Skip to main content
Aether supports a wide range of LLM providers via the Pi framework that powers it under the hood. You bring your own credentials — nothing is proxied through Aether’s servers. Your credentials go directly from your device to each provider’s API endpoint.

Supported Providers

The Pi framework supports additional providers beyond those listed here. If your preferred provider is compatible with Pi, it may already be available when you tap Add Provider in Settings.

Adding a Provider

1

Open Settings

Open the conversation drawer from the menu button, then tap Settings.
2

Go to Providers

Tap Model Providers in the Settings menu to see your currently configured providers.
3

Add a new Provider

Tap Add Provider and select your desired provider from the list.
4

Configure credentials

Choose API key, OAuth, or environment credentials when the selected provider supports them.
5

Save

Fetch the provider’s model catalog, enable the models you want, then tap Save.

Switching Models

Tap the model selector displayed in the top bar. The list shows every model available across all of your configured providers. Tap any model to switch to it — the change takes effect on the next message you send.

Model Configuration

For models that expose reasoning controls, Aether lets you choose from the thinking levels reported for that model. Open the model selector to change the reasoning level for the selected model.
API keys are stored only on your device within Aether’s private app storage. They are never sent anywhere other than the respective provider’s own API endpoint.
Current recommended models include GPT 5.6 Sol, Gemini 3.5 Flash, Grok 4.5, and Claude Fable 5.