Hacker News Reader

Comment by hmontazeri | Hacker News Reader

I had the same experience using ds 4.1 last couple of weeks. It’s insanely good for the price. I’m doing mostly web dev it excels at everything I throw at it. The pricing is ridiculous. I canceled my gpt subscription and haven’t looked back hope the pricing stays like that. I almost never need a better model. I still keep my Claude 20$ sub for now but I feel like one more iteration and I won’t need even that anymore I hardly use it

View on HN

If DS4.1 impresses you I would be really interested to see your comparison to GLM 5.3. I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.

GLM 5.3 is very impressive and definitely better, but it also at least 4x the price.

On that note I’ve been subbing in MiMo-2.6-pro when cost is an issue, which is super cheap and also performing really well.

IDK what happened today but I used GLM-5.3 as usual from Ollama cloud and it was so fast it generated entire documents like instantly.

The reasoning and the result document were done after less than 1 or 2 seconds.

Have Ollama suddenly bought GPU capacity?

DS4 (not 4.1) crossed my dont-care threshold and I genuinely stopped paying attention to new models. I'd love to try GLM 5.3 but I just don't see any point in spending the effort any more. I can get passable intelligence for a bargain price either direct from China or from a ZDR EU provider for a small markup. Paying 10x more will not make me 10x happier, it's unlikely to make me even 1.1x happier now I've got some intuition for the natural limits of these models.

I don't even bother checking how much I spent on API any more, its well under $30 over the past 2 months despite daily constant use. Who even needs a subscription at these numbers?

I’m sure it’s more intelligent but the speed of DS is so freaking fast I can’t user slower models anymore

But it also frequently uses massively more tokens for the same task compared to other models which kind of negates the speed.

I'm simply not seeing this

Wallclock time matters and GLM 5.3, even when it is considerably slower (~30 tokens right now vs 100+ on DeepSeek 4) it is quite frequently faster on the same set of tasks overall. Deepseek 4 seems to do the 'Oh, wait' thing just about forever and has a tendency to find irrelevant rabbit holes that it then spends a massive amount of tokens on.

There is also GLM 5.3 Flash

What inference provider are you using?

opencode go

Reply on news.ycombinator.com