Skip to content

Get started with distil labs

distil labs is a developer platform where engineers train and deploy small models that match frontier accuracy at 80% lower cost. Training (and retraining) runs on synthetic data created from real traces so no preprocessing is required to ensure high accuracy.

Start with Claude

Section titled “Start with Claude”

Run this in your terminal:

claude "Let's get started with distillabs.ai/onboarding"

Claude installs the CLI, creates your account, and trains your first model with you. It stops for your go-ahead at four points, so nothing runs that you have not seen. The whole flow takes about 45 minutes, and jobs run for about 25 of those minutes.

Start with the CLI

Section titled “Start with the CLI”

Install the CLI and create your account, both from the terminal:

curl -fsSL https://cli-assets.distillabs.ai/install.sh | sh
distil signup

distil signup opens your browser and hands the session back, so you finish signed in. If you already have an account, run distil auth instead. You can also sign up at app.distillabs.ai/sign-up.

The installer supports macOS and Linux. On Windows, or on a machine that permits no new binaries, use the REST API instead.

Then train and deploy a model with five commands:

distil seed-dataset create --data ./my-data-dir
# Seed dataset created with ID: <seed-dataset-id>

distil training-dataset create-from-seed-dataset <seed-dataset-id>
# Training dataset created with ID: <training-dataset-id>

distil slm create-from-training-dataset <training-dataset-id>
# SLM created with ID: <slm-id>

distil deployment create-from-slm <slm-id>
distil deployment endpoint <deployment-id>     # URL and API key

Your trained model is ready for hosted inference, or you can run it locally.

Have production traces from an existing LLM application instead of a curated dataset? You can turn those into training data too.

Next steps

Section titled “Next steps”