GPU Cloud

RunPod

On-demand GPUs and serverless inference for training and running AI models.

gpuserverless-inferencepods

Website

Pricing plans

From $0.27

RTX A5000 Pod

$0.27

/ monthly

• GPU sob demanda
• Preço observado por hora
• Pods

A100 PCIe Pod

$1.39

/ monthly

• GPU sob demanda
• Preço observado por hora
• Pods

H100 PCIe Pod

$2.89

/ monthly

• GPU sob demanda
• Preço observado por hora
• Pods

A4000 Serverless

$0.58

/ monthly

• Inferência serverless
• Preço observado por hora
• Sem free tier público identificado

Enterprise

Not available

• Workloads de grande escala
• Preço sob consulta

Activity on Konsenso

0 Visits (30d)

6 Outbound clicks (30d)

0 Likes

Active coupons

This tool has no active coupons right now.

What's included

RunPod is a specialized cloud computing platform providing GPU infrastructure and serverless compute for artificial intelligence workloads. It enables developers and teams to run real-time inference, fine-tuning, and large-scale model training on scalable cloud hardware. The platform offers on-demand GPU instances deployed across more than thirty global regions, auto-scaling serverless GPU endpoints for low-latency API serving, and multi-node clusters for distributed model training. It also features a repository of pre-configured open-source AI models and templates ready for one-click deployment. The infrastructure is designed for machine learning researchers, AI engineers, software developers, and technology enterprises. Its pricing model operates on a pay-as-you-go basis billed by the second or hour, with both on-demand and reserved instance tiers.