AI Chat Applications

Overview

Most chat apps can connect through their OpenAI-compatible settings. Enter https://api.tokenlab.sh/v1 as the Base URL, paste a TokenLab API key, and choose a current chat model ID.

These settings use Chat Completions. Coding tools that require Responses or another API format have separate integration guides.

Supported Applications

Application	Platform	Notes
Open WebUI	Web, Self-hosted	Supports OpenAI-compatible connections
LibreChat	Web, Self-hosted	Supports custom OpenAI endpoints
LobeChat	Web, Desktop, Self-hosted	Supports custom model providers
Cherry Studio	Windows, macOS, Linux	Supports OpenAI-compatible providers
Chatbox	Windows, macOS, Linux	Supports OpenAI-compatible settings
DeepChat	Windows, macOS, Linux	Desktop client with OpenAI-compatible provider settings
Jan	Desktop, Self-hosted	Local-first app with remote OpenAI-compatible providers
TypingMind	Web, Desktop	Uses a custom endpoint style
NextChat	Web, Self-hosted	Lightweight ChatGPT-style client with base-URL overrides
ChatWise	Windows, macOS	Standard custom provider pattern

Default Connection Values

Field	Value
Base URL	`https://api.tokenlab.sh/v1`
API Key	`sk-your-tokenlab-key`
API Type	OpenAI Compatible

If an app asks for a full endpoint URL instead of a base URL, use:

Chat Completions: https://api.tokenlab.sh/v1/chat/completions

Example App Setups

Self-hosted LobeChat

OPENAI_API_KEY=sk-your-tokenlab-key
OPENAI_PROXY_URL=https://api.tokenlab.sh/v1

LobeChat Cloud

Open Settings → AI Service Provider
Select OpenAI
Enter your TokenLab API key
Set the custom endpoint to https://api.tokenlab.sh/v1

Open Settings → Model Provider
Add an OpenAI-compatible provider
Enter:
- Name: TokenLab
- API Base URL: https://api.tokenlab.sh/v1
- API Key: sk-your-tokenlab-key
Add the models you want to use

Open Settings → AI Model
Choose OpenAI API Compatible
Enter:
- API Host: https://api.tokenlab.sh/v1
- API Key: sk-your-tokenlab-key
- Model: a current chat model ID from TokenLab

Open Settings
Choose Custom Endpoint
Enter:
- Endpoint URL: https://api.tokenlab.sh/v1/chat/completions
- API Key: sk-your-tokenlab-key
Configure the models you want to expose

Open Admin Settings → Connections
Add an OpenAI-compatible connection
Enter:
- Base URL: https://api.tokenlab.sh/v1
- API Key: sk-your-tokenlab-key
Save and select the models you want to expose

Open Settings -> Model Provider
Add an OpenAI-compatible provider
Enter:
- Base URL: https://api.tokenlab.sh/v1
- API Key: sk-your-tokenlab-key
- Model: a current chat model ID from TokenLab
Save and run a test chat

Open Settings -> Providers
Add a remote OpenAI-compatible provider
Enter:
- Provider name: TokenLab
- Base URL: https://api.tokenlab.sh/v1
- API Key: sk-your-tokenlab-key
Select a current TokenLab chat model

Add an OpenAI-compatible endpoint in your LibreChat provider config and point it to:

customEndpoints:
  - name: TokenLab
    apiKey: '${OPENAI_API_KEY}'
    baseURL: 'https://api.tokenlab.sh/v1'
    models:
      default: ['your-tokenlab-model-id']
      fetch: false

Choose a Model

Copy a current chat model ID from the Models page. Capabilities, context limits, and prices can change, so do not keep a static model list in setup instructions.

Tips

Prefer base URL when the app supports it

Most apps are easier to configure and less fragile when you provide https://api.tokenlab.sh/v1 as a base URL instead of a full endpoint URL.

Test the model in your app

Compare a few current models on the same conversations before choosing a default.

Keep coding tools separate

General chat apps and coding agents often need different endpoint behavior. Keep Codex/Cursor-style tools on their dedicated integration pages.

Troubleshooting

Connection Error

Verify the base URL is exactly https://api.tokenlab.sh/v1
Remove trailing slashes if the app auto-appends paths
If the app wants a full endpoint URL, use https://api.tokenlab.sh/v1/chat/completions

401 Unauthorized

Double-check your API key
Confirm the key is active in TokenLab dashboard
Make sure there are no extra spaces or line breaks

Model Not Available

Verify the model name exactly
Copy the exact model ID from the TokenLab Models page
Check that the model supports Chat Completions

Compatibility Matrix

Coding Tools

Native SDKs

Frameworks & Platforms

Chat Apps

AI Chat Applications

Overview

Supported Applications

Default Connection Values

Example App Setups

Choose a Model

Tips

Troubleshooting

​Overview

​Supported Applications

​Default Connection Values

​Example App Setups

​Choose a Model

​Tips

​Troubleshooting

Overview

Supported Applications

Default Connection Values

Example App Setups

Choose a Model

Tips

Troubleshooting