Use UnsavedAi with LibreChat
Configure a custom Chat Completions provider for your LibreChat installation.
Configure a custom endpoint
LibreChat supports custom providers in librechat.yaml. Configure name, baseURL, apiKey, and models. Set baseURL to the URL ending in /v1 from UnsavedAi. Keep the key in a server environment variable rather than committing it to the configuration repository.
Configure model discovery
Use models.fetch or an explicit default model list as supported by your LibreChat version. Copy the exact model ID from UnsavedAi Models. Restart or reload your LibreChat configuration as required by your installation.
Start with text chat
Check one short response first. Disable tools or other optional features unless the selected model and UnsavedAi endpoint explicitly support them. These are configuration instructions, not certification of every LibreChat version.
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.