WorkBuddy is a desktop AI agent workbench. You can connect it to Model Studio using Pay-as-you-go, Coding Plan, Token Plan Personal Edition, or Token Plan Team Edition.
Go to the WorkBuddy official website, click Download, and download the installer for your operating system. After installation, follow the on-screen instructions to sign in to your WorkBuddy account.
Click the model selector at the bottom of the conversation interface and click Configure custom models at the bottom of the list. You can also open Settings from the avatar in the lower-left corner and select Model in the left navigation.
Click Add model and select Custom as the provider.
Enter the API address, API key, and model name. You can click Test connection to verify connectivity.
Click Save.
Model Studio offers the following billing plans. Choose based on your needs:
Token Plan Personal Edition: Deducts personal Credits based on token consumption.
Token Plan Team Edition: Seat-based subscription that deducts Credits based on token consumption.
Coding Plan: Fixed monthly subscription billed by the number of model calls.
Pay-as-you-go: Postpaid billing based on actual usage.
The API address is not completed automatically. Enter the complete Chat Completions address (ending with /chat/completions), as shown in the plan configurations below.
Custom models support only the OpenAI-compatible Chat Completions protocol. Responses API and Anthropic protocols are not supported.
After saving, select the added model from the model selector at the bottom of the conversation interface and ask a question. A valid response confirms the setup.For more information about WorkBuddy features and model configuration, see the WorkBuddy documentation.
The model name is sent as the model parameter in the request and must exactly match a Model Studio model name (case-sensitive, without extra prefixes or suffixes). Check the model name in the custom model settings and try again.
