Managing models

Manage your model's deployment and versions.
Deployed models in your workspace — both pre-trained models and your own models — are listed on the models page. To manage any model, click on its row in the list to visit its overview page.
Model overview
Everything on the main panel of the model page is version-specific. First, version details highlight key information about your deployed model version:
  • Version: The version of the model to which the page refers
  • Created: Timestamp, in your local time, at which this version of the model was created
  • Active: Timestamp, in your local time, since which this version of the model has been active
  • Status: The model version's status, explained below
  • Version ID: The alphanumeric sequence used to invoke the model version
  • Framework: The framework with which the model was trained
Next to the version details panel is information on invoking the model — by Python client or cURL — for both primary version and the version described on the page. You'll need an API key to invoke the model.

Model status

Each deployed version of a model has a status explaining its current state. Possible statuses are:
  • Active: The version is active and available. It can be invoked from the Python client or cURL and, if it is the primary version, from Baseten applications.
  • Unhealthy: The model is active but is in an unhealthy state due to errors while running. Check the logs and redeploy the model or adjust model resources to resolve the error.
  • Deploying: While a model version is being deployed, it has this intermediary status.
  • Updating: While model resources are being updated, all versions of the model will have this intermediary status.
  • Inactive: The version is unavailable and is not consuming resources, but may be reactivated.
  • Build failed: The version is not active due to a Docker build failure. Check the logs, resolve the error, and try again.
  • Deployment failed: The version is not active due to a model deployment failure. Check the logs, resolve the error, and try again.

Model documentation

Documentation shares essential steps and context for using a system — that's why you're reading these docs right now. Every model deployed on Baseten has an editable Readme file where you can document its purpose, inputs, and outputs. Models from a model template come with that information pre-filled, but you'll need to document custom models yourself.

Download the model

Any model version can be downloaded as a Truss from your Baseten account to your local computer. Just open terminal and run:
pip install --upgrade baseten
baseten login # see:
baseten models pull # asks you for a model version ID to download, find this on the model's page