# ISSUE GLM 5.2 **URL:** \ **Category:** Models\ **Created:** [July 3, 2026, 7:36am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422 "2026-07-03T07:36:37Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 3, 2026, 7:36am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/1 "2026-07-03T07:36:37Z")
Appear API is returning Internal Server Error when the request is getting higer thant 202k token, please nvidia can fix that or let us know the real context windows limitation instead say 1M ? ---
**Author:** ![levantam.98.2324](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@levantam.98.2324](https://forums.developer.nvidia.com/u/levantam.98.2324)\ **Post date:** [July 4, 2026, 3:16pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/2 "2026-07-04T15:16:35Z")
for real ---
**Author:** ![AnchorInTheWebster](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@AnchorInTheWebster](https://forums.developer.nvidia.com/u/AnchorInTheWebster)\ **Post date:** [July 5, 2026, 10:51am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/3 "2026-07-05T10:51:25Z")
Experiencing the same, happened at 170k. ---
**Author:** ![VMMS1245](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@VMMS1245](https://forums.developer.nvidia.com/u/VMMS1245)\ **Post date:** [July 6, 2026, 1:02am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/4 "2026-07-06T01:02:18Z")
One question, @bozoweed. Are you still experiencing the same issue? From what I’ve seen, you’re not the only one. The real question is: are they going to fix it? Will it stay like this? Or is it even a bug in the first place, or is it intentional? Because if the model is advertised as supporting a 1M token context window, then the expectation is that it should actually provide that capacity, right? I’m asking mostly out of curiosity, since the model is still relatively new on NVIDIA’s infrastructure. I assume they may still be making adjustments or changes. ---
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 6, 2026, 10:46am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/5 "2026-07-06T10:46:36Z")
they can let it like this like they have done with deepseek v4 pro/flash, they are also not accept the 1M context as excepted … it’s nvidia stuff and appear they don’t give a ■■■■ ---
**Author:** ![musicvityca](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@musicvityca](https://forums.developer.nvidia.com/u/musicvityca)\ **Post date:** [July 6, 2026, 12:57pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/6 "2026-07-06T12:57:59Z")
Since yesterday I have only Internal Server Error or Timeout connection when working with model GLM5.2 in every scenario (I use kilocode) ---
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 6, 2026, 5:55pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/7 "2026-07-06T17:55:30Z")
i have keep working on roo-code from my side and still working ( really slow but working ) ---
**Author:** ![musicvityca](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@musicvityca](https://forums.developer.nvidia.com/u/musicvityca)\ **Post date:** [July 6, 2026, 7:18pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/8 "2026-07-06T19:18:59Z")
Do you change settings like connection timeout or api response timeout? ---
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 6, 2026, 8:00pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/9 "2026-07-06T20:00:32Z")
i don’t think i have juste made few change to follow vs-code update ---
**Author:** ![blanco.outsiders](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@blanco.outsiders](https://forums.developer.nvidia.com/u/blanco.outsiders)\ **Post date:** [July 7, 2026, 7:38am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/10 "2026-07-07T07:38:27Z")
Right now it’s unusable, showing error ‘DEGRADED function cannot be invoked’ ---
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 7, 2026, 8:07am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/11 "2026-07-07T08:07:50Z")
maybe we should mail bombing the support to froce them to fix the model 🤷‍♂️ ---
**Author:** ![dracusmorlin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@dracusmorlin](https://forums.developer.nvidia.com/u/dracusmorlin)\ **Post date:** [July 7, 2026, 8:37am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/12 "2026-07-07T08:37:18Z")
Is this the reason it keep getting “message”:“Request failed with status code 400” error on sillytav? ---
**Author:** ![musicvityca](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@musicvityca](https://forums.developer.nvidia.com/u/musicvityca)\ **Post date:** [July 7, 2026, 8:59am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/13 "2026-07-07T08:59:36Z")
I think NVIDIA team works on this because my problem from yesterday was solved since some time. But now “degraded function” is coming)))) May be GLM5.2 change something and nvidia nim team can’t be in time with some wrapper So I guess we have to wait and suffer And communicate there to show our faith in best future :) ---
**Author:** ![levantam.98.2324](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@levantam.98.2324](https://forums.developer.nvidia.com/u/levantam.98.2324)\ **Post date:** [July 7, 2026, 9:54am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/15 "2026-07-07T09:54:59Z")
why it so fast for me ---
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 7, 2026, 9:57am UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/16 "2026-07-07T09:57:12Z")
maybe becaause you are lucky, if it’s so fast you can maybe try to ask them to fix that please 🙏 ---
**Author:** ![levantam.98.2324](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@levantam.98.2324](https://forums.developer.nvidia.com/u/levantam.98.2324)\ **Post date:** [July 7, 2026, 1:35pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/17 "2026-07-07T13:35:43Z")
idk it response time hover around from 1 - 7 second. Also how to ask them to fix? ---
**Author:** ![bozoweed](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/bozoweed/32/275904_2.png) [@bozoweed](https://forums.developer.nvidia.com/u/bozoweed)\ **Post date:** [July 7, 2026, 2:07pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/18 "2026-07-07T14:07:03Z")
using the support email [help@build.nvidia.com](mailto:help@build.nvidia.com) ---
**Author:** ![ser279127](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@ser279127](https://forums.developer.nvidia.com/u/ser279127)\ **Post date:** [July 7, 2026, 4:39pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/19 "2026-07-07T16:39:35Z")
they have to fix the context to 1M but also the others errors , it’s completely broken since early this morning. ---
**Author:** ![sherman.shank](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@sherman.shank](https://forums.developer.nvidia.com/u/sherman.shank)\ **Post date:** [July 7, 2026, 8:36pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/20 "2026-07-07T20:36:39Z")
yes. only 202k context windows. and DeepSeek flash/Pro only 256K context ---
**Author:** ![robinho0d007](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@robinho0d007](https://forums.developer.nvidia.com/u/robinho0d007)\ **Post date:** [July 7, 2026, 9:55pm UTC](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422/21 "2026-07-07T21:55:53Z")
Working fine now so far, thanks for the help and support! [Next page](https://forums.developer.nvidia.com/t/issue-glm-5-2/375422.md?page=2)