Hello NVIDIA team,
I’m unable to call models like z-ai/glm-5.2 via the API endpoint
(https://integrate.api.nvidia.com/v1/chat/completions). The request
connects successfully (TLS handshake OK, request body sent), but the
server never returns any response — it hangs until client timeout
(tested with curl, 60s timeout, 0 bytes received).
The same model works fine in the build.nvidia.com Playground using
the same account.
Could you please enable the “Public API Endpoints” permission for
my personal organization?
Account email: operamrx@gmail.com
Thank you for your help.