TypingMind Integration

TypingMind is a browser-based chat interface for working with models from multiple AI providers. Its custom model support lets you connect an OpenAI-compatible endpoint, including LLM API.

This guide adds one LLM API model to TypingMind. Repeat the custom model steps for each additional model you want to use.

Prerequisites

An LLM API account with an API key
Access to TypingMind with permission to add custom models
The exact ID and context length of the model you want to add

Use the LLM API models page to choose a model and copy its details.

Add an LLM API Model

Get Your LLM API Key

Open the LLM API dashboard.
Click Create Key to Start.
Copy the new API key. It is shown only once.
Store the key securely, such as in a password manager.

WARNING

Treat your API key like a password. Do not include the real key in screenshots or share an exported configuration that contains it.

Open the Models Page

Open TypingMind.
Select Models in the left sidebar.
Open the Models tab.
Click Add custom model in the upper-right corner.

Open the TypingMind Models page and click Add custom model

Enter the Model Details

Select Create Manually, then enter the model information:

Name: a display name, such as GPT-5.4 Mini via LLM API
Model ID: the exact LLM API model ID, such as gpt-5.4-mini
Context Length: the model's context length, such as 128000

The Name only controls how the model appears in TypingMind. The Model ID is sent to LLM API and must match the ID on the models page.

INFO

Model IDs and context lengths vary. Treat the values above as an example and use the details for your selected model.

Configure Authentication

In the Authentication tab, enter these values:

Field	Value
API Type	`OpenAI Chat Completions API`
Endpoint URL	`https://api.llmapi.ai/v1/chat/completions`
Authentication Type	`API Key via HTTP Header`
Header Key	`Authorization`
Header Value	`Bearer YOUR_LLM_API_KEY`

Replace YOUR_LLM_API_KEY with the key copied from the LLM API dashboard. Keep Bearer followed by one space before the key.

Configure the custom model endpoint and authorization header in TypingMind

WARNING

The screenshot shows the location of each setting but was captured in a development environment. Use the public https://api.llmapi.ai/v1/chat/completions endpoint from the table above, not the internal hostname shown in the image.

Review Capabilities and Save

Open the Capabilities tab and enable only the features supported by your selected model, such as vision, tool calling, or reasoning.
Leave Request Options at their defaults unless the model requires a specific override.
Click Test to verify the configuration.
After the test succeeds, click Add Model or Save.

Incorrect capability settings can make TypingMind send fields that the model does not support. If you are unsure, save the model with the default capabilities first and enable additional features later.

Select and Test the Model

Return to Chats.
Open the model selector above the message box.
Select the custom model you just added.
Start a new chat and send a short message, such as Reply with: LLM API is connected.
Confirm that TypingMind returns a response.

Select the custom LLM API model from the TypingMind chat model menu

A successful response from the custom LLM API model in TypingMind

Requests made with this model are routed through LLM API and appear in your LLM API usage analytics.

INFO

TypingMind stores API keys and chat data in your browser by default. Cloud Sync and proxy features are optional; review your TypingMind privacy settings before enabling them.

Add More Models

TypingMind creates one custom model entry for each model ID. To use another LLM API model:

Return to Models and click Add custom model.
Reuse the same endpoint and authorization settings.
Enter the new model's exact Model ID, Name, and Context Length.
Test and save the new entry.

You can then switch between the models from the chat model selector without changing API keys.

Troubleshooting

401 Unauthorized

Confirm the header key is exactly Authorization.
Confirm the header value starts with Bearer , including the space.
Paste the LLM API key again without quotation marks or leading or trailing spaces.
Verify that the key is active in the LLM API dashboard.

404 or Endpoint Error

Confirm the endpoint is exactly https://api.llmapi.ai/v1/chat/completions.
Select OpenAI Chat Completions API, not the Responses, Anthropic, or Gemini API type.
Make sure the endpoint includes the full /v1/chat/completions path.

Model Not Found

Copy the exact model ID from the models page.
Do not use the display name as the model ID.
Confirm that the API key's IAM rules allow the selected model and provider.

The Model Does Not Appear in Chat

Return to Models and search for the custom model.
Make sure the model is enabled, then reopen the chat model selector.
Refresh TypingMind if the saved model does not appear immediately.

A Capability Fails

Edit the custom model and disable capabilities the model does not support.
Verify support for vision, tool calling, reasoning, and other features on the model's details page.
Start a new chat after changing model capabilities so the request does not reuse incompatible conversation data.

Next Steps

Add other LLM API models with the same endpoint and API key.
Configure model pricing in TypingMind if you want its local cost estimates to match the selected model.
Review usage, cost, latency, and provider routing in the LLM API dashboard.