Models and Providers

Select and manage models

Find, switch, and manage AI models in the Playground using search, provider filters, and visibility settings.

Updated October 17, 2026

The EidoStack AI Playground brings supported models into one selector so you can choose the right model for a conversation or try several models on the same task. Visibility settings help you keep that list manageable. Hiding a model does not remove it from the catalog, connect a provider, or change what your provider account is allowed to use.

Select a model in a chat

  1. Open a chat and select the current model name in the prompt toolbar.

EidoStack prompt toolbar showing the current model name.

  1. Use Search models… to find a name or use All, OpenAI, Anthropic, or Google to filter by provider.

EidoStack model selector search field with provider filters and a matching model result.

  1. Select a model card in grid view, or choose a row in list view.

EidoStack model selector showing a selected model card.

  1. Send a prompt when the matching provider key is configured and the vault is unlocked.

The selector opens with a search field focused, resets to All when reopened, and can be closed with Escape or by selecting outside the panel. Its grid/list preference is retained in the browser. The active model is highlighted so you can confirm the selection before sending a request.

Changing the model affects the current chat, not every conversation in the Playground. This makes it easy to continue a task with another model or explore a different response. Start a new chat when you want to compare models without inherited conversation history.

Control which models appear

  1. Open the workspace settings and select Models.

EidoStack Models settings page showing the workspace model list and visibility controls.

  1. Choose All or a provider filter.

EidoStack Models settings page showing the provider filter options.

  1. Use the switch beside an individual model to show or hide it.

EidoStack Models settings page showing an individual model visibility switch.

  1. Use the All Models switch, or the selected provider’s switch, to enable or disable a group at once.

EidoStack Models settings page showing the All Models and provider-level switches.

The header shows how many catalog models are enabled. The chat selector hides disabled models and only shows provider filter pills for providers that still have at least one enabled model. If the current selection is disabled while you are in a chat, EidoStack moves the active selection to an enabled fallback when one is available.

Handle deprecated models

Some catalog entries display a warning icon. Hover or focus it to see the scheduled shutdown date. A deprecated entry can remain visible for testing, but avoid relying on it for ongoing tasks because provider availability may end on the displayed date.

EidoStack Models settings page showing a deprecated model warning and scheduled shutdown date.

Keep a successor model enabled while you test the replacement against your representative prompts. This makes it possible to compare the behavior and estimated cost before the retired model becomes unavailable.

Resolve selection issues

The model does not appear

Open Settings > Models, select the appropriate provider filter, and enable the model. If the entire provider is absent from the selector, it has no enabled catalog models.

The model appears but cannot send a request

Visibility is separate from credentials. Save a key for that model’s provider in Settings > Providers, then unlock the vault. See Configure your first AI provider.

The list is too broad

Hide models you do not currently use, and keep your preferred choices enabled for faster switching in the Playground. You can re-enable hidden models later; hiding one does not delete chats that previously used it.

When you want to see two models answer the same prompt, open Compare model responses and explore the results side by side.

Select and manage models | EidoStack Docs