Run custom LLMs on autopilot with
Friendli Dedicated Endpoints


Automate generative AI serving
with just a few clicks

fde
QUICKSTART

How it works

See the guideline below to easily deploy any generative AI model
on Friendli Dedicated Endpoints.
01

Create a deployment

From the Friendli web, you can create new deployments. Each deployment will handle the inference of an AI model.

02

Select your model

You can either upload your checkpoint or choose any of the models provided by FriendliAI.

03

Configure cloud resources

Friendli Dedicated Endpoints provides multiple virtual machine types across multiple regions. Select a virtual machine type to continue.

04

Interact with your AI model

Go to the interactive playground to test your AI model live.

05

Monitor your deployments

Friendli Dedicated Endpoints monitors your deployments automatically. Look at how your AI model is performing with our supercharged engine.

PRICING

Basic

Sign up
Featured highlights
check

Serve your LLMs on autopilot with Friendli Dedicated Endpoints

check

Billed monthly

Pricing details
check

Friendli on A10G

$1.1 per hour

check

Friendli on A100 40GB

$4 per hour

check

Friendli on A100 80GB

$5 per hour

Enterprise

Contact Sales
Featured highlights
check

Dedicated support

check

Custom pricing based on contracts