FriendliAI
CuratedActivefriendli.aiSince 2021
Inference platform with model APIs, per-second dedicated GPUs and bring-your-own-GPU
From
—
GPU from
$4.00/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
4
plans
Overview
FriendliAI runs its optimised Friendli inference engine as serverless model APIs, dedicated endpoints on A100 to B300 GPUs billed per second, and a bring-your-own-GPU option for customers' own clusters.
Plans & prices
GPU instances4
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
Dedicated endpoint, A100 80GB — on-demand per GPU, billed per second | 1× A100 80GB | $4.00 | $4.00 | — | Verified 3 days ago | |
Dedicated endpoint, H100 80GB — on-demand per GPU, billed per second | 1× H100 SXM | $5.00 | $5.00 | — | Verified 3 days ago | |
Dedicated endpoint, H200 141GB — on-demand per GPU, billed per second | 1× H200 | $7.00 | $7.00 | — | Verified 3 days ago | |
Dedicated endpoint, B200 180GB — on-demand per GPU, billed per second | 1× B200 | $9.00 | $9.00 | — | Verified 3 days ago |
GPU models
Similar providers
NebiusAmsterdam-based AI cloud with GB300/B300/H200 capacity and Token Factory inference
immers.cloudMoscow GPU cloud with immersion-cooled servers and per-second billing
Denvr DataworksCanadian AI cloud with sovereign GPU compute in Canada and the US
Together AIOpen-model inference API plus self-serve and reserved NVIDIA GPU clusters
Intelion CloudMoscow GPU cloud with per-second billing, H200/H100 SXM and 48GB RTX 4090 cards
Cloud.ruSber's cloud provider (ex-SberCloud) with Evolution IaaS/PaaS and GPU rental
falGenerative media platform with pay-per-use model APIs and serverless GPUs
HyperbolicOpen-access AI cloud with on-demand H100/H200/B200 and reserved clusters