Hacker News Reader

Comment by johnmlussier | Hacker News Reader

If you are expecting any sort of usable limits on their subscription plan I suggest adjusting your expectations. I subscribed to $99 a month plan and within 47 minutes with one session (not asking for swarms or anything) was limited by 5-hour quota.

View on HN

Same experience. I had the $19 monthly plan for experimenting and running benchmarks, but it was a uselessly small amount of usage, a single task would blast through the whole five hour limit and a big chunk of the weekly limit. All of the US provider plans are remarkably more generous (though OpenAI plans have gotten a lot stingier lately, where they used to be the most generous).

I don’t agree. I tried the $20 Claude Plan and was able to reach the 5 hour limit in maybe one prompt.

Would you mind sharing that prompt? I'm struggling to even hit 10% of my Claude quota! I don't want more work out of it TBH but I'm interested...

I have been using DS Flash 4.1 pretty heavily. It runs for hours and hours and is pretty cheap.

I realized the other day that I had a $30 a month Claude subscription. So, I fired it up all excited and tried Opus 5.5 on a codebase I was already in with DS. After about 30 minutes I hit a 5 hour limit. The next day I tried again and the same thing happened. And it felt much slower to boot. I was super disappointed.

do you use their proprietary platform API?

and how are costs like for your usual workflows/etc.?

There is a $30/mo Claude subscription?

If you're not paying in USD. ;)

Sounds like the price in Canadian or Australia dollars

DS 4.1 is basically endless, even if you paid for APIs you will hardly touch some prices.

But it's slow.

I don't think I can any longer appreciate any major difference in "intelligence" between models for most tasks but Opus is consistently much faster than competitors at finishing tasks and keeping me in the loop.

Of course excluding ultra code, the you will wait 50 minutes for a minor refactor.

Did you use Fable, set Opus 5.5 to xhigh, or use 'ultracode' / workflows? That's the only way this will happen.

In my experience a single 5 hour allowance in the 20eur Claude plan equals about $5-10 in Deepseek 4.1 Flash API usage. DS is a lot more token hungry and takes 3x-4x longer. The subscription is way cheaper, probably around $200/month worth of DS, just stick to Opus low and Sonnet for most tasks.

It's not just prompt, it's also which model, effort, time of day, fast/flex, etc. This is why people have such different experiences.

Yeah, the $20 Claude plan is stingier than one might like, but not as stingy as Kimi. I think the best $20 subscription deal these days is probably from Google, now that Gemini 4 Argon exists and is an acceptably high quality model for coding. It's got quite generous usage and includes some other Google account upgrades (though I know some people don't use their regular account for Google AI for fear of account suspension or whatever, so the extra storage and other account upgrades are not a useful thing). I can use it pretty heavily without ever running into caps. The $20 ChatGPT plan used to be similarly generous, but no more.

Gemini isn't generous at all 5-10 Argon prompts and that's it.

When I've most recently done the same tasks across multiple providers I have a subscription to, I found the order of generosity of them was something like Gemini->Claude->ChatGPT->Kimi. OpenAI used to be a lot more generous than all of them, but that ended recently, and now it's quite stingy in the $20 plan. What competitive model has a more generous subscription than Gemini?

Opencode Go, if you think DS 4.1 is competitive.

I have a DeepSeek account and almost always use it when I need something with API access. I consider it Good Enough™, if not competitive. I also have a MiMo token plan, though that's weird in that it's not a monthly subscription, it's just a bulk buy of tokens that expire after a year, but still seems to be a pretty good deal on a pretty good model.

It is a LOT more efficient on claude code. Takes forever to run out of credits, and a whole lot of useful code gets generated. The web Ui reconstructs code while claude code just tweaks it.

How long ago was this? The amount of usage they give you for a given plan seems to change over time, and the Claude limits seem to be more favourable recently.

I don't think the limit changed per se, but Opus 5.5 consumes a lot less usage than 5.0 did, so it goes further.

I had the same experience with OpenAI's 20$ one, literally one prompt to do some code analysis, it didn't even complete it.

And that was 6.1 sol xhigh, not astra max..

That's surprising, I had the exact same experience as GP. I dropped my Kimi sub this month, but I'm keeping claude because I can use Opus 4.8 basically endlessly. Even Opus 5.5 doesn't drain the usage that much, though I rarely use it because it refuses to do anything cyber-related.

Was the prompt "Re-implement Call of Duty 4, make no mistakes"?

Welp, that ruins this news for me. I'm glad open models are catching up but if I can't practically run them locally _or_ through a flat fee then it doesn't really help me. I fear API pricing.

This'll end up on opencode go soon enough. $40/month on there gives you a bit more than just "light use"

Don't use frontier models like this for problems that can be solved with flash models, and you'll see API pricing isn't that terrible. Still cheaper than anything with remotely this level of capability 2.5 months ago.

Don’t worry. When SlopenAI and Antslopic run out of VC money, all the models will be equally expensive.

Had a similar experience here. Their limits are very, very low, and ultimately make it not worth subscribing. Can't leverage a good modal if it exhausts its 5-hour budget in 30 minutes.

Paying API prices for Deepseek 4.1 Flash feels like a much better deal at the moment.

It also has the lowest quota of any model on https://opencode.ai/go

I think Kimi just doesn't have the means to subsidize plans.

We really need consumer hardware to catch up so we can run these models locally...

How? I've been running k3.1 Pro with K2.8 preview for codegen (subagents) and I've only used 22% of my weekly and it's been running for 8 hours on a RE project.

Are you using k3 with thinking set to the absolute highest and only using k3 for everything?

Yeah, the plan is far too expensive for what it provides. I wonder if the quota with these new models will be better, but I'll wait for others to try this out before wasting another hundred bucks.

but its not expensive tho ??? it is not subsidize

Yes, if you just look at API pricing, the cost is about on par with its capabilities. The problem is that we all use subscriptions, and when you compare subscription pricing, Kimi is much pricier than pretty much all of their competitors, including Chinese ones.

I tried Claude pro for the first time 3 weeks ago.

At the beginning it was the best coding agent I'd used so far and I'd used the most popular ones and the more niche opencode models.

Within the last week, Usage has fired up at least x3 to x4 times on the same projects and tasks.

Just now, sonnet and opus doubled-down on a game bug even when I provided a video which clearly showed what was wrong.

Something is definitely up.

What about via US hosted data center resellers like Fireworks?

I have the same plan and have never experienced that with K3. I have hit the limit within a 5 hour quota using Swarm, however.

Ya it's not very usable compared to Claude / codex

Yup, insanely low 5-hour limits.

Honestly, use Pi, start the session with K3, design it, store the design + chat history + todo with phases + why + readme then when you are at the time to build do `/model` select deepseek and let it rip!!

You can even make a Pi extension to let it switch models on its own, then tell it to switch to one or the other for a given task. It's not perfect, but it is pretty reliable once you have the instructions dialed in.

Here's mine: https://pi.dev/packages/@arcanemachine/pi-model-switcher

I have mine configured to use a "thinker" model for planning and decision making, and a "doer" model for the easy stuff (digging around the repo, writing code based on the thinker's instructions, etc.).

I run a similar setup, just with different models. I also use herdr, which lets me have the same project worked on side by side by different models, each in its own git worktree.

https://github.com/earendil-works/pi

https://github.com/herdrdev/herdr

Reply on news.ycombinator.com