Hi NVIDIA Team,
I’m trying to use the NVIDIA NIM API ( with an OpenAI-compatible client. My API key is valid — GET /v1/models returns the model list successfully. However, every request to POST /v1/chat/completions returns 404 “page not found”, regardless of which model I try (e.g. meta/llama-3.1-nemotron-70b-instruct, google/gemma-2b, mistralai/mistral-large-2-instruct).
I believe my account is missing the “Public API Endpoints” permission. Could you please enable it for my account / personal organization?
Account Info
- NVIDIA account email: 273078389@qq.com
- Organization / Personal Org: Personal
- API key prefix: nvapi-Gu98cFU67mWpt…
Verification I’ve Done
GET → 200, returns model list
POST → 404 page not found
Request Body Example
{
“model”: “meta/llama-3.1-nemotron-70b-instruct”,
“messages”: [{“role”: “user”, “content”: “hi”}],
“max_tokens”: 50
}
Thank you!