GPU
Access powerful on-demand NVIDIA™ GPUs with predictable, cost-effective pricing
Deploy the right GPU to meet your application’s needs and budget
Sustainably test and scale compute-intensive workloads on Akamai’s GPU cloud services without draining your infrastructure budget. Akamai Cloud’s NVIDIA™ GPUs are structured to support your workloads and keep you building. Easily deploy cloud-based GPUs when needed. Predictable pricing and low-cost egress help you manage costs and scale machine learning, AI workloads, data processing, and other high-performance computing with confidence.
Key features
Dedicated GPU resources
Get strong, predictable performance with GPU and CPU resources 100% allocated to your plan.
25x media encoding performance
RTX 4000 Ada GPU plans are built for media workloads, with 2x encoding, 2x decoding, and 1x AV1 encode/decode engines per card.
Superior AI inference performance
Deliver up to 60% lower latency and 3x higher throughput for up to 86% less cost with image generation and AI workloads on RTX 4000 Ada GPUs compared to equivalent hyperscaler GPUs.
Features
- Low, predictable GPU pricing starting at $0.52 per hour for RTX 4000 Ada GPU plans
- Configure Backups to retain data with automated daily, weekly, and biweekly snapshots
- Add GPU nodes to managed Kubernetes clusters with LKE
- Easily resize a Shared CPU, Dedicated CPU, Premium CPU, or High Memory instance to a GPU instance
- Save up to 90% on egress with Akamai Cloud ($0.005 per GB in most regions)
- Set up CI/CD pipelines with custom images, Terraform provider, and more
- Access full documentation support to install NVIDIA CUDA toolkit to get started
- Manage infrastructure flexibly with our UI, API, CLI, and developer tool integrations
- 24/7/365 email and phone support for all customers
Explore other compute plans
Accelerated Compute
Optimize performance with ASICs and NETINT VPUs for faster media transcoding.
Essential Compute
Match Shared CPU, Dedicated CPU, or High Memory compute plans to your applications’ needs and budget.
Next steps
Browse GPU technical documentation
Learn more about Akamai Cloud GPUs.
Learn how to create a compute instance
Learn how to create a compute instance in your preferred core compute region using Cloud Manager.
Ready to get started?
Log in or create an account and start deploying compute instances today.
Have questions?
Contact a sales consultant today to learn more.
Installing NVIDIA CUDA toolkit on GPU instances
Learn how to install NVIDIA’s CUDA toolkit to get started after deployment.
See if you qualify for up to US$5,000 in cloud credits
We’re here to help you with large deployments, migrations, app optimization, architecture assessments, security and reliability audits, and much more. For support or account issues, please visit our support page.