Claude Code removed from Anthropic's Pro plan
199 points by JamesMcMinn 2 hours ago | 103 comments

robertkarl 27 minutes 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.

reply
jmcodes 21 minutes 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.

reply
operatingthetan 9 minutes 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.
reply
robertkarl 5 minutes 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.
reply
operatingthetan 2 minutes 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.
reply
hank2000 56 seconds ago
how was it? I'm doing this today
reply
elschneider 20 minutes 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.
reply
operatingthetan 19 minutes 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.

reply
elschneider 7 minutes 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
reply
strangattractor 18 minutes ago
Hmmm.. I don't see even one commenter asking Claude about this

Yes! Claude Code is included with the Pro plan. Claude The free Claude plan does not include it — you need at least a Pro subscription ($20/month) or API credits to access Claude Code. Howdoiuseai A few things worth knowing about Pro + Claude Code:

Claude Code draws from the same token budget as your regular Claude usage on subscription plans. Once you hit your limit, you either wait for the window to reset or pay overage at standard API rates. SSD Nodes The Pro plan works well for development, small projects, and learning, though you may hit usage limits with extensive coding sessions. ClaudeLog If you have an ANTHROPIC_API_KEY environment variable set on your system, Claude Code will use that API key for authentication instead of your Pro subscription, which would result in API usage charges rather than using your plan's included usage. Claude

If you find yourself hitting rate limits frequently on Pro, the Max plans ($100–$200/month) offer significantly higher usage caps.

reply
hannahstrawbrry 7 minutes 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"
reply
strangattractor 16 seconds 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:)

reply
ricardobeat 11 minutes 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.
reply
operatingthetan 10 minutes ago
That's just a billing trick.

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

reply
civvv 12 minutes 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.
reply
EstanislaoStan 13 minutes ago
Claude often doesn't know the truth about Claude Code etc. lol
reply
strangattractor 10 minutes ago
I got down voted by 4 people just for pointing that out. lol
reply
wrxd 10 minutes 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

reply
Xunjin 7 minutes 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.
reply
danielspace23 22 minutes 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.
reply
UncleOxidant 11 minutes 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 8 days (more than a week).
reply
zozbot234 14 minutes 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.
reply
dminik 12 minutes ago
Well, if there's one way to show that you're not profitable on inference, this would be it.
reply
chewz 50 minutes 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.

reply
jfrbfbreudh 3 minutes 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.

reply
rustyhancock 6 minutes 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.

reply
whattheheckheck 25 minutes 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

reply
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...

reply
_aavaa_ 2 hours ago
It’s now being explicitly shown as unavailable on the pro plan, scroll down to the comparison matrix.
reply
UncleOxidant 33 minutes ago
Claude Code is a freely downloadable CLI Agent. Why would they not let you use that anymore?
reply
_--__--__ 30 minutes 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.
reply
skeledrew 19 minutes 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.

reply
_--__--__ 14 minutes 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.
reply
skeledrew 2 minutes 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.
reply
foolswisdom 30 minutes ago
Because including it in a plan results in un-metered usage?
reply
UncleOxidant 28 minutes 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.
reply
ezfe 30 minutes ago
You have to login and authorize it? It costs money to process tokens.
reply
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...
reply
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.
reply
sourabhv 9 minutes ago
reply
Larrikin 43 minutes 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.

reply
papichulo2023 36 seconds ago
My company. Medium size, base in Europe. It is paying over 1800 per dev in AI tools. Home users stand no chance.
reply
fg137 20 minutes 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 a given day] on a whim, which Anthropic doesn't necessarily want to do business with.

reply
tayo42 10 minutes ago
> Individual users barely matter.

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

reply
quickthrowman 2 minutes ago
> Why is management at Anthropic trying so hard to ruin their reputation with developers?

I don’t work in software but I’m guessing IC level programmers have between $0-$500 of buying power at work before they have to go ask purchasing or a manager for a PO number.

Anthropic cares about people with millions or billions of dollars of buying power.

reply
mrhottakes 32 minutes ago
they don't care about their reputation with devs, they care about their reputation with people that can write them big fat checks
reply
plutokras 18 minutes 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.

reply
verdverm 40 minutes ago
Also note that they are letting OpenClaw be used again with `claude -p`, so a partial reversal
reply
Xunjin 33 minutes ago
And I thought MS was confused one on how to do pricing and business decisions.
reply
dd8601fn 25 minutes ago
Last I saw they have 21 products or services named Copilot. I think they still win the confusion prize.
reply
Xunjin 10 minutes ago
We should have "The Copilot Award goes to..." Every year for the most confusing product name/lineup
reply
gozucito 27 minutes 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.

reply
thyb23 23 minutes ago
In the “Compare features across plans” section, Claude Code appears to be available only on the Max plan.
reply
civvv 23 minutes ago
If you scroll down, you can clearly see that the Pro plan has an "x" on Claude Code now.
reply
hannahstrawbrry 59 minutes ago
Claude Code page still shows it included with Pro/Max. https://claude.com/product/claude-code
reply
lukeasrodgers 40 minutes 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.
reply
nubinetwork 27 minutes 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?
reply
zaptheimpaler 3 minutes ago
This just made me gamble on a yearly subscription for Pro, hoping they will grandfather in existing customers..
reply
spprashant 16 minutes ago
I can't believe they are yanking tool access instead of just reducing the token quota. To be fair even that would be shitty, 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.
reply
poetril 46 minutes ago
I’ve got nearly 10 months left on my yearly subscription, I wonder what that means for my access.
reply
UncleOxidant 32 minutes 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.
reply
skeledrew 16 minutes 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.
reply
enedil 29 minutes ago
Or also sue in fact or demand refunds.
reply
gbalduzzi 20 minutes 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.

reply
tacker2000 21 minutes 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.

reply
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

reply
jamietanna 51 minutes ago
> The Wayback Machine has not archived that URL.

Might have been taken down?

reply
scq 40 minutes 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...
reply
tiberius_p 12 minutes ago
It works for me at the moment on the pro plan. Is there a grace period until they enforce the new pricing?
reply
UncleOxidant 5 minutes 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.
reply
dv_dt 34 minutes 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
reply
dd8601fn 22 minutes ago
Do they have their own cli agents or just the api inference services?
reply
jmcodes 19 minutes ago
I don't think they do but you can always use OpenCode or Pi Agent.
reply
hannahstrawbrry 2 minutes ago
very easy to configure claude code to route to GLM as well.
reply
skeledrew 10 minutes ago
Time to do research.
reply
cambaceres 8 minutes 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.
reply
pluc 6 minutes 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.

reply
dallen33 33 minutes ago
They should allow existing Pro plan users to keep using Claude Code.
reply
UncleOxidant 17 minutes ago
I don't see it mentioned in the Max plan there either.
reply
skeledrew 35 minutes ago
This is a joke, right... right??
reply
vicchenai 28 minutes 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.
reply
moregrist 11 minutes 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.
reply
skeledrew 12 minutes 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.

reply
boogerbuttcheek 21 minutes ago
Choosing to do it quietly instead of letting everyone know is actually not that surprising.
reply
natrys 2 minutes ago
You are replying to a bot. HN and Reddit is full of these now.
reply
ed 53 minutes 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.

reply
sama004 32 minutes ago
only if it actually improves the downtime, people were expecting the same when they revoked openclaw access but that didn't change anything
reply
civvv 26 minutes ago
Does this mean that for enterprises using per-seat pricing, only the $100 premium seat gets access to claude code?
reply
wilg 24 minutes 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.
reply
quietsegfault 19 minutes 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.

reply
DeathArrow 21 minutes ago
I'm very happy with GLM 5.1, MiniMax M2.7 and Kimi K2.5. My wallet is happy, too.
reply
HDBaseT 6 minutes ago
[dead]
reply
Xunjin 36 minutes ago
Is this confirmed?!
reply
tayo42 12 minutes ago
Vibe coded ui bug?

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

reply
alxhslm 14 minutes 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.
reply
werd_eithw 40 minutes ago
Their chat bot claims that pro users still have access to Claude Code.
reply
aenis 30 minutes ago
"You are absolutely right!"
reply
fuomag9 28 minutes ago
I'm asking for a full refund of my plan via amex if this actually happens. Fuck them.
reply
guelo 27 minutes 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.
reply
wilg 32 minutes ago
Related perhaps to GitHub pausing signups for Copilot? https://github.blog/changelog/2026-04-20-changes-to-github-c...
reply
wasabinator 11 minutes ago
The enshitification intensifies.
reply
nkzd 23 minutes ago
Meh, $20 Codex is better at this moment anyway.
reply
verdverm 52 minutes 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.
reply
jryb 33 minutes 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)
reply
woeirua 39 minutes ago
[flagged]
reply