API Reference

Empower - Serverless Fine-tuned LLM Hosting Platform

Get Started

Sign In

We'd like to talk with you! Your thoughts and feedback are invaluable to us,  and we're here to listen.

Contact Us

Empower is a fine-tuned LLM hosting platform that delivers performance on par with dedicated instances deployment at a fraction of the cost. 

Welcome to Empower!

Deploy Your First LoRA

Query a Deployed Model

Streaming

JSON mode and Structured Output

Introduction

Multi-Turn Tool Calling

Parallel Calling

Built in Chain-of-Thought

Authentication

Supported LoRAs

List all LoRAs

Returns a list of all LoRAs. The LoRAs are returned sorted by deployment time, with the newest LoRA appearing first.

List all LoRAs

Retrieve a LoRA

Retrieve the details of a LoRA.

Retrieve a LoRA

Deploy a LoRA

Make a new deployment to the LoRA, if it does not already exist, a new LoRA will be created.

Deploy a LoRA

Delete a LoRA

List all base models

Returns a list of all base models. The base models are returned sorted by deployment time, with the newest base model appearing first.

List all base models

Retrieve a base model

Retrieve the details of a base model.

Retrieve a base model

Completions

See  https://platform.openai.com/docs/api-reference/chat/create
for the API specification. This API mimics the OpenAI ChatCompletion API.

NOTE: Currently we do not support the following features:
- function_call (Users should implement this by themselves)
- logit_bias (to be supported by vLLM engine)

Quickstart

Inference

Tool Using (Function Calling)

Reference

About

Contact Us

Book a call

Discord

Email