What is RunPod?
RunPod is an all-in-one cloud built for AI, providing a globally distributed GPU cloud for developing, training, and scaling AI models. It offers a range of features, including serverless AI inference, autoscaling, job queueing, and sub-250ms cold start time.
Features of RunPod
Develop
- Globally distributed GPU cloud for AI workloads
- Deploy any GPU workload seamlessly
- Focus on running ML models, not infrastructure
Train
- Run machine learning training tasks that can take up to 7 days
- Train on available NVIDIA H100s and A100s or reserve AMD MI300Xs and AMD MI250s a year in advance
Autoscale
- Serverless GPU workers scale from 0 to n with 8+ regions distributed globally
- Only pay when your endpoint receives and processes a request
Bring Your Own Container
- Deploy any container on our AI cloud
- Public and private image repositories are supported
- Configure your environment the way you want
Zero Ops Overhead
- RunPod handles all operational aspects of your infrastructure from deploying to scaling
- You bring the models, let us handle the ML infra
Network Storage
- Serverless workers can access network storage volume backed by NVMe SSD with up to 100Gbps network throughput
- 100TB+ storage size is supported, contact us if you need 1PB+
Easy-to-use CLI
- Use our CLI tool to automatically hot reload local changes while developing
- Deploy on Serverless when you’re done tinkering
Secure & Compliant
- RunPod AI Cloud is built on enterprise-grade GPUs with world-class compliance and security
- Pending certifications: SOC 2, ISO 27001, and HIPAA
Lightning Fast Cold-Start
- With Flashboot, watch your cold-starts drop to sub 250 milliseconds
- No more waiting for GPUs to warm up when usage is unpredictable
Pricing
RunPod offers a range of pricing plans, including:
- Secure Cloud: starting from $2.89/hour
- Community Cloud: starting from $0.39/hour
- Serverless: pay only when your endpoint receives and processes a request
Helpful Tips
- Use RunPod's serverless AI inference to scale your machine learning inference while keeping costs low
- Take advantage of RunPod's autoscaling feature to respond to user demand in real-time
- Use RunPod's network storage to access up to 100TB+ of storage size
Frequently Asked Questions
What is RunPod?
RunPod is an all-in-one cloud built for AI, providing a globally distributed GPU cloud for developing, training, and scaling AI models.
How does RunPod's autoscaling work?
RunPod's autoscaling feature allows serverless GPU workers to scale from 0 to n with 8+ regions distributed globally. You only pay when your endpoint receives and processes a request.
What is the cold-start time for RunPod's serverless AI inference?
With Flashboot, the cold-start time for RunPod's serverless AI inference is sub 250 milliseconds.