Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.baseten.co/llms.txt

Use this file to discover all available pages before exploring further.

The truss CLI is your primary interface for everything from packaging and deploying AI models to building and orchestrating multi-step chains to launching and managing training jobs. Use the following commands to manage your models, chains, and training jobs:
  • Models: Package and deploy individual model servers.
  • Chains: Build and deploy multi-step inference pipelines.
  • Training: Launch and manage training jobs.
You need uv installed and a Baseten account with an API key.

​
CLI structure

The truss CLI organizes commands by workflow: 
truss [OPTIONS] COMMAND [ARGS]...

​
Model commands

Use these commands to package, deploy, and iterate on individual models.
CommandDescription
truss authManage authentication (login, logout, status)
truss loginAuthenticate with Baseten (alias for truss auth login)
truss initCreate a new Truss project
truss pushDeploy a model to Baseten
truss watchLive reload during development
truss predictCall the packaged model
truss model-logsFetch logs for the packaged model

​
Chain commands

Use these commands to build multi-model pipelines with shared dependencies.
CommandDescription
truss chains initInitialize a new Chain project
truss chains pushDeploy a Chain to Baseten
truss chains watchLive reload Chain development

​
Training commands

Use these commands to launch, monitor, and manage training jobs.
CommandDescription
truss train initInitialize a training project
truss train pushDeploy and run a training job
truss train logsStream logs from a training job
truss train viewList and inspect training jobs

​
Authentication

After installing Truss, authenticate with Baseten using one of these methods: Option 1: Environment variable (recommended for CI/CD) 
export BASETEN_API_KEY="EMPTY"
Option 2: Interactive login 
truss login
The CLI prompts you to choose between pasting an API key and logging in via browser (OAuth device flow). Credentials are stored in your OS keyring when available and otherwise in ~/.trussrc. See truss auth for details on credential storage and managing multiple remotes.

​
Next steps

Deploy your first model

Package and deploy a model in minutes.

Build a Chain

Create multi-step inference pipelines.

Launch a training job

Fine-tune models on Baseten infrastructure.

Truss configuration

Configure dependencies, resources, and more.