X
Akamai acquires Fermyon to combine WebAssembly function-as-a-service (FaaS) with Akamai’s globally distributed platform. Read news
Login
Login Close
Control Center
Access the Akamai platform
Login Close
Cloud Manager
Manage your cloud resources
Login
Login Close
Control Center
Access the Akamai platform
Login Close
Cloud Manager
Manage your cloud resources
Try Akamai
Under Attack?

Akamai Cloud GPUs Powered by NVIDIA

Distribute AI inference with NVIDIA RTX PRO 6000 Blackwell Server Edition® GPUs and Akamai

Create account
Join waitlist
Book AI consult

Be among the first to access NVIDIA™ RTX PRO 6000 Blackwell GPUs optimized for AI inference.

Join waitlist

Powering Innovation: Akamai Cloud with NVIDIA’s Latest GPUs

NVIDIATM is a recognized leader in GPU technology. Its innovation is present in everything, from the films you watch to programs powered by machine learning, such as virtual personal assistants and product recommendations. Akamai Cloud lets you choose the right GPU for your workload: NVIDIA RTX PRO Servers, featuring NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, and the Quadro® RTX line of GPUs running NVIDIA’s latest generation of GPU architecture.

Benefits

Enterprise-grade GPU acceleration

Access powerful RTX PRO VMs optimized for AI inference: 6000 Blackwell Server Edition, RTX 6000 and RTX 4000 Ada.

Scalable high-performance computing

Leverage cutting-edge GPUs on Akamai Cloud with flexible pricing, empowering teams to scale resources and manage costs.

Optimized cloud deployment

Deploy workloads at the edge with low-latency access to GPU power, ideal for real-time insights and large-scale AI tasks.

NVIDIA GPUs on Akamai Cloud

Our powerful cloud GPU instances are backed by NVIDIA’s industry-leading hardware and Akamai’s developer-friendly infrastructure.

NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs

Power agentic AI, physical AI, and scientific computing to 3D graphics, rendering, and video with 96GB GDDR7.

View data sheet
Join waitlist

NVIDIA RTX 4000 Ada Generation

Balanced price-performance for ML, analytics, and gaming using CUDA, Tensor, and RT cores.

View data sheet

NVIDIA Quadro RTX 6000

Price-performance powerhouse for media transcoding with 6,144 CUDA cores, dual encode/decode engines, and AV1 support.

View data sheet

GPU pricing plans

Discover flexible GPU pricing with cost-effective scaling to meet your workload demands.

See pricing

Explore other compute plans

GPU

Parallel process workloads including machine learning, scientific computing, and video processing.

View product details

Essential Compute

Match Shared CPU, Dedicated CPU, or High Memory compute plans to your applications’ needs and budget.

View product details

Accelerated Compute

Optimize performance with ASICs and NETINT VPUs for faster media transcoding.

View product details
Se muestra a una persona con gafas negras y la cara iluminada por la luz de la pantalla de un ordenador

Book your AI consultation today

AI is moving from the lab to production, and the pressure is on to deliver faster, smarter, and more secure experiences. Whether you’re optimizing inference, scaling models, or reducing latency, we’re here to help you bring AI to life ... at the edge.

  • See how to deploy and scale AI inference closer to your users.
  • Learn how edge native infrastructure improves performance.
  • Explore how to cut costs while maintaining enterprise-grade security.

Book an AI consultation to unlock what’s possible!

Thank you for your submission.

One of our AI consultants will be in touch soon to set up time to speak with you.