Projects
Projects are optional organizational tags within a workspace. They let you group related resources—such as datasets, customization jobs, and evaluation results—without creating separate access boundaries. Anyone with access to the workspace can see all its projects.
Use projects when you need to organize related work within a team. For example, group everything related to a fine-tuning experiment (llama-3-customer-support-v2) or an evaluation campaign (quarterly-eval-2025q1). For access isolation between teams or environments, use separate workspaces instead.
Project vs. Workspace
Think of workspaces as filing cabinets (separate, locked) and projects as labels you can apply to documents within a cabinet.
Create a Project
To create a project, provide a name and optionally a description. The name must be unique within the workspace.
Resource names must follow these rules:
- Must start with a lowercase letter (
a-z) - 2-63 characters long
- Allowed characters: lowercase letters, digits, hyphens, and temporarily
@,.,+,_ - No consecutive hyphens (
--) - Cannot end with a hyphen
Example valid names: my-model, llama-3.2-3b, test-config-v1
Once created, a project cannot be renamed.
Python SDK
CLI
List Projects
To list projects in a workspace, call the list endpoint. The response includes pagination metadata.
Python SDK
CLI
Get a Project
To retrieve a specific project by its name:
Python SDK
CLI
Update a Project
To update a project, only the description field can be modified. The name cannot be changed after creation.
Python SDK
CLI
Delete a Project
To delete a project: