# Error 504 when calling the model through api

**URL:** <https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655>\
**Category:** Access/Accounts\
**Tags:** nim\
**Created:** [November 26, 2025, 5:36am UTC](https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655 "2025-11-26T05:36:24Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![aaronfeng.lw14](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@aaronfeng.lw14](https://forums.developer.nvidia.com/u/aaronfeng.lw14)\
**Post date:** [November 26, 2025, 5:36am UTC](https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655/1 "2025-11-26T05:36:24Z")

</div>

Is there anyone also suffering from unable to call the model? Even using the demo code with api key gave the same result error 504 ( as I didn’t find information about where can i check the status of the NIM service, im not sure whether its down for now or what. Tried diffierent account and re-generating the api key. not working. Any update will be appreciated. Thx

---

<div class="post-metadata">

**Author:** ![neal.vaidya](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/neal.vaidya/32/256893_2.png) [@neal.vaidya](https://forums.developer.nvidia.com/u/neal.vaidya)\
**Post date:** [December 12, 2025, 9:47pm UTC](https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655/2 "2025-12-12T21:47:06Z")

</div>

Hi @aaronfeng.lw14, which model was this? Are you still seeing the 504 error?

---

<div class="post-metadata">

**Author:** ![aaronfeng.lw14](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@aaronfeng.lw14](https://forums.developer.nvidia.com/u/aaronfeng.lw14)\
**Post date:** [December 13, 2025, 5:53pm UTC](https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655/3 "2025-12-13T17:53:16Z")

</div>

hi @neal.vaidya , sorry for missing the information, it was [yentinglin](https://build.nvidia.com/yentinglin)/llama-3-taiwan-70b-instruct, i having using it after I found its just the specific model keeps failing so im not sure what is the current status. Thank you for looking into it.

---

<div class="post-metadata">

**Author:** ![abodhankar](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/abodhankar/32/382649_2.png) [@abodhankar](https://forums.developer.nvidia.com/u/abodhankar)\
**Post date:** [December 15, 2025, 8:26pm UTC](https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655/4 "2025-12-15T20:26:30Z")

</div>

Hello @aaronfeng.lw14 Could you re-confirm if you are still facing this issue? If not, will have to re-deploy the model.

---

<div class="post-metadata">

**Author:** ![aaronfeng.lw14](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@aaronfeng.lw14](https://forums.developer.nvidia.com/u/aaronfeng.lw14)\
**Post date:** [December 20, 2025, 2:54am UTC](https://forums.developer.nvidia.com/t/error-504-when-calling-the-model-through-api/352655/5 "2025-12-20T02:54:40Z")

</div>

Hi @abodhankar , i tested the model with sample code on the model page as follow, the problem still exist, ty.

openai.InternalServerError: Error code: 504

```auto
from openai import OpenAI

client = OpenAI(
base_url = “https://integrate.api.nvidia.com/v1”,
api_key = “”
)

completion = client.chat.completions.create(
model=“yentinglin/llama-3-taiwan-70b-instruct”,
messages=[{“role”:“user”,“content”:“cheese burger”}],
temperature=0.5,
top_p=1,
max_tokens=1024,
stream=True
)

for chunk in completion:
if chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end=“”)

```