Connect SillyTavern to UnsavedAi

Use a hosted AI model for character conversations without running a GPU yourself.

Choose the connection

In SillyTavern, select Chat Completion and Custom (OpenAI-compatible). Copy the API base URL ending in /v1 from your UnsavedAi console into the custom endpoint field. Add a named API key reserved for SillyTavern.

Choose a model and context

Use the exact model ID from Models. Character cards, lore, system instructions, history, and your next message all count toward input. Leave room for output within the total context limit.

Test a short conversation

Start with basic sampling settings and a short reply. Check streaming and stopping a response before loading a long conversation. Unsupported options can cause a request error.

Client configuration reference: official documentation. Client settings can change between versions.

Your next step

Check available models, open your console, or read the API documentation. Public signup and paid plans are still being prepared.