Skip to content

NVIDIA Nemotron credentials#

You can use these credentials to authenticate the following nodes:

A single credential covers both deployment modes:

Prerequisites#

For cloud access, create an NVIDIA build account.

For self-hosted access, run a NIM container that exposes an OpenAI-spec compatible endpoint. Refer to NVIDIA NIM documentation for setup guidance.

Supported authentication methods#

  • API key (optional when connecting to a self-hosted NIM that doesn't enforce authentication)

Refer to NVIDIA's build catalogue for the list of available Nemotron models and to the NIM documentation for self-hosting guidance.

Using API key#

To configure this credential, you'll need:

  • A Base URL: the OpenAI-spec compatible endpoint to call. Use the default https://integrate.api.nvidia.com/v1 for build.nvidia.com cloud, or replace it with your self-hosted NIM URL (for example, http://localhost:8000/v1).
  • An API Key: required for build.nvidia.com cloud. Leave blank for a self-hosted NIM that doesn't require authentication.

To generate an API key for build.nvidia.com:

  1. Sign in to your NVIDIA build account.
  2. Open a Nemotron model in the catalogue and select Get API Key.
  3. Copy your key and add it as the API Key in n8n.

To connect to a self-hosted NIM:

  1. Set Base URL to your NIM endpoint, including the /v1 path (for example, http://localhost:8000/v1).
  2. If your NIM requires authentication, paste the token into API Key. Otherwise, leave the field blank.
This page was