Reference documentation

This reference section documents Baseten’s APIs, CLIs, and Python SDKs for deploying models, managing your workspace, running training jobs, and calling endpoints in production.

​

API reference

Baseten provides APIs for inference, workspace management, Training Jobs, Loops, and Frontier Gateway:

​

CLI reference

The Baseten CLI deploys and operates models, and the Truss CLI authors model code and runs the Chains, Training, and Loops workflows. See the CLI overview to choose the right CLI for a task.

• Baseten CLI reference: The default CLI for deploying and operating models, managing deployments and environments, and automating your workspace from scripts and CI.
• Truss CLI reference: Commands for authoring config.yaml and model.py, building images, and running Chains, Training, and Loops workflows.
• Chains CLI reference: Commands for orchestrating multi-model workflows.
• Loops CLI reference: Commands for deploying and inspecting Loops sessions, runs, samplers, and checkpoints.
• Training CLI reference: Commands for managing training jobs.
• Baseten Switch CLI reference: Commands for routing Claude Code, Codex CLI, and Pi to Model APIs.

---

​

Truss configuration

The Truss configuration reference documents every key in config.yaml: model resources, dependencies, secrets, and engine settings.

---

​

SDK reference

Use the Python SDKs to deploy models, manage deployments, and call models from code.

• Truss SDK reference: Deploy and interact with Truss models using Python.
• Chains SDK reference: Build and manage inference chains programmatically.
• Loops SDK reference: Python clients for Loops training, sampling, and session management.
• Training SDK reference: Deploy and interact with trained models using Python.

---

​

CI/CD

The Truss Push GitHub Action deploys and validates a Truss model or chain from GitHub Actions.