Hello NVIDIA Support Team,
My Personal Organization API key can successfully access GET /v1/models, but every POST /v1/chat/completions request hangs and times out with 0 bytes received.
I reproduced this directly with curl, using multiple models including moonshotai/kimi-k3, deepseek-ai/deepseek-v4.1-flash, and z-ai/glm-5.3, with both stream=true and stream=false.
Network/TLS connectivity to integrate.api.nvidia.com:443 works, and the request is fully sent successfully.
This issue occurs independently of my application or client.
Please check whether the Public API Endpoints entitlement is enabled for my Personal Organization and enable it if required.
Use case: personal development, coding, and API testing.
Thank you.