Salad

已审核运营中
salad.comUS美国始于 1999

SaladCloud runs containers on a distributed network of consumer RTX GPUs

无服务器去中心化
访问官网 价格
起价
—
GPU起价
¥2.21/GPU时
地区
0
个国家
数据中心
0
个站点
网络 (ASN)
0
个ASN
方案与价格
2
个方案

概览

SaladCloud schedules containerised workloads onto a crowd-sourced network of gaming PCs with consumer RTX GPUs, billed per second with vCPU and RAM included and four priority tiers trading price against preemption risk. It suits batch inference, transcription and image generation.

方案与价格

GPU实例2
Instance配置每GPU小时总价 /时竞价地区来源
RTX 4090 24GB — highest priority tier, per GPU incl. vCPU and RAM (lowest tier $0.15)
1× GeForce RTX 4090¥2.21¥2.21—
 已核实
4天前
RTX 5090 32GB — highest priority tier, per GPU incl. vCPU and RAM (lowest tier $0.25)
1× GeForce RTX 5090¥3.35¥3.35—
 已核实
4天前

GPU型号

RTX PRO 6000 BlackwellGeForce RTX 5090GeForce RTX 5080GeForce RTX 4090GeForce RTX 4080 / SuperGeForce RTX 3090 / TiGeForce RTX 3080 / TiGeForce RTX 3070 / TiGeForce RTX 3060 / Ti

类似服务商

RunPodDeveloper GPU cloud with per-second Pods, serverless endpoints and community hostsUSfalGenerative media platform with pay-per-use model APIs and serverless GPUsUSModalPython-native serverless cloud with per-second GPUs from T4 to B300USHugging FaceAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inferenceUSDeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minuteUSFireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deploymentsUSBasetenInference platform for dedicated model deployments and model APIs, billed per minuteUSBeamServerless GPUs, sandboxes and BYOC deployments billed by the millisecondUS