Hello NVIDIA Team,
My API key can list models, but inference is blocked.
- GET https://integrate.api.nvidia.com/v1/models → 200
- POST https://integrate.api.nvidia.com/v1/chat/completions → 410 Gone
Tested with meta/llama-3.3-70b-instruct and other models, all 410.
This looks like my Personal org is missing the “Public API Endpoints” permission.
Account:
- Email: 1776795943@QQ.COM
- Org: Personal
- Key prefix: nvapi-U1uZEpu-i…
- Region: China (+86)
Only for personal, non-commercial learning. Could you please enable it?
Thank you!