TokenLab

Chat Apps

AI Chat Applications

Connect popular chat applications to TokenLab

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.

The app-specific settings below identify the API where a choice is required. Some apps select Responses by model. Use a model that supports the API used by your app; coding tools have separate integration guides.

Supported Applications

ApplicationPlatformNotes
Open WebUIWeb, Self-hostedSupports OpenAI-compatible connections
LibreChatWeb, Self-hostedSupports custom OpenAI endpoints
LobeChatWeb, Desktop, Self-hostedSupports custom model providers
Cherry StudioWindows, macOS, LinuxSupports OpenAI-compatible providers
ChatboxWindows, macOS, LinuxSupports OpenAI-compatible settings
DeepChatWindows, macOS, LinuxDesktop client with OpenAI-compatible provider settings
JanDesktop, Self-hostedLocal-first app with remote OpenAI-compatible providers
TypingMindWeb, DesktopUses a custom endpoint style
NextChatWeb, Self-hostedLightweight ChatGPT-style client with base-URL overrides
ChatWiseWindows, macOSStandard custom provider pattern

Default Connection Values

FieldValue
Base URLhttps://api.tokenlab.sh/v1
API Keysk-your-tokenlab-key
API TypeOpenAI 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

  1. Open Settings → AI Providers
  2. Select OpenAI
  3. Enter your TokenLab API key
  4. Set the custom endpoint to https://api.tokenlab.sh/v1

Enable and select a model, then send a test message. LobeChat can automatically use Responses for some GPT models, so choose a TokenLab model that supports the API it uses.

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

Troubleshooting

On this page