because most people work for someone else and don't decide their own salaries. It's not doubling productivity, but even a 10-20% boost to productivity for a team of engineers means that, as a business, even $1k per month per seat is perfectly acceptable. For consumers and hobbyists that basically kills access.

Comment by jfrbfbreudh 1 hour ago

Truly makes no sense. I pay for the $200/month plan and end up using about $3k/month worth of API costs. I imagine that the only reason they haven’t cut me off is because my habits serve as good training data for them.

Guess they’ve decided to move in the direction of allocating compute primarily to power users and enterprise.

But power users are not a sticky customer base. I just bought the ChatGPT Pro plan and would immediately switch over if the model performance is better and/or I get more compute.

Comment by whattheheckheck 1 hour ago

Vscode agent mode and github copilot can use Claude models and has feature parity with the .md customization for agents prompts skills etc.

Not too expensive

Comment by user34283 1 hour ago

They slapped a 7.5x “promotional” multiplier on Opus 4.7 and they are removing Opus 4.6 in short order.

I heard they disabled signups for non-business accounts too.

Best forget about using Claude Opus models in Copilot.

Comment by Larrikin 1 hour ago

Why is management at Anthropic trying so hard to ruin their reputation with developers? I missed the OpenClaw hype but it was something that kept me excited about my yearly subscription.

It makes no sense to do one of the higher tier plans unless they are directly generating you money.

Comment by fg137 1 hour ago

They care about developers from companies that are on their team/enterprise plans or using bedrock.

Individual users barely matter. That's probably also the same group that decides to switch to Codex/Kimi/[whatever the hottest agent on any given day] on a whim, which Anthropic doesn't necessarily want to do business with.

Comment by sidrag22 29 minutes ago

feel like its beyond optimistic on their part, just starting to hear their name be blended with companies desires on job listings, and they are destroying the goodwill of the devs who surely are the main reason their name has landed there. They aren't dug in like a microsoft, maybe they get some staying power for nocode people who feel trapped, but im done with their nonsense already and won't recommend them anywhere. Other stuff is good enough already to match.

Comment by tayo42 1 hour ago

> Individual users barely matter.

Individuals are the ones that push for new tools at work though.

Comment by fg137 1 hour ago

A fraction of them do. Many just use whatever the employer provides to get their job done. HN users only represent a small sample of the overall software developers which is nowhere nearly enthusiastic about new things.

Source: what I witnessed at my company

Comment by mrhottakes 1 hour ago

they don't care about their reputation with devs, they care about their reputation with people that can write them big fat checks

Comment by plutokras 1 hour ago

At my company, devs were the ones pushing for the Claude subscription. Left to management, we would have only had GitHub Copilot – we already have an existing relationship with them and the tool is good enough.

If Anthropic is intent on losing the goodwill of the devs, they might not be happy with the consequences. Their product is quite commoditized at this point – the latest GPT, Gemini or GLM is just as good for most enterprise tasks.

Comment by papichulo2023 1 hour ago

Where I work. Medium size, base in Europe company. It is paying over 1800 per dev in AI tools. Home users stand no chance.

Comment by 1 hour ago

Comment by verdverm 1 hour ago

Also note that they are letting OpenClaw be used again with `claude -p`, so a partial reversal

Comment by jamietanna 1 hour ago

https://news.ycombinator.com/item?id=47853799 for the curious

Comment by Xunjin 1 hour ago

And I thought MS was confused one on how to do pricing and business decisions.

Comment by dd8601fn 1 hour ago

Last I saw they have 21 products or services named Copilot. I think they still win the confusion prize.

Comment by Xunjin 1 hour ago

We should have "The Copilot Award goes to..." Every year for the most confusing product name/lineup

Comment by dd8601fn 1 hour ago

I love it. It’ll be doubly funny when the Xbox marketing team wins the Copilot Confusion Award.

Comment by uKER 1 hour ago

So their minimum workable offer for devs just went from $17 to $100. Also, I don't see how the Pro subscription is relevant anymore. Nobody pays $17 a month just to chat. I just unsubscribed. :) Time to try Chat GPT Codex, which even works with the free subscription (don't expect crazy token allowance, of course).

Comment by kzisme 4 minutes ago

Curious how this will play out (if true) for folks who signed up for that annual plan - expecting Claude Code to be included.

Comment by 0x_rs 1 hour ago

If true, very strange change when Codex (at both 20 & 100) is a much, much better deal for a model much better at most coding tasks, with way more usage even with the /fast mode enabled. Is losing most non-enterprise customers the right move for them?

Comment by mil22 1 hour ago

Equally, will offering a presumably unprofitably large quota of Codex tokens at $20 to retain non-enterprise customers turn out to be the right move for OpenAI?

Would not be surprised to see OpenAI follow suit.

Or perhaps OpenAI's LLMs are just so more compute efficient that they can actually offer that sustainably...

Comment by 0x_rs 57 minutes ago

Feels to me it's a battle between who has the most compute. OpenAI does not seem to be struggling with their x2 usage on the new 100 Plan, which is very close to unlimited usage with the best performing model on the highest reasoning setting. Not mentioning the resets every 1 million customers, or the other generous usage multipliers last months. Meanwhile Anthropic seems to be desperately trying to cut down on inference with their changes to reasoning effort and more lately, so they might be focusing on what they consider to be more valuable customers for their long-term strategy. The 20 plan with Opus had gotten so bad on CC they might've just pulled the plug to stop people from complaining about usage limits. If OpenAI can burn money longer and capture the market from the bottom, I think they'd win in the long run.

Comment by williamstein 14 minutes ago

What does " Not mentioning the resets every 1 million customers" mean?

Comment by 0x_rs 12 minutes ago

>To celebrate 3 million weekly codex users, we are resetting usage limits.

>We will do this every million users up to 10 million.

>Happy building!

https://x.com/sama/status/2041658719839383945

Last reset today, after the 4 million users milestone.

Comment by hannahstrawbrry 1 hour ago

That's exactly what I fear- that Mythos/Glasswing has made anthropic confident that they can survive by only serving that type of customer. Would be sad to see.

Comment by sourabhv 1 hour ago

It's still included here

https://claude.com/product/claude-code

Comment by csullivannet 1 hour ago

Maybe they're putting out a weather balloon to test sentiment. That way when they're caught they can just point at the other page to say it was just a mistake.

Comment by gbalduzzi 1 hour ago

I think that Anthropic has capacity problems. They went all in on acquiring new customers but now they don't have enough capacity to both serve users and train new models, so they are trying to limit user usages.

It is pure speculation of course, but I don't have any other explanations on the stuff they are pulling in the last 2 months.

Comment by gAI 55 minutes ago

Yeah, this is pretty clearly what's going on, but I wish they'd be more transparent about it. Funneling compute to Mythos and Design, while auto-setting effort levels lower and removing user control of extended thinking. I don't think the need to shuffle compute around is unique to Anthropic, though. I suspect it's part of why Sora got killed. And everyone's having uptime issues. Are we reaching the limits of the available compute?

Comment by naet 1 hour ago

Seems like a pretty bad business move if it's really what they're doing. They should want devs using the product on a cheaper subscription to see the value with profitable limits on usage.

I think the only reason to do this would be that they just can't scale up to service the volume they have and need to cut down significantly on the total number of users. Seems also like a rough business proposition. Most of the pro plan users would probably migrate to a competitor at a similar price point (I know I will).

The only other possibility would be if they are losing too much money on the compute power and just can't offer it at that price anymore. But then upgrading the plan gives you more compute per dollar, so maybe they're just banking on people not actually using all of what they pay for?

I had previously thought that the inference cost of using a trained model was relatively low and that most costs went into training new models, but maybe that is less true with the more powerful newer models.

If it costs a ton more to serve Opus vs serving something like Kimi or Qwen, then I think most people just won't use the more expensive version for most things.

Comment by dminik 1 hour ago

Well, if there's one way to show that you're not profitable on inference, this would be it.

Comment by fxd123 44 minutes ago

Just tried Claude Code on my Pro plan. It worked. So no, it's not removed

Comment by HDBaseT 34 minutes ago

I would assume users who have an existing subscription will be grandfathered in.

It would seem misleading to sell monthly, or even yearly, subscriptions under the guise Claude Code comes with the subscription, for it to only be yanked out underneath you. (Although depending who you ask, Anthropic have already done actions similar to this).

Comment by mingus88 16 minutes ago

I was billed $220 on Mar 1 for the pro plan

If they rugpull Claude code from my already paid for annual subscription I’ll have to issue a chargeback

Comment by hannahstrawbrry 2 hours ago

Claude Code page still shows it included with Pro/Max. https://claude.com/product/claude-code

Comment by lukeasrodgers 1 hour ago

Claude Design was iterating on the plans page and decided to remove clutter and their review bot LGTM’d it as “minor copy change human review not required” and auto-merged it.

Comment by nubinetwork 1 hour ago

Shits confusing... I'm using the Claude code vscode plugin, yet my account page says I'm not using Claude code... so am I, or aren't I?

Comment by gozucito 1 hour ago

If it was removed from the pro plan, then the max plan should list claude code as one of its extras, and it doesn't.

I would not jump to conclusions yet.

Comment by thyb23 1 hour ago

In the “Compare features across plans” section, Claude Code appears to be available only on the Max plan.

Comment by gozucito 21 minutes ago

You're right. I didn't scroll down. I wonder why they didn't update the top cards that everyone see. They do it for claude Cowork but not claude code? That is not very transparent. How does it make sense? It's not like claude code is too niche to be included, it's in the main app and I know multiple non-techie people who use it.

Comment by civvv 1 hour ago

If you scroll down, you can clearly see that the Pro plan has an "x" on Claude Code now.

Comment by spprashant 1 hour ago

I can't believe they are yanking tool access instead of just reducing the token quota or simply pulling Opus 4.7 access. To be fair even that would be poorly received, but at least people would have a choice of working within limits. Claude Code is their real winner, and a great ramp for newcomers coming into AI assisted development. They are playing straight into OpenAIs hands.

Comment by poetril 1 hour ago

I’ve got nearly 10 months left on my yearly subscription, I wonder what that means for my access.

Comment by UncleOxidant 1 hour ago

Same. I hope we're grandfathered in. Otherwise current pro subscribers who signed up with the understanding that they could use it in Claude Code are going to be extremely pissed and go off and sign up for alternatives (or start running local models instead). I mean, I guess they could say too bad, they got your money, but this would destroy their brand among people who are currently their most loyal users.

Comment by skeledrew 1 hour ago

I don't want to leave, but I'm ready. The entire reason I got a Pro sub was so I can use Claude Code instead of going between browser and editor.

Comment by enedil 1 hour ago

Or also sue in fact or demand refunds.

Comment by subscribed 39 minutes ago

Same. I'm not a dev but I use CC a few times in a week and it's been a great help.

However, my company paid for my annual subscription, so maybe I'll ask our lawyers for advice - the only reason they paid for this was my access to CC and with my use the next tier wouldn't make sense, AND no one will expect Anthropic to not nerf it too.

Comment by 2001zhaozhao 9 minutes ago

Apparently it's just an A/B test. Legit LMAO moment, speedrunning reputation destruction to your entire userbase just to test a question whose answer you can probably already guess.

---

> For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected.

> When we launched Max a year ago, it didn't include Claude Code, Cowork didn't exist, and agents that run for hours weren't a thing. Max was designed for heavy chat usage, that's it.

> Since then, we bundled Claude Code into Max and it took off after Opus 4. Cowork landed. Long-running async agents are now everyday workflows. The way people actually use a Claude subscription has changed fundamentally.

> Engagement per subscriber is way up. We've made small adjustments along the way (weekly caps, tighter limits at peak), but usage has changed a lot and our current plans weren't built for this.

> So we're looking at different options to keep delivering a great experience for users. We don't know exactly what those look like yet - that's what we're testing and getting feedback on right now.

> When we do land on something, if it affects existing subscribers you'll get plenty of notice before anything changes. Will hear it from us, not a screenshot on X or Reddit.

https://x.com/TheAmolAvasare/status/2046724659039932830

---

Personally I love how they have increased everyone's quotas to counteract the Opus 4.7 tokenizer change a few days ago, but are immediately regretting it and trying to cut off subscription users.

If the subscriptions are unprofitable, then just communicate honestly, raise the price or lower limits for new subscribers transparently, and grandfather in existing users. That's what GLM coding plan is doing and it works fine for them. Don't ruin your reputation with opaque messaging and hidden changes. Lol

Comment by rideontime 1 minute ago

If it’s just a “test,” why did they update the documentation?

Comment by wrxd 6 minutes ago

What does it mean that they’re running a test? If you’re one of the unlucky 2% you need to pay more?

Comment by altitudinous 8 minutes ago

Chickens have come home to roost. Someone had to pay for the servers and the debt, and its us!!

Comment by whythismatters 1 hour ago

Hey, I'm a pro, and I feel genuinely insulted. I could consider going back to Claude Desktop + MCP, but I'm getting tired of this telenovela, and will probably cancel my sub and take my business elsewhere.

Comment by thebiblelover7 2 hours ago

Previous page, when Claude Code was included:

https://web.archive.org/web/20260421141017/https://claude.co...

Edit: fixed the url thanks to scq

Comment by jamietanna 2 hours ago

> The Wayback Machine has not archived that URL.

Might have been taken down?

Comment by scq 1 hour ago

There seems to be some JS on the page that messes with the URL. Try this one: https://web.archive.org/web/20260421141017/https://claude.co...

Comment by ykl 1 hour ago

At least for me Claude Code is still working on my Pro plan. I don't know if that's because the change simply hasn't propagated all the way through their systems yet (the change is now up on the main Claude pricing page and on their support pages, but not on the Claude Code landing page yet), or if it's because existing plans are grandfathered in, or what.

In general Anthropic seems to be pretty bad at clearly communicating what is going on. I have both Claude Pro for Claude Code and ChatGPT Plus for Codex, and lately I've been reaching for Codex first more and more often... at least for the hobby stuff I'm using Claude/Codex on, they seem pretty much equivalent in terms of practical capability/usefulness.

Comment by barbazoo 1 hour ago

How long until OpenAI remove Codex from their cheap plan?

Should we instead use a generic coding agent with a particular model and just pay per token?

Comment by zaptheimpaler 1 hour ago

This just made me gamble on a yearly subscription for Pro, hoping they will grandfather in existing customers..

Comment by angry_octet 59 minutes ago

Please report back if they send you a Dear John email.

Comment by mmcconnell1618 1 hour ago

Anthropic clearly doesn't understand that customers see their brand as "Claude", Google's brand as "Gemini" and OpenAI's brand as "ChatGPT." They have so many plans and exclusions that they risk customer confusion. I was surprised when I was pay $200/month for Claude Code, finding it super helpful, and then I had to pay separately to get API access for an experiment. Why are so many parts of "Claude" separate from each other, especially on a $200/month subscription.

Anthropic better get this sorted out with a proper product manager and marketing or they risk customers jumping to easier to understand platforms that are good enough.

Comment by abeindoria 12 minutes ago

>or they risk customers jumping to easier to understand platforms that are good enough.

https://www.anthropic.com/news/anthropic-raises-30-billion-s...

I reckon they'll be fine. Not agreeing or disagreeing with you, but they have enough customers who won't leave.

Comment by robertkarl 54 minutes ago

That also was really opaque to me RE: API access. I initially thought at $200/month I could get whatever I needed. I eventually set up a OpenAI API with a few bucks to try what I wanted to.

Comment by dv_dt 1 hour ago

I predict this may get reversed as it would be a huge opening for glm, kimi, and qwen offerings. I'd switch instead of upgrading to Max

Comment by dd8601fn 1 hour ago

Do they have their own cli agents or just the api inference services?

Comment by jmcodes 1 hour ago

I don't think they do but you can always use OpenCode or Pi Agent.

Comment by hannahstrawbrry 1 hour ago

very easy to configure claude code to route to GLM as well.

Comment by charcircuit 56 minutes ago

Moonshot AI has Kimi Code and their $20 per month plan had a lot more than Anthropic's (before 4.6 and the other changes to eat up your limit faster).

Comment by skeledrew 1 hour ago

Time to do research.

Comment by tacker2000 1 hour ago

Funny, I just signed up for Pro a couple hours ago, to check how Claude Code works using this plan, instead of using my API keys.

I got rate limited after about 30mins of coding and was thinking, who the hell i going to work like this?

So they really seem to be running into extreme capacity issued now.

Comment by skeledrew 1 hour ago

This is a joke, right... right??

Comment by netsec_burn 24 minutes ago

I can't even sign up for Max (last tried yesterday), their credit card processor has issues.

Comment by UncleOxidant 1 hour ago

I don't see it mentioned in the Max plan there either.

Comment by dallen33 1 hour ago

They should allow existing Pro plan users to keep using Claude Code.

Comment by Kaotique 48 minutes ago

They will lose the individual subscribers for sure. My day job can pay up to the roof for ai access in this climate but personally I cannot.

Comment by vehemenz 12 minutes ago

Believe me, plenty of "day jobs" are already stretching to pay for $20/mo for their users.

Others in non-tech sectors are forced to use Copilot. Who knows what I would pay for a usable LLM out of my own pocket. Probably more than $200.

Comment by tiberius_p 1 hour ago

It works for me at the moment on the pro plan. Is there a grace period until they enforce the new pricing?

Comment by UncleOxidant 1 hour ago

I would hope that we'd be grandfathered in since we signed up with the expectation that we could use it in Claude Code. I could see where maybe that might lead to problems down the line where they do some kind of update and "forget" that people who signed up before a certain date were supposed to be grandfathered in.

Comment by ryanmcgarvey 54 minutes ago

Everyone that is upset about this should take note: you are not a (coding) customer at $20/mo. Their coding customers spend thousands per month (week!) on claude and it's growing faster than they can keep up with (source: I'm one of them, and I know many other like me. We're budgeting 10-20% of engineering salary spend on tokens). It sucks to no longer be able to code on the cheap anymore, but don't fool yourself into thinking you have any leverage here.

Comment by vehemenz 40 minutes ago

I agree about the leverage point, but it was definitely possible to be a coding customer at $20/mo before, especially with Sonnet.

Comment by nickthegreek 50 minutes ago

My leverage is i’m canceling my plan. Openai gives me codex+chatgpt for my $20. I use me claude code sparingly, but I enjoyed it and it worked great when I did. Access to it was a reason they got my money a few months ago and it’s been a shit show since.

Comment by ed 2 hours ago

This makes sense given Anthropic’s recent downtime and resource constraints.

Opus 4.7 consumes tokens at a faster rate and folks were complaining that the Pro plan included too few credits for real work.

And Anthropic now allows `claude -p` (which invokes Claude code) for 3rd party agents like OpenClaw, which consume far more tokens by running autonomously, 24/7.

Comment by sama004 1 hour ago

only if it actually improves the downtime, people were expecting the same when they revoked openclaw access but that didn't change anything

Comment by cambaceres 1 hour ago

That’s too bad, I just purchased a one year pro plan for my dad just for him to play around with CC when he retires next week.

Comment by 1 hour ago

Comment by 1 hour ago

Comment by civvv 1 hour ago

Does this mean that for enterprises using per-seat pricing, only the $100 premium seat gets access to claude code?

Comment by vict7 1 hour ago

Team plan shows “Claude code” in a main bullet point still. Which would indicate it is part of the team plan regardless if it has premium seats or not.

But it seems this is all in a state of flux.

And there’s the lovely asterisk at the bottom:

> Prices and plans are subject to change at Anthropic's discretion.

Comment by 1 hour ago

Comment by npunt 1 hour ago

No particular opinion on this change, but generally pricing is a great way to separate dabblers from serious users. There isn’t a great deal of value in dabblers or what they produce, I imagine that training data isn’t worth much relative to the pro users. Similar pricing story with $100 yearly price for Apple developer accounts that people complain a lot about. The reality is if you’re serious about making something, these costs are pretty cheap.

The folks hurt most by this are serious people in developing countries and young people starting out. Occasionally a dabbler turns into a serious user but I imagine that’s far less likely than people wish it were.

The value to companies who make these changes is they don’t have low value users or low value contributions to worry about, which has its own not insignificant overhead. In the age of AI slop everywhere we’re likely to see a lot more attempts to separate the wheat from the chaff.

Comment by vehemenz 20 minutes ago

The dabbler/serious user distinction isn't the only framing here.

Assuming this limitation applies to team seats in the same way, at $20/mo, businesses could afford to have everybody on the plan. Plenty of folks write only a few hours of code per day—or even per week in their job. These are still professionals, not dabblers.

Comment by 1 hour ago

Comment by numbers 1 hour ago

does anyone have recommendations on replacing CC with something else for around $20-30 / month?

Comment by 2001zhaozhao 44 minutes ago

Huh? I just don't understand why they're doing this. Feels like shooting themselves in the foot, given that Claude's individual subscribers are a large part of who is introducing all their enterprise customers to them. Plus removing access is never good for public perception.

Comment by Xunjin 1 hour ago

Is this confirmed?!

Comment by fuomag9 1 hour ago

I'm asking for a full refund of my plan via amex if this actually happens. Fuck them.

Comment by tayo42 1 hour ago

Vibe coded ui bug?

That sucks, I guess I'll cancel my Claude account. Not paying 100 dollars. That's crazy

Comment by DeathArrow 1 hour ago

I'm very happy with GLM 5.1, MiniMax M2.7 and Kimi K2.5. My wallet is happy, too.

Comment by HDBaseT 1 hour ago

[dead]

Comment by guelo 1 hour ago

This is more ethical than what they've been doing, trying to keep those subscribers but limiting them to the point it's become unusable. But it's also kneecaping themselves because they'll miss out on any innovation and hype coming out of the hobbyist community.

Comment by werd_eithw 1 hour ago

Their chat bot claims that pro users still have access to Claude Code.

Comment by aenis 1 hour ago

"You are absolutely right!"

Comment by quietsegfault 1 hour ago

Trying to chat with "fin" is like trying to argue with a bowl of congealed oatmeal.

Me: Why is your website saying Claude Code is not included in Claude Pro subscriptions?

"Fin", the slow, dopey AI agent: That’s confusing, but it usually comes down to what “Claude Code” means in that context. Claude Pro does include Claude Code (the Code tab in the desktop app, and Claude Code access for individuals).

What Pro does not include is API access via the Claude Console. Those are separate products: Pro is for chat, and the Console is for building apps with the API.

So if the website is saying “not included,” it’s likely referring to Console/API access, not the Claude Code feature itself.

Did that clear up the confusion?

Me: No. It clearly states on the pricing page that Claude Code is not included.

Fin: That’s frustrating, <NAME>. The key detail is that Claude Code is included in Claude Pro, but API access via the Claude Console is not.

So if the page you’re looking at says “Claude Code is not included,” it’s almost certainly referring to Console/API access (the developer platform), not the Claude Code feature itself.

If you tell me the exact URL or screenshot of the page that says that, I can confirm which “Code” it’s talking about.

Was that explanation helpful?

Me: https://claude.com/pricing

Fin: On https://claude.com/pricing, Pro does include Claude Code. It’s listed right there under Pro’s “Everything in Free, plus” bullets: “Includes Claude Code.” So if you’re seeing “not included” somewhere else on that page, it’s likely referring to something different than the Claude Code feature. The one thing Pro does not include is API access via the Claude Console (that’s a separate product).

Also, the Code tab in the desktop app requires a Pro (or Max/Team/Enterprise) subscription, and it may not show for everyone yet since it’s still rolling out.

Does that clear things up for you?

Me: there is clearly an "x" at this page. escalate to a human immediately.

and then the cycle continues. I'm cancelling my Anthropic subscription, sick of worrying about limits and getting banned and simply awful experience.

Comment by menthe 1 hour ago

[dead]

Comment by wilg 1 hour ago

People really have to internalize that these things are expensive to run, and that there isn't enough compute to go around, like actually for real for real, which is likely the source of this. My guess is its a temporary new sign up pause.

Comment by alxhslm 1 hour ago

Annoying, signed up for a personal pro account a couple of weeks ago. No way I’m going to spend $200 just for a few personal projects.

Comment by vehemenz 18 minutes ago

For $20, it seems like a no-brainer to switch to Codex.

However, if you think you'll need the extra capacity of Max, it's $100, not $200.

Comment by dandaka 1 hour ago

no, most likely you will try codex and get more value (as I did)

Comment by wilg 1 hour ago

Related perhaps to GitHub pausing signups for Copilot? https://github.blog/changelog/2026-04-20-changes-to-github-c...

Comment by nkzd 1 hour ago

Meh, $20 Codex is better at this moment anyway.

Comment by verdverm 2 hours ago

I just cancelled my plan, but still have access to Pro and Code apparently until my cycle would have renewed. Hopefully they get a clear signal from this, especially if more of us cancel with the intention to sign back up should they reverse this decision.

Comment by jryb 1 hour ago

I’d be surprised if they’re running at less than 100% capacity after this. It’s just too useful to too many people for whom an $80/month increase is immaterial (I speculate)

Comment by wasabinator 1 hour ago

The enshitification intensifies.

Comment by woeirua 1 hour ago

[flagged]

Comment by pluc 1 hour ago

I posted this question two weeks ago: "What is your plan when the AI you have implemented throughout your company changes the results you've come to trust?" (https://www.theregister.com/2026/04/06/anthropic_claude_code...).

Since then, I had to add:

"or won't let you log in?": https://github.com/anthropics/claude-code/issues/44257

"or makes stuff up?": https://dwyer.co.za/static/claude-mixes-up-who-said-what-and...

"or when it's down?": https://status.claude.com/incidents/6jd2m42f8mld

"or when you get banned?": https://bannedbyanthropic.com/

"or installs spyware?": https://www.thatprivacyguy.com/blog/anthropic-spyware/

And this is all exclusively about Anthropic. It's insane. On any other tech, there would be a consensus to wait until it's stable, but not AI - we go full throttle when it's AI.

Genuinely curious how people who have implemented this in serious companies are answering these questions, because my answer is to keep it the fuck out.

Comment by vicchenai 1 hour ago

Saw this coming eventually. $20/month for autonomous agents running 24/7 was clearly not sustainable at API pricing. The part that's surprising is there's still no official announcement - just a quiet page edit.

Comment by moregrist 1 hour ago

The $20/mo plan never supported 24/7 autonomous agents. With Opus 4.5 and 4.6 I would hit resource limits after a reasonable amount of work, which corresponded to a variable amount of wall clock time.

This makes me think either they’re severely resource constrained and need to focus on “high value” customers, they’re bleeding money on inference, or their sales and marketing team is incompetent.

Regardless, this feels like a pretty big rug pull. Especially without a phase-out period and a real announcement. As someone using Claude Code on a personal hobby project to get a better feel for its capabilities, I’m not sure what to do now. I can’t justify the $100+/mo plans for a hobby project.

My choices are then:

  - Code this project by hand, which would be fun but defeats the point of this being my agentic coding project.

  - Find another model and use Codex or OpenCode or whatever.

  - Put the project on a shelf till this shakes out.
Fun times.

Comment by skeledrew 1 hour ago

> running 24/7

This was never the case though. There's a per week and per 5 hour quota. If you exhaust either you have to wait for the reset. What they're doing makes no sense.

Comment by boogerbuttcheek 1 hour ago

Choosing to do it quietly instead of letting everyone know is actually not that surprising.

Comment by skeledrew 57 minutes ago

And yet they're very aware that Hacker News, etc exists and so the awareness and backlash would be instant. It's like they want to get a lower rating from the community. Maybe that's their solution for the resource issue: make enough people mad so they abandon their subscriptions.

Comment by 1 hour ago

Comment by ppetty 1 hour ago

Wonder where this leaves folks who paid the annual rate? Here’s what Claude said:

https://claude.ai/share/1a4293bd-b2d4-41b7-a887-eb42b3ae8b6e

“ The standard answer here is no — Anthropic does not typically refund the unused portion of annual plans , and annual subscribers won’t see prorated refunds, retaining access for the full remaining period instead. That said, your situation is a bit different — you’re not just canceling, you’re canceling because a feature you paid for was removed. That’s worth contacting Anthropic support directly about. Their support team can check your refund eligibility , and this kind of material change to the plan is exactly the case where a support escalation could go differently than a standard cancellation. You can reach them through the in-app support messenger at support.claude.com or via the thumbs-down feedback button. I’d recommend explaining specifically that Claude Code was a factor in your annual plan purchase. ”