lobehub__lobehub/docs/usage/providers/nvidia.mdx

---
title: Using Nvidia NIM API Key in LobeHub
description: >-
  Learn how to configure and use Nvidia NIM AI models in LobeHub, obtain your
  API key, and start chatting.
tags:
  - LobeHub
  - Nvidia NIM
  - API Key
  - Web UI
---

# Using Nvidia NIM in LobeHub

<Image alt={'Using Nvidia NIM in LobeHub'} cover src={'/blog/assetsd8927338578c426b833e5cb57e0b57ec.webp'} />

[NVIDIA NIM](https://developer.nvidia.com/nim) is part of NVIDIA AI Enterprise, designed to accelerate the deployment of generative AI applications through microservices. It offers a set of easy-to-use inference microservices that can run on any cloud, data center, or workstation, with support for NVIDIA GPU acceleration.

This guide will walk you through how to integrate and use AI models provided by Nvidia NIM in LobeHub:

<Steps>
  ### Step 1: Obtain Your Nvidia NIM API Key

  - First, visit the [Nvidia NIM Console](https://build.nvidia.com/explore/discover) and complete the registration and login process.
  - On the `Models` page, select the model you want to use, such as Deepseek-R1.

  <Image alt={'Select a model'} inStep src={'/blog/assets74000cc1bc59ee4a15e8f0304afbf866.webp'} />

  - On the model details page, click on `Build with this NIM`.
  - In the pop-up dialog, click the `Generate API Key` button.

  <Image alt={'Get API Key'} inStep src={'/blog/assetsaf57d31364a41634b10c243ed9b1f8f8.webp'} />

  - Copy and securely save the generated API key.

  <Callout type={'warning'}>
    Make sure to store your API key securely, as it will only be shown once. If you lose it, you’ll need to generate a new one.
  </Callout>

  ### Step 2: Configure Nvidia NIM in LobeHub

  - Go to the `App Settings` section in LobeHub and navigate to `AI Service Providers`.
  - Find the `Nvidia NIM` option in the list of providers.

  <Image alt={'Enter Nvidia NIM API Key'} inStep src={'/blog/assetscad58c557fda04b9379000cbbaa4c493.webp'} />

  - Enable the Nvidia NIM provider and paste in your API key.
  - Choose a Nvidia NIM model for your assistant to start chatting.

  <Image alt={'Select Nvidia NIM Model'} inStep src={'/blog/assets45d90e73abffd7ae7d85808f81827bb9.webp'} />

  <Callout type={'warning'}>
    You may incur charges from the API service provider during usage. Please refer to Nvidia NIM’s pricing policy for details.
  </Callout>
</Steps>

That’s it! You’re now ready to use Nvidia NIM-powered models in LobeHub for your conversations.