Tuned Tensor

Access tokens

Local TT commands work without a Tuned Tensor account or access token. Add a TT token to use the managed agent model and cloud operations.

  1. Sign in to the dashboard settings.
  2. Create an access token and copy it while it is displayed.
  3. Run tt auth login and paste the token at the hidden prompt.
tt auth login
tt

If you have not selected a provider, TT uses the managed model automatically. Tuned Tensor chooses the model and sends requests through OpenRouter, so there is no separate model key to configure. Revoke a token in settings when it is no longer needed.

Use your own provider

In the TT shell, use /login openrouter and then /model openrouter/<model-id>. Requests go directly to OpenRouter with your key and chosen model. Use either provider with the local pipeline. Commands under tt cloud and report publishing require a TT token; training on your own AWS instance uses your local AWS profile and SSH credentials. See the AWS GPU guide.

To return to the managed agent, select /model tunedtensor/managed. See the agent guide for credential storage and data flow.