GLM-5.1: Towards Long-Horizon Tasks • Hacker News Board

Re: GLM-5.1: Towards Long-Horizon Tasks

#281

Post by cmrdporcupine » Thu, Apr 09, 2026, 3:46 PM UTC

Lalabadie wrote: post #117

cmrdporcupine wrote: post #54

Earlier quoted context omitted.

Is there any advantage to their fixed payment plans at all vs just using this model via 3rd party providers via openrouter, given how relatively cheap they tend to be on a per-token basis? Providers like DeepInfra are already giving access to 5.1 https://deepinfra.com/zai-org/GLM-5.1 $1.40 in $4.40 out $0.26 cached / 1M tokens That's more expensive than other models, but not terrible, and will go down over time, and…

I use GLM 5 Turbo sporadically for a client, and my Openrouter expense might climb over a dollar per day if I insist. At about 20 work days per month it's an easy choice.

I'm not certain if you're saying it's an easy choice to go with or without the fixed cost coding plan.

I see it's $81/quarter, but it's also not clear to me from what I've seen from people's postings that it actually gives you immediate access to new models as they come and whether there's usage limits and such.

The other advantage of just using API is that one is free to use other less expensive, free, or local models for more routine grunt work stuff

Re: GLM-5.1: Towards Long-Horizon Tasks

#282

Post by joelwallis » Thu, Apr 09, 2026, 6:10 PM UTC

Ms-J wrote: post #196

Z.ai and their GLM models are pretty low quality. I've been testing it for awhile now since it seemed to have potential as a local model. With this new update it still cannot parse simple, test PDFs correctly. It inconsistently tells me that the value in the name field in the document is incorrect, and has the name reversed to put the last name first. Or that a date is wrong as it's in the past/future, when it is not…

So you're saying it's pretty low quality because it failed specifically to parse PDFs?

Re: GLM-5.1: Towards Long-Horizon Tasks

#283

Post by fireant » Thu, Apr 09, 2026, 7:58 PM UTC

adrian_b wrote: post #275

fireant wrote: post #272

Earlier quoted context omitted.

You are just trading opex for capex. Local GPUs aren't free.

True, but this is not only a trade-off between opex and capex. Local inference using open weight models provides guaranteed performance which will remain stable over time, and be available at any moment. As many current HN threads show, depending on external AI inference providers is extremely risky, as their performance can be degraded unpredictably at any time or their prices can be raised at any time, equally unpr…

I agree in principle that more democratic compute = better and third parties introduce additional risk that is outside of your control. That said I just don't see it working economically - either you have an underpowered GPU (4-digit range) at which point you have weak model, or slow model, probably both weak and slow. Or you have expensive GPU cluster, but at that point you also need to consider utilization as you are probably not streaming tokens out 24/7 and at that point TCO is just drastically more expensive for self hosting.

Personally I hope we see a third way - strong open weight models hosted by variety of companies actually competing on price and 9s of availability. That way capex expensive GPUs are fully utilized and users can rent intelligence as a commodity.

There is a very apt analogy to virtual server hosting - hosting vps/shared web is a commodity, it does not make financial sense for most users to host their website on their own physical servers in their basements.

Re: GLM-5.1: Towards Long-Horizon Tasks

#284

Post by Lalabadie » Fri, Apr 10, 2026, 2:04 PM UTC

cmrdporcupine wrote: post #281

Lalabadie wrote: post #117

Earlier quoted context omitted.

I use GLM 5 Turbo sporadically for a client, and my Openrouter expense might climb over a dollar per day if I insist. At about 20 work days per month it's an easy choice.

I'm not certain if you're saying it's an easy choice to go with or without the fixed cost coding plan. I see it's $81/quarter, but it's also not clear to me from what I've seen from people's postings that it actually gives you immediate access to new models as they come and whether there's usage limits and such. The other advantage of just using API is that one is free to use other less expensive, free, or local mode…

For usage that's regular instead of bursty, I suppose the subscription is a no-brainer. Daily agents dev, -claw scenarios, etc.

My total usage might be about equivalent to the sub price, so what I get in return is the absence of quotas for the few periods I need GLM to be available without restriction.

In sporadic use, I wouldn't improve my spend by paying a subscription then also paying metered when I cross the hours/day/week quota, only to leave the rest of the sub unused most of the month.

Re: GLM-5.1: Towards Long-Horizon Tasks

#285

Post by jauntywundrkind » Tue, Apr 14, 2026, 10:00 PM UTC

jauntywundrkind wrote: post #18

bigyabai wrote: post #8

It's an okay model. My biggest issue using GLM 5.1 in OpenCode is that it loses coherency over longer contexts. When you crest 128k tokens, there's a high chance that the model will start spouting gibberish until you compact the history. For short-term bugfixing and tweaks though, it does about what I'd expect from Sonnet for a pretty low price.

Chiming in to second this issue. It is wildly frustrating. I suspect that this isn't the model, but something that z.ai is doing with hosting it. At launch I was related to find glm-5.1 was stable even as the context window filled all the way up (~200k). Where-as glm-5, while it could still talk and think, but had forgotten the finer points of tool use to the point where it was making grevious errors as it went (burn…

Writing in to say things have been working MUCH MUCH MUCH better for me for a couple days now. Thank you GLM for hearing our cries. Sorry I was so slow in getting back to support with all the trace information they wanted on what I was doing; it was taking me a while to reverse engineer & get opencode to spit that information out.