(function() { var utmInheritingDomain = "appstore.com", utmRegExp = /(&|\?)utm_[A-Za-z]+=[A-Za-z0-9]+/gi, links = document.getElementsByTagName("a"), utms = [ "utm_medium={{URL - utm_medium}}", "utm_source={{URL - utm_source}}", "utm_campaign={{URL - utm_campaign}}" ]; for (var index = 0; index < links.length; index += 1) { var tempLink = links[index].href, tempParts; if (tempLink.indexOf(utmInheritingDomain) > 0) { tempLink = tempLink.replace(utmRegExp, ""); tempParts = tempLink.split("#"); if (tempParts[0].indexOf("?") < 0 ) { tempParts[0] += "?" + utms.join("&"); } else { tempParts[0] += "&" + utms.join("&"); } tempLink = tempParts.join("#"); } links[index].href = tempLink; } }());

Pricing

Find the best product for you

Friendli Dedicated Endpoints

Build and run generative AI models on autopilot in the cloud.

Featured highlights
check

Pay-as-you-go

check

Configurable autoscaling

check

Fine-tune custom models

Featured highlights
check

Everything in the Basic plan

check

Monitor endpoints with Metrics & Logs

check

Custom pricing

Compare plans and features

FeaturesBasicEnterprise
Fine-tuningFine-tune custom models
Weights & Biases integration
Training assistance by FriendliAI experts
EndpointsDirectly create endpoints from Hugging Face
Priority access to high demand GPUs
Configurable autoscaling
Metrics & Logs
Endpoint versioning
Multi-LoRA deployments
PricingPay-as-you-go
Custom quote
Customer SupportEmail & in-app chat support
Dedicated support

Fine-tuning

Basic

Enterprise

Fine-tune custom models
Weights & Biases integration
Training assistance by FriendliAI experts

Endpoints

Basic

Enterprise

Directly create endpoints from Hugging Face
Priority access to high demand GPUs
Configurable autoscaling
Metrics & Logs
Endpoint versioning
Multi-LoRA deployments

Pricing

Basic

Enterprise

Pay-as-you-go
Custom quote

Customer Support

Basic

Enterprise

Email & in-app chat support
Dedicated support

Pricing details

Endpoints are billed per GPU hour, while fine-tuning is billed based on the number of tokens processed and the model size.
Interested in fine-tuning other model types, such as image models? Reach out to us at contact@friendli.ai.
* Contact sales for a customized, discounted pricing plan for your enterprise.

Endpoint

GPU Type

Basic

Enterprise

A100 80GB

Service costGPU cost

$2.9 / hour

$1.3

$1.6

H100 80GB

Service costGPU cost

$5.6 / hour

$2.7

$2.9


Fine-tuning

Model

Basic

Enterprise

Models up to 16B parameters

$0.50 / 1M tokens

Models 16.1B - 72B

$3.00 / 1M tokens

* We charge based on the total number of tokens processed by your fine-tuning jobs.

We use cookies to enhance your browsing experience and analyze our traffic.