It's always been clear to me that Cursor's business model of reselling others' APIs had its days numbered. Not necessarily because the providers would pull the plug, but because you wouldn't be able to compete with subsidized plans.
Cursor is already kind of useless for third party models unless you're willing to spend thousands of dollars. It's only worth it if you're going to use mostly grok/composer.
I've never seen a product blow another product out of the water so hard as Claude Code did to Cursor.
I saw that happen culturally. But never saw that much different in performance. And I really dislike terminal development. And their desktop app is really buggy.
Given you can use the same models on both, you're right about performance. However I've found the cross-session context and memory in claude code much more helpful which can lead to better outcomes faster.
Additionally helpful where 2 apps/repos might require running at the same time, e.g. headless web apps, or, for plugin development where the plugin might be a dedicated repo but needs to run in another app to observe changes and make it re-test itself.
I also switched from terminal to the app not that long ago, I don't find it buggy, it has access to a browser which is really helpful.
The tide is turning though. I was using the old non agent view in cursor every day for about a year when I built my startup with it. Then Claude Code blew it out of the water. But since two month or so I much prefer Codex and Cursor with the agent view.
However, what I see cooking at Cursor is way more promising than the others. Things like full system understanding, their own forge, multi-repo support. I'd put them as way more visionary in the Gartner magic Quadrant ;)
what do you mean by 'full system understanding', here? And don't you think that claude and openai are using their own forge as well?
Claude code is a decent harness but then you have to use Anthropic models, which are good but no longer the best bang for the buck.
In particular Haiku 4.5 is rubbish, Anthropic don’t have anything in the cheap/fast part of the market.
For people fortunate enough to still be on a subscription instead of per-token billing this is less relevant, but their time will come.
The cursor model is quite nice because it allows you to switch between cheap and expensive models for different tasks
I think the point is that CC was the first general use, terminal based harness. I think. Now you can use PI, or OpenCode, or whatever, and use any model you like.
Now, I’m no expert, because I was late to the game and have only ever used Pi. But I guess Cursor is some product that’s tied to your IDE? If so, then yeah. That’s just too restrictive. I still love my IDE, but I don’t want it to be my harness too.
Claude Code was very late to the party.
Aider (and probably others) came well before CC.
> Claude code is a decent harness but then you have to use Anthropic models...
Claude Code works with models from other providers too. Anthropic supports this. You can configure some Claude Code environment variables to switch: eg changing ANTHROPIC_DEFAULT_HAIKU_MODEL to point to GLM Flash or Luna, setting ANTHROPIC_BASE_URL to point to api.z.ai, and making ANTHROPIC_AUTH_TOKEN the API key for your alternative provider instead.
Some instructions here:
https://docs.z.ai/scenario-example/develop-tools/claude
That said, I've not actually tried this myself, opting to build my own harness instead. And you don't know what information Claude Code might be sending back to Anthropic about how you use competing models and which models you use. I don't know for sure that they do this, but after hearing about how they used steganography in the date of harness system prompts to identify the user's location, I don't entirely trust Claude Code anymore.
Cursor has a surprising amount of inertia, though, at least where I work.
I've recently moved to a company that uses Cursor, and I'm actually quite fond of it.
I basically never use the editor but the fact that there's a review UI for all the agent work is incredibly helpful.
For me, that makes the models much more usable. I've also been using GPT models a lot, as they're cheaper and less vomit inducing than Claudes text, so this is definitely bad news for me.
Why do people keep insisting that subscription plans are subsidized? They are not. API prices are outrageous, designed to milk enterprise users. They probably have an 80-90% profit margin on subscription plans.
Inference is cheap; Dax once said on a podcast that Opencode has a close to 90% profit margin on the openweight models it provides inference for (at 10x cheaper pricing). Those models are close in size and spec to models from large labs.
OpenAI leaked financial data (2025) suggests this - it has $5.7 billion for marketing which 44% of revenue. It’s hard to explain where these billions go other than into subsidised subscription plans and a free tier.
To provide inference, Anthropic and OpenAI need to also constantly spend resources on training new models.
If either one of them stops doing that, customers will stop using them, because other models will become better.
In other words, there is no point in talking about inference cost in isolation.
Enterprise customers are not getting the subsidized subscriptions so for them the point is moot.
Token reselling stops working when providers literally won't work with you
What about openrouter though?
I will slightly disagree on a small slice: Their harness/instruction makes Opus/Fable so much better to work with.
Honestly, _this_ was their moat more than Composer to me.
If the Opus/Fable harness is superior and it's written using Opus/Fable then it will cease to be a moat. Otherwise the premise for coding using LLMs is essentially untrue.
> Otherwise the premise for coding using LLMs is essentially untrue.
Why? Written by does not mean designed by etc. There's a lot more to it.
Couldn't you just download cursor, not even pay for any account and hook up an Anthropic api key and get that functionality?
I dont know how cursor works. Everytime ive tried to use, its super buggy and has memory leaks that make my very quite PC sound like a jet engine.
Cursor charges the “Cursor Token Rate” for BYOK https://cursor.com/docs/models-and-pricing#cursor-token-rate
No. Its is not for bring your own key.
It is for 3rd party models (which you get double the amount of your sub price as usage).
Of course they wont charge you extra for BYOK. how would they???
You can just pirate Adobe's software and their marketcap is 115.88B.
Alternate take: open source models and model routers are the real bang for your buck. Subsidized plan or not.
I just told my boss to cancel my cursor subscription. My flow is basically Claude/opencode + kyde/vscode for por changes review
Shit, for most things, ive got a dev agent that reads change requests from a GDoc and communicates through email with me. I can develop in my mobile
Agreed. Wrapping token spend is great for pumping your revenue numbers (congrats to them on $60B!), but doesn’t seem sustainable over the long term.
Big reason we built https://boxes.dev around the model harnesses (Codex + Claude Code), so you can bring your own subscriptions.
Surely the days of being able to “bring your own subscription” to a third party platform are also numbered?
On one hand, yes, it doesn't make sense to give out subsidized tokens forever.
On the other hand, subscriptions create lock-in in a way that API pricing doesn't.
I think a more likely end is that subscription value decreases over time because API pricing gets more reasonable, but subscriptions stay because they are a good way of getting money out of people consistently.
Right, subscriptions are not only cheaper because they "create lock-in". They also let you do things like forecast demand and plan your capacity for it, borrow against it sometimes if you need to, and keep somewhat less around because your cashflows are predictable. It is also valuable because it keeps customers around but that's by no means the only reason recurring revenue gets a higher multiple.
This is why "subsidized tokens" is possibly a misnomer. Money at lower variance is worth more than the same money at higher variance. Not "subsidy" so much as reducing risk and passing some of that to a consumer.
I’m not so sure… Claude backtracked on this when they tried it
They played pigeon on discless videogame consoles a time or two, too.
How long have you been in tech, outta curiosity?
Edit: great answer.
> Edit: great answer.
What do you mean by that? If you're being sassy about a downvote then I'll remind you that when you reply to a comment, that person can't downvote your reply. Also this is an account with barely any comments or points, I'm pretty sure they can't downvote at all.