Libraries and tools

Command-line tools

Baseten CLI

Deploy and manage models from your terminal. Install with Homebrew on macOS or Linux:

brew tap basetenlabs/baseten
brew trust --formula basetenlabs/baseten/baseten
brew install baseten

GitHub · Docs

Truss CLI

Package models and run Chains, Loops, and Training commands.

pip install truss

GitHub · Docs

Baseten Switch

Configure coding agents to use Model APIs on macOS. Baseten Switch is in beta.

brew trust basetenlabs/baseten
brew install basetenlabs/baseten/baseten-switch

Docs

Management SDKs

Call the Management API from your application.

Python

Manage models and deployments with synchronous or asynchronous Python methods.

pip install baseten

GitHub · Docs

TypeScript and JavaScript

Manage models and deployments from Node.js applications.

npm install @basetenlabs/client

GitHub · Docs

Go

Manage models and deployments from Go applications.

go get github.com/basetenlabs/baseten-go

GitHub · Docs

Model development and training

Truss SDK

Package and deploy models from Python. Import the package as truss.

pip install truss

GitHub · Docs

Chains SDK

Define chainlets and compose inference pipelines. Import the package as truss_chains.

pip install truss

GitHub · Docs

Loops SDK

Run LoRA training and generate samples with Python 3.12 or later. Import the package as baseten.loops.

pip install baseten-loops

PyPI · Docs

Training SDK

Configure compute, runtime, and storage for training jobs. Import the package as truss_train.

pip install truss

GitHub · Docs

Inference clients

The Performance Client sends concurrent embedding, reranking, classification, and batch requests to model endpoints.

Python Performance Client

Send concurrent inference requests with synchronous or asynchronous Python methods.

pip install baseten_performance_client

GitHub · Docs

Node.js Performance Client

Send concurrent inference requests from Node.js applications.

npm install @basetenlabs/performance-client

GitHub · Docs

Rust Performance Client

Send concurrent inference requests with Tokio.

cargo add baseten_performance_client_core

GitHub · Docs

See Batching and concurrency to control batch size and concurrent requests.

Terraform

Terraform provider

Manage Baseten resources with Terraform. Add the provider to your configuration:

terraform {
  required_providers {
    baseten = {
      source  = "basetenlabs/baseten"
      version = "~> 0.1"
    }
  }
}

Run terraform init to install the provider.GitHub · Docs

CLI reference for terminal commands and scripts.
API reference for HTTP endpoints.
Configuration reference for Truss and engine settings.

Reference

Inference API

Management API

Loops API

Training API

Frontier Gateway API

CLI reference

SDKs and clients

Configuration

Metrics

Integrations

Libraries and tools

Command-line tools

Baseten CLI

Truss CLI

Baseten Switch

Management SDKs

Python

TypeScript and JavaScript

Go

Model development and training

Truss SDK

Chains SDK

Loops SDK

Training SDK

Inference clients

Python Performance Client

Node.js Performance Client

Rust Performance Client

Terraform

Terraform provider

​Command-line tools

Baseten CLI

Truss CLI

Baseten Switch

​Management SDKs

Python

TypeScript and JavaScript

Go

​Model development and training

Truss SDK

Chains SDK

Loops SDK

Training SDK

​Inference clients

Python Performance Client

Node.js Performance Client

Rust Performance Client

​Terraform

Terraform provider

​Related references

Command-line tools

Management SDKs

Model development and training

Inference clients

Terraform

Related references