Salad
CuratedActiveSaladCloud runs containers on a distributed network of consumer RTX GPUs
From
—
GPU from
$0.330/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
2
plans
Overview
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.
Plans & prices
GPU instances2
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
RTX 4090 24GB — highest priority tier, per GPU incl. vCPU and RAM (lowest tier $0.15) | 1× GeForce RTX 4090 | $0.330 | $0.330 | — | Verified 3 days ago | |
RTX 5090 32GB — highest priority tier, per GPU incl. vCPU and RAM (lowest tier $0.25) | 1× GeForce RTX 5090 | $0.500 | $0.500 | — | Verified 3 days ago |
GPU models
Similar providers
RunPodDeveloper GPU cloud with per-second Pods, serverless endpoints and community hosts
falGenerative media platform with pay-per-use model APIs and serverless GPUs
ModalPython-native serverless cloud with per-second GPUs from T4 to B300
Hugging FaceAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference
DeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute
Fireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deployments
BasetenInference platform for dedicated model deployments and model APIs, billed per minute
BeamServerless GPUs, sandboxes and BYOC deployments billed by the millisecond