Subject: Request to Enable Public API Endpoints for Personal Organization
Hello NVIDIA Support Team,
I am experiencing the same issue reported in this thread and would appreciate your help verifying my account’s inference permissions.
I generated an API key through NVIDIA Build. The GET https://integrate.api.nvidia.com/v1/models endpoint works successfully and returns the available model catalog. However, inference requests to POST https://integrate.api.nvidia.com/v1/chat/completions fail with HTTP 404 errors.
When testing moonshotai/kimi-k2.6, the response included the error Function ... Not found for account. I also encountered inference failures while testing the NVIDIA Build Playground.
I am using a personal organization for personal development and learning. Could you please verify whether my organization has the required Public API Endpoints permission enabled and whether there are any account-specific restrictions or current service issues affecting inference?
I would also appreciate confirmation of which models are currently available for inference with my account.
Thank you for your assistance.