Comment by satvikpendem
5 days ago
Cursor, since Grok 4.5, has had an incredible deal for frontier level models, their subscription now goes way further than OpenAI or Anthropic. Even on their lower tier plans you can use a lot tokens on their of their first party models (Grok and Composer) and not really run out comparatively. Combine them with an orchestrator and implementor type setup and it goes even further.
>their subscription now goes way further than OpenAI or Anthropic.
Until it doesn't...
Honestly, this entire OpenAI reset credit fiasco this past week has convinced me to rip off the Codex and Claude Code bandaids and start building my own proper Pi Coding Agent running models that I select and pay for on openrouter.
And I am feeling a lot better about it now that I've finally got it working.
>Until it doesn't...
I don't get the point of this. We all seem to agree that these companies have almost no moat, if one stops being a good deal, you can switch to another. That doesn't invalidate the existence of a deal that is currently good.
No, it doesn't.
My point was that chasing deals like this is just kicking the can down the road. You're going to have to reckon with harsh price increases sooner or later.
So I have resolved to avoid that future-dreading and fixed it, basically.
2 replies →
switching cost is something you then have to pay everytime the deal changes.
the rest of the comment is about moving from expensive switching costs of what harness you are using to having the difference be closer to changing some config in openrouter
But still for US frontier you're paying 10-20x more per token compared to their limited subscriptions. For China frontier you'll be good though, and that might be the future anyway.
Grok is cheaper vs real Chinese frontier aka kimi. Sponsored or not.
2 replies →
Relying on a single frontier model to just zero-shot all the work is so 2025.
Deepseek V4 Flash 0731 is surprisingly capable and cheap. [0]
Checkout pi coding agent. You can create as many different sub-agents as you wish, to specialize and understand and tackle or pass off any problem you like. It's refreshing, really. I feel like a coder in control again.
[0] https://arcprize.org/results/deepseek-v4-flash-0731
An economist walks past a hundred dollar bill on the ground because someone would've picked it up already if it were real.
> Honestly, this entire OpenAI reset credit fiasco this past week
Huh, what's happened? I'm on the 20x plan and haven't noticed any fiasco, what went down exactly?
Nothing really, when model usage goes up they do a credit. They did two last week.
10 replies →
Can you explain what you mean? These days courtesy of an addictive reset game OpenAI is playing, I can't find anything with frontier intelligence that's more cost efficient...
If they didn’t constantly reset, they’d be about the same as Anthropic.
Right now, I find that Grok offers better value, uses fewer tokens per turn, and makes better code. I haven’t tried Cursor because I don’t want to change editors again, but maybe I should try it…
That is not true; GPT is the most reasoning efficient model family on the market.
2 replies →
Are there any projects that track how much usage of each model translates to how much percentage drop in weekly/5hr windows?
4 replies →
How does Grok 4.5 compare to Opus >= 4.8 though?
I'm willing to pay 2x for a 10% smarter model. Intelligence matters that much (because 10% smarter probably saves, on average, several hours of human time).
It's a bit worse.
I haven't tried so it's pure speculation based on benchmarks, but I'd assume Grok 4.6 is around Opus 4.8 in real world use, but clearly below Opus 5.
I've found Fable 5 to be so much better than 4.8.
For building a full stack custom CRM and media pipeline tool with video conversion, transcription, and indexing. Supabase, AWS, Meili, NextJS, GCS - lots of surfaces and planes.
4.8 basically couldn't do it, I abandoned the project as the fallback was, "current business processes".
With F5 it's been 4 weeks and almost ready for production release.
2 replies →
Grok is $2 in and $6 out. 4.8 is $5 in and $25 out.
It’s not as quite as smart as opus 4.8 but it’s close and x4 the cheaper.
I believe they are the only western provider that has Kimi K3 on a subscription plan today as well. I would love to ditch Anthropic and be on Kimi if there were a subsidized plan like that with ZDR
Opencode have it in their subscription
I believe it's one of the models you have to go in to your settings on and enable Chinese providers for to use. Could be mistaken. I wish there was a clear list on this.
6 replies →
GitHub Copilot does have Kimi K3.
There seems to be something strange going on with how it plays with the GHCP harness: I've experimented on a variety of inputs (code, plain text, literature search), and more than half the time it falls into an infinite text/tool call loop a la GPT-2. Which is a bit spooky as you're still being billed for those infinite loops! But when it works it works, and responses do seem a good deal cheaper than OAI/Anthropic equivalents, so hopefully they'll get it ironed out.
What’s the multiplier? GH copilot nerfed their product so badly that I unsubscribed.
3 replies →
I’d love a subsidized Kimi subscription too. The official Kimi subscription is always out of stock and doesn’t have great limits, while the K3 allotments on OpenCode and Cursor don’t seem to last very long either.
You can apply to join the Kimi subscriptions. I clicked join on the $20/m plan and got in the same day.
Apparently 5x usage when using Kimi Code too.
kimi k3 credits end in just a few sessions. Only Grok models allow generous use in Cursor Pro/+
you can use Kimi K3 on the typed++ model tier: https://typed.cloud
Kimi is expensive . Cursor with subscription is cheaper , grok 4.5 per task paid per tokens ( no subs ) is also cheaper .
If you willing to share to no zdr, meta is waaaaaay cheaper vs Kimi.
With recent offerings from spacex and meta , I hardly imagine why would you pay money to any Chinese vendor it’s not as cheap and it’s not as intelligent neither .
Maybe deepseek is an exception , but it’s only good for narrow use cases that probably goes into modal.com and other gpu + fine tune me easy vendors , not vanilla dumb but cheap model .
GabAI has KimiK3
Goes even further to exfiltrate your data, yeah.
That would be Muse Spark Contributor Tier. 12-21x price reduction at the expense of your digital existence.
I'd be the first model I'd reach for if I was providing a free service to AI gooners though. Serves them both right.
1 reply →
Cursor also allows disabling Grok Fast mode which means tokens last forever. Fast is great tho, but nice to have the option.
When I last used Cursor their subscription covered usage of ~$20 per month. Have they switched to a subsidized subscription model like ChatGPT and Claude?
Subsidized for their own models now, plus 20 dollars of API credit for non first party models.
The value in their subscription is bound to the Cursor agent/software only though correct?
Sounds like you have your final solution