Hello NVIDIA Team,
I am trying to access the model deepseek-ai/deepseek-v4-pro via the API (https://integrate.api.nvidia.com/v1). When I make a request using the OpenAI client with stream=True, it runs forever and returns no response (timeout).
The same issue occurs when I try simple curl commands to the chat/completions endpoints. However, listing the models (/v1/models) works fine.
Based on other posts in this forum, I believe my personal organization is missing the “Public API Endpoints” permission.
Could you please enable this permission for my account?
My account details:
- **Registered email address:**thg13@yahoo.com
- First characters of my API key: nvapi-clC0cbxHa
The access is strictly for personal testing and development purposes.
Thank you for your support!