Auto-Distillation Platform

Fine-tune, deploy, and run inference.

📖 View Docs

What is Auto-Distillation?

Auto-Distillation lets you automate dataset preparation, fine-tune models, deploy them seamlessly, and run inference – all through simple APIs.

Core APIs

Get Available Models

Retrieve a list of all supported models that can be used for fine-tuning.

Train & Deploy

Start fine-tuning with bot id and model name. Automatically trains & deploys your model.

Check Training Status

Track progress with job id and get inference URL once complete.

Run Inference

Use your deployed model with inference url and a prompt to generate responses.

How It Works

1

Choose a Model

Pick from available supported models.

2

Train & Deploy

Kick off auto-training & deployment in one step.

3

Run Inference

Generate intelligent responses via inference API.