# How to integrate RouterLink in TypingMind

{% 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 <a href="#overview" id="overview"></a>

This tutorial guides you through integrating **RouterLink**—WORLD3's decentralized AI model routing infrastructure—with **TypingMind**, a professional AI chat interface platform.

### Purpose <a href="#purpose" id="purpose"></a>

RouterLink provides a unified API endpoint that routes requests to multiple AI model providers through a decentralized network. By integrating RouterLink with TypingMind, 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 <a href="#what-you-will-learn" id="what-you-will-learn"></a>

By completing this tutorial, you will:

* **Configure TypingMind** to connect with RouterLink's API endpoint
* **Authenticate** using your RouterLink API credentials with custom headers
* **Add and manage AI models** available through the RouterLink network
* **Execute inference requests** through TypingMind's conversational interface

### Prerequisites <a href="#prerequisites" id="prerequisites"></a>

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 TypingMind <a href="#introduction-to-typingmind" id="introduction-to-typingmind"></a>

<figure><img src="/files/IHtRDR3tB6a4UwA10yZ6" alt=""><figcaption></figcaption></figure>

**TypingMind** is a professional, customizable chat interface (UI) that enables users to interact with multiple large language models (LLMs) such as GPT, Claude, and Gemini from a single platform. It offers enhanced features for organizing conversations, managing prompts, uploading documents for context (RAG), and building custom AI agents.

Key features include:

* Multi-provider model support with custom API configurations
* Advanced prompt library and conversation management
* Document upload capabilities for Retrieval-Augmented Generation (RAG)
* Options for personal use, team collaboration, and self-hosting for privacy

***

### Step 1: Access TypingMind <a href="#step-1-access-typingmind" id="step-1-access-typingmind"></a>

Navigate to <https://www.typingmind.com/> and authenticate using your email address.

<figure><img src="/files/NMqRoQUGsUo9AZdg52hG" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/mqCQYPvQK8fJi1sWTzOE" alt=""><figcaption></figcaption></figure>

***

### Step 2: Add a Custom Model <a href="#step-2-add-a-custom-model" id="step-2-add-a-custom-model"></a>

1. Click the **Models** icon in the left sidebar, then select **"Add custom model"**.

<figure><img src="/files/5YfloAGrWJ6LhqTVL48O" alt=""><figcaption></figcaption></figure>

For this tutorial, we will configure **OpenAI's GPT-5.2** model via RouterLink.

***

### Step 3: Retrieve Model Configuration from RouterLink <a href="#step-3-retrieve-model-configuration-from-routerlink" id="step-3-retrieve-model-configuration-from-routerlink"></a>

<figure><img src="/files/rwLyA5WvOD2Gev2n6YHE" alt=""><figcaption></figcaption></figure>

1. Visit the RouterLink model page at [OpenAI's GPT 5.2 model](https://world3.ai/routerlink/GPT%20-%205.2) to access the integration details.
2. In the **Integration Guide** section, locate the source code example and copy the **model** identifier.&#x20;

<figure><img src="/files/PpX0ROwjae3mUwOzIzDO" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/iHcRzmFeiz6ofsO9rAVw" alt=""><figcaption></figcaption></figure>

***

### Step 4: Configure Model Parameters <a href="#step-4-configure-model-parameters" id="step-4-configure-model-parameters"></a>

Enter the following configuration values in the TypingMind custom model form:

<figure><img src="/files/JdM5tvKM13MAJ6M0NnYJ" alt=""><figcaption></figcaption></figure>

#### API Configuration Parameters <a href="#api-configuration-parameters" id="api-configuration-parameters"></a>

| Parameter        | Value                                                   |
| ---------------- | ------------------------------------------------------- |
| **Model ID**     | `world3-router-north-america/openai/gpt-5.2`            |
| **API Endpoint** | `https://router-link.world3.ai/api/v1/chat/completions` |

#### Custom Headers Configuration <a href="#custom-headers-configuration" id="custom-headers-configuration"></a>

Expand the **Advanced** section to configure **Custom Headers**:

| Key               | Value                   |
| ----------------- | ----------------------- |
| **Authorization** | `Bearer <YOUR_API_KEY>` |
| **Content-Type**  | `application/json`      |

{% hint style="info" %}
&#x20;For the Authorization header, replace `<YOUR_API_KEY>` with your actual RouterLink API key. Ensure there is exactly **one space** between `Bearer` and your API key. **Example:** If your API key is `sk-1234abcd`, enter `Bearer sk-1234abcd`
{% endhint %}

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).

<figure><img src="/files/FMPu3p2THqo0RiCEmqIR" alt=""><figcaption></figcaption></figure>

#### Validate Configuration <a href="#validate-configuration" id="validate-configuration"></a>

1. Click the **"Test"** button to verify the connection is working correctly.
2. Upon successful validation, the **"Add Model"** button will become active.

<figure><img src="/files/rAR6FPpowCQtrhujZoIv" alt=""><figcaption></figcaption></figure>

3. After adding the model, set `world3-router-north-america/openai/gpt-5.2` as your default model for convenience.

***

### Step 5: Initiate a Conversation <a href="#step-5-initiate-a-conversation" id="step-5-initiate-a-conversation"></a>

1. Click **"Chats"** in the top-left navigation area to access the conversation interface.

<figure><img src="/files/ipSmVDS7VA76oPEGYvJC" alt=""><figcaption></figcaption></figure>

2. Verify that the newly added model **`world3-router-north-america/openai/gpt-5.2`** is selected in the model dropdown at the bottom of the interface.

<figure><img src="/files/ZJwL6jDQzVUTzojwoyUC" alt=""><figcaption></figcaption></figure>

3. Enter your desired prompt to confirm the integration is functioning correctly.

***

## Summary <a href="#summary" id="summary"></a>

You have successfully integrated RouterLink with TypingMind. 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 TypingMind'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 <a href="#troubleshooting" id="troubleshooting"></a>

| Issue                     | Solution                                                                              |
| ------------------------- | ------------------------------------------------------------------------------------- |
| **Authentication failed** | Verify your API key is correctly formatted with `Bearer` prefix (including the space) |
| **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 endpoint URL is correct            |
| **Test button fails**     | Verify all custom headers are properly configured (Authorization and Content-Type)    |

For additional support, please open a ticket on [Discord](https://discord.gg/world3).

## Links <a href="#links" id="links"></a>

* Website: [https://routerlink.world3.ai](https://routerlink.world3.ai/)
* Litepaper: <https://docs.world3.ai/world3/routerlink-litepaper>
* Genesis Program (Alpha Phase): <https://routerlink.world3.ai/?tab=alphaprogram>
* Twitter: [@world3\_ai](https://twitter.com/world3_ai)
* Discord: [discord.gg/world3](https://discord.gg/world3)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.world3.ai/world3/how-to-guides/routerlink/tutorials/how-to-integrate-routerlink-in-typingmind.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.