miton
Request beta access

Add a Model

How to configure and add new AI models to your workspace.

Product stage
Development build
Last reviewed
2026-08-27
Successful result
The change is visible in the active project.

What this accomplishes

Configure and connect an AI model (local or cloud-based) to use within your chat sessions.

Current availability

This page documents behaviour verified in Miton development builds. Miton is still pre-release and is not publicly downloadable; invited beta users will receive a signed desktop build with automatic updates.

Before you start

  • A Miton development build and an active project.
  • A connected cloud or local model, plus any credentials or local runtime required by this task.

Steps

  1. Open Settings → Providers → Connected model providers.
  2. Click Add provider and choose one from the list — OpenAI, OpenRouter, and Ollama are built in — or turn on Custom OpenAI-compatible provider and enter a name and endpoint yourself.
  3. Enter your API key (cloud providers) or confirm the local endpoint (Ollama), then save.

What success looks like

The provider shows as connected, and its models appear in the model chip in the roster bar above the chat input, ready for selection.

Common failures and recovery

  • Model not appearing: Double-check that the model name exactly matches the provider’s identifier (e.g. llama3.1 or gpt-4o).
  • Connection errors: Make sure the local provider service is active, or that you have configured a valid connection endpoint.

Continue with your first project or choose the next task from Docs.