FriendliAI

ПровереноРаботает
friendli.aiС 2021

Inference platform with model APIs, per-second dedicated GPUs and bring-your-own-GPU

ИнференсServerless
Перейти на сайт ЦеныКонтакты
От
—
GPU от
336 ₽/GPU-час
Локации
0
стран
Дата-центры
0
площадок
Сети (ASN)
0
ASN
Тарифы и цены
4
тарифов

Обзор

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.

Тарифы и цены

GPU-инстансы4
InstanceКонфигурацияза GPU-часВсего /часSpotЛокацииИсточник
Dedicated endpoint, A100 80GB — on-demand per GPU, billed per second
1× A100 80GB336 ₽336 ₽—
 Проверено
4 дн. назад
Dedicated endpoint, H100 80GB — on-demand per GPU, billed per second
1× H100 SXM420 ₽420 ₽—
 Проверено
4 дн. назад
Dedicated endpoint, H200 141GB — on-demand per GPU, billed per second
1× H200588 ₽588 ₽—
 Проверено
4 дн. назад
Dedicated endpoint, B200 180GB — on-demand per GPU, billed per second
1× B200756 ₽756 ₽—
 Проверено
4 дн. назад

Модели GPU

B300 (Blackwell Ultra)B200H200H100 SXMA100 80GBA100 40GB

Похожие провайдеры

NebiusAmsterdam-based AI cloud with GB300/B300/H200 capacity and Token Factory inferenceNLimmers.cloudMoscow GPU cloud with immersion-cooled servers and per-second billingRUDenvr DataworksCanadian AI cloud with sovereign GPU compute in Canada and the USCATogether AIOpen-model inference API plus self-serve and reserved NVIDIA GPU clustersUSIntelion CloudMoscow GPU cloud with per-second billing, H200/H100 SXM and 48GB RTX 4090 cardsRUCloud.ruSber's cloud provider (ex-SberCloud) with Evolution IaaS/PaaS and GPU rentalRUfalGenerative media platform with pay-per-use model APIs and serverless GPUsUSHyperbolicOpen-access AI cloud with on-demand H100/H200/B200 and reserved clusters