Hello NVIDIA Team,
I’m unable to call any chat completion models via
https://integrate.api.nvidia.com/v1 from my personal
organization account. I would like to request the “Public API Endpoints”
permission to be enabled for my account.
Account details:
- Registered email: 854202677@qq.com
- Organization type: Personal
- API Key prefix (first 10 chars): nvapi-NEKoy
Issue description:
- GET /v1/models returns 200 OK with the full model list.
- POST /v1/chat/completions returns HTTP 410 Gone with an empty body.
- Tested models: deepseek-ai/deepseek-v4-pro, deepseek-ai/deepseek-v4-flash, moonshotai/kimi-k3, moonshotai/kimi-k2.6,
- All requests return 410 regardless of which model is used.
- Phone number verification has been completed on my account.
Request:
Could you please enable the “Public API Endpoints” permission for my
personal organization so that I can access these models through the
public API endpoint? I understand this is a permission issue, not a
rate limit increase request, and I will adhere to the free tier
usage policy.
If any additional information is needed, please let me know.
Thank you for your help!
Best regards,
Leon Wang