Hello NVIDIA Support Team,
I am trying to use NVIDIA NIM APIs for personal development and learning.
My API key is active, and:
GET https://integrate.api.nvidia.com/v1/models
returns HTTP 200 successfully and lists the available models.
However, requests to:
POST https://integrate.api.nvidia.com/v1/chat/completions
hang and eventually time out with 0 bytes received.
I tested this directly using curl with multiple models, including:
- openai/gpt-oss-20b
- z-ai/glm-5.3-flash
The API key generation page does not provide an option to enable “NVIDIA Public API Endpoints”.
Could you please check my Personal Organization and enable Public API Endpoints access if required?
Use case: personal learning, development, and API testing.
Thank you.