Hello NVIDIA Support Team,
I am using NVIDIA NIM with a Personal Organization for personal development and testing.
My API key is active and valid.
What works:
GET https://integrate.api.nvidia.com/v1/models returns HTTP 200.
What fails:
POST https://integrate.api.nvidia.com/v1/chat/completions returns HTTP 410 Gone.
In my NGC Personal Key configuration, the “Public API Endpoints” service is not available under “Services Included”.
Organization type: Personal / Individual
Could you please verify my account and enable the Public API Endpoints permission for my organization?
Use case: personal AI development, testing, and integration with my own application.
Thank you.
Hello NVIDIA Support,
I am using NVIDIA Build with a Personal Organization for personal development and testing.
My API key is active and valid.
What works:
GET https://integrate.api.nvidia.com/v1/models
returns HTTP 200 and lists the available models, including:
-
z-ai/glm-5.3
-
z-ai/glm-5.3-flash
-
google/gemma-4-31b-it
-
openai/gpt-oss-20b
What does not work:
POST https://integrate.api.nvidia.com/v1/chat/completions
The request either times out after 60 seconds or returns HTTP 404, depending on the model.
I also verified that:
When I try to manage/update my API key authorization in NGC, the page shows:
“Oh No! An Error Occurred”
I also cannot find “Public API Endpoints” under Services Included for my Personal Organization.
Could you please check whether the NVIDIA Public API Endpoints entitlement is enabled for my Personal Organization and enable it if necessary?
Thank you.