LLM Services

Connect IVYX Studio to a remote LLM service by pointing it at an endpoint URL and API token, then define reusable AI capabilities that run against it.

What you can do

• Enter a remote endpoint URL and API token, save them, and test the connection before you rely on it.
• Author instruction classes (reusable prompts/capabilities) for that endpoint: give each an ID, role, system prompt, temperature, max tokens, and response format (text or JSON), with an optional output schema for JSON.
• Edit an existing instruction class — registering an updated one replaces the old definition.

Instruction classes you register here show up in the LLM Capabilities panel under Instruction Classes, where you list and manage them.

Getting started

Open LLM Services from the command palette, or from the LLM Capabilities panel's "Add Remote" action under Instruction Classes.

Note

The API token is currently kept in the settings store. A dedicated, encrypted secret store is a planned improvement.