Choosing models

Harriet Desktop shows the models your organization has enabled in one picker. This page covers model selection and billing for OpenCode workspaces. If your organization has enabled the preview for workspaces running Claude Code, see choose a workspace engine for account connection and billing differences.

The model picker

The picker works at two levels:

The picker groups Recommended models first and is searchable, so you can jump straight to the one you want. Match the model to the job: a heavyweight reasoning model for a finance forecast or an IT architecture review, a fast model for a sales rep churning through call summaries or an operations team reformatting shift notes.

Where the list comes from

Model traffic from OpenCode workspaces goes through Harriet's LLM proxy. Your organization supplies its own provider keys (BYOK) or uses Harriet's managed credits, and Harriet records usage and cost.

Which models you see is a policy decision, not a personal one: the picker shows exactly what your organization's model allowlist permits. Everyone signs in with their Harriet account and gets the same governed list, so there is no per-seat AI subscription to buy or manage.

💡

Because the proxy carries the credentials, you never paste an API key into Harriet Desktop, and switching providers never requires new accounts on your machine.

If the picker is empty or missing a model

When no models have reached the app yet, the picker says so directly: "No LLM models are available from your Harriet account yet. Sync from Settings → Harriet account, or check LLM billing and model access in the Harriet console."

  1. Sync first. Open Settings → Harriet account and sync; a fresh sign-in or a newly enabled catalog can take one sync cycle to land.
  2. Check the allowlist. A model that exists but isn't listed for you is usually excluded by the allowlist — that's an admin setting, not an app fault.
  3. Check billing. If your organization's keys or credits aren't set up for a provider, its models can't be served. Model availability walks through the cases.

A cloud workspace shows its own messages. While it is still starting, the picker says "Your cloud workspace is still starting. Models will appear here as soon as it is up." There is nothing to sync or fix: a cloud workspace lists its own models, so they appear once it is running.

If the workspace is running and the picker says "No models are available in this workspace yet. If none appear, check billing and model access in the Harriet console.", the workspace has not listed any models. Work through the allowlist and billing steps above. Syncing from Settings does not apply to a cloud workspace.