> For the complete documentation index, see [llms.txt](https://docs.world3.ai/world3/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.world3.ai/world3/how-to-guides/routerlink/tutorials/how-to-integrate-routerlink-in-lobechat.md). # How to integrate RouterLink in LobeChat {% hint style="info" %} This documentation is provided for informational purposes only and demonstrates how to configure and use our API with third-party AI chat interfaces. Any third-party software, websites, or services mentioned are not operated, controlled, or endorsed by us. {% endhint %} ## Overview This tutorial guides you through integrating **RouterLink**—WORLD3's decentralized AI model routing infrastructure—with **LobeChat**, an open-source multi-modal AI chat platform. ### Purpose RouterLink provides a unified API endpoint that routes requests to multiple AI model providers through a decentralized network. By integrating RouterLink with LobeChat, you gain access to a diverse range of large language models (LLMs) without managing multiple API keys or provider-specific configurations. ### What You Will Learn By completing this tutorial, you will: * **Configure LobeChat** to connect with RouterLink's OpenRouter-compatible API endpoint * **Authenticate** using your RouterLink API credentials * **Add and manage AI models** available through the RouterLink network * **Execute inference requests** through LobeChat's conversational interface ### Prerequisites Before proceeding, ensure you have: * A RouterLink API key (obtain one from the [Quick Start Guide](https://docs.world3.ai/world3/how-to-guides/routerlink/quick-start-guide)) * A web browser with internet access * Basic familiarity with API configuration concepts *** ## Introduction to LobeChat ![](/files/PDZIbyrWRnSaWeiJL5OO) **LobeChat** is an open-source, multi-modal AI chat platform and framework that serves as a unified interface for various large language models (LLMs). Designed as a personal AI "operating system," it enables users to access, orchestrate, and interact with different AI models and tools through a single, cohesive interface. Key features include: * Multi-provider model support via OpenRouter protocol * Plugin ecosystem for extended functionality * Customizable conversation management * Cross-platform accessibility *** ### Step 1: Access LobeChat Navigate to and authenticate using your preferred sign-in method (e.g., GitHub, Google, or email). ![](/files/VSldX0sLq7vP7jAnenMg) *** ### Step 2: Navigate to AI Service Provider Settings 1. Locate and click your **user avatar** in the top-left corner of the interface. 2. Select **"Settings"** from the dropdown menu. ![](/files/3Yc3CzYGbDftY9N8lOye) 3. In the Settings panel, navigate to **"AI Service Provider"** in the left sidebar. 4. Scroll down and locate the **OpenRouter** provider option. ![](/files/2HuCcj8fyn8ljy6O6xNQ) *** ### Step 3: Configure RouterLink API Connection Configure the OpenRouter provider with your RouterLink credentials: ![](/files/dvxSqSX6DHh1gSpvTH8g) #### API Configuration Parameters | Parameter | Value | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------ | | **API Key** | Your RouterLink API key from the [Quick Start Guide](https://docs.world3.ai/world3/how-to-guides/routerlink/quick-start-guide) | | **API Proxy URL** | `https://router-link.world3.ai/api/v1` | After entering the credentials, click the **"+"** button adjacent to **"Fetch Models"** to add a custom model configuration. ![](/files/wXpweVCl7WeWK62UJ3t8) ![](/files/MBETH5c5Xk8jSuVTBQyS) #### Model Registration Specify the model you wish to utilize. This example demonstrates configuration for **Gemini 3 Pro Image Preview**. {% hint style="info" %} For optimal compatibility with the OpenRouter protocol, select models with the Provider designation **"WORLD3 Router North America"**. {% endhint %} ![](/files/Tpi0EhYH12fim1zKyW4y) **Model ID Format:** Retrieve the model identifier from the example code section in your desired model's documentation page. For instance: * [Gemini 3 Pro Image Preview](https://world3.ai/routerlink/Gemini%203%20Pro%20Image%20Preview) Enter the fully-qualified model ID: ``` world3-router-north-america/google/gemini-3-pro-image-preview ``` ![](/files/QgHLIeSa6llgWO6QOeUy) Click **"OK"** to confirm the model configuration. ![](/files/lPBRsvMYFVLZAf7ovYYx) ### Enable the Provider Toggle the **OpenRouter master switch** in the top-right corner to enable the provider connection. ![](/files/dglOpXtH2oORJgO5oW67) *** ### Step 4: Initiate a Conversation 1. Click **"Chat"** in the top-left navigation area to access the conversation interface. ![](/files/AjS1fyXrn37klUVGuTKu) 2. Select **"Just Chat"** and choose your configured OpenRouter model from the model selector. {% hint style="info" %} To streamline model selection, navigate to Settings and disable unused model providers, leaving only your RouterLink-configured models active. {% endhint %} ![](/files/miDboU0uwFNxoxBQpxPT) 3. If you are using the free daily WORLD3 credits, please set the max tokens to ensure the service works properly (for example, set it to 4096).
*** ## Summary You have successfully integrated RouterLink with LobeChat. You can now: * Send prompts to various AI models through RouterLink's decentralized routing network * Switch between different models available on the RouterLink platform * Leverage LobeChat's interface features while utilizing RouterLink's infrastructure For advanced configuration options, model availability, and API documentation, visit the [RouterLink Documentation](https://world3.ai/new-agent/router-link). *** ## Troubleshooting | Issue | Solution | | ------------------------- | ------------------------------------------------------------------------------- | | **Authentication failed** | Verify your API key is correctly copied without leading/trailing spaces | | **Model not responding** | Confirm the model ID matches the exact format from the RouterLink documentation | | **Connection timeout** | Check your network connectivity and ensure the API Proxy URL is correct | For additional support, please open a ticket on [Discord](https://discord.gg/world3). ## Links * Website: * Litepaper: * Genesis Program (Alpha Phase): * Twitter: [@world3\_ai](https://twitter.com/world3_ai) * Discord: [discord.gg/world3](https://discord.gg/world3)