Akamai launches global edge AI cloud with NVIDIA for fast inference

Akamai Technologies has announced the launch of Akamai Inference Cloud, a platform developed in collaboration with NVIDIA to provide global, scalable, and low-latency artificial intelligence (AI) inference.

The Akamai Inference Cloud aims to extend AI inference from traditional core data centres out to the edge of the internet, closer to users and devices. The platform builds on Akamai's distributed infrastructure and leverages NVIDIA Blackwell AI technologies to enable real-time processing and decision-making for both agentic and physical AI applications worldwide.

Edge-powered AI

The service is positioned to address the requirements of next-generation AI applications, such as smart agents, personalisation systems, and real-time industrial AI solutions, which require local context and instantaneous responses. By distributing AI inference to thousands of edge locations, Akamai Inference Cloud seeks to reduce latency and improve the responsiveness of AI-powered experiences.

Dr. Tom Leighton, CEO and co-founder of Akamai, said, "The next wave of AI requires the same proximity to users that allowed the internet to scale to become the pervasive global platform that it is today. Akamai solved this challenge before - and we're doing it again. Powered by NVIDIA AI infrastructure, Akamai Inference Cloud will meet the intensifying demand to scale AI inference capacity and performance by putting AI's decision-making in thousands of locations around the world, enabling faster, smarter, and more secure responses."

Jensen Huang, founder and CEO of NVIDIA, commented, "Inference has become the most compute-intensive phase of AI - demanding real-time reasoning at planetary scale. Together, NVIDIA and Akamai are moving inference closer to users everywhere, delivering faster, more scalable generative AI and unlocking the next generation of intelligent applications."

Technical foundation

The platform combines NVIDIA RTX PRO Servers equipped with NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, NVIDIA BlueField-3 DPUs, and NVIDIA AI Enterprise software atop Akamai's global cloud infrastructure. The company's network extends to more than 4,200 global locations. Akamai also plans to incorporate the NVIDIA BlueField-4 DPU, enhancing acceleration and security for distributed AI workloads from the core to the edge.

Akamai Inference Cloud is designed to support emerging AI-driven workloads through several use cases. These include:

• Extending enterprise AI Factories to the edge for commerce, enabling AI agents to create personalised user experiences and execute real-time transactions.
• Enabling streaming inference and agentic workflows for use cases such as instant financial insights, real-time decisioning, and industrial automation, aimed at reducing latency in sequential AI task completion.
• Supporting real-time physical AI capabilities, powering systems such as autonomous vehicles, robotics, and smart infrastructure to process sensor data with millisecond-level precision and operate safely alongside humans.
• Accelerating time to value by orchestrating complex AI workloads through an intelligent layer that automatically routes tasks between edge and central locations, reducing infrastructure complexities for enterprises.

Deployment and expansion

Akamai Inference Cloud has launched with availability in 20 locations around the world. The company has announced plans to expand this presence further to increase coverage and capacity for AI inference at the edge.

This initiative is intended to enable organisations operating large-scale AI systems, such as smart agents and robotics, to process data and perform inference actions locally, minimising delays and potentially reducing infrastructure costs. Akamai maintains that its platform abstracts away many operational complexities, providing a unified solution for handling distributed AI workloads.

"The next wave of AI requires the same proximity to users that allowed the internet to scale to become the pervasive global platform that it is today," said Dr. Tom Leighton, Akamai CEO and co-founder. "Akamai solved this challenge before - and we're doing it again. Powered by NVIDIA AI infrastructure, Akamai Inference Cloud will meet the intensifying demand to scale AI inference capacity and performance by putting AI's decision-making in thousands of locations around the world, enabling faster, smarter, and more secure responses."

Akamai Inference Cloud aims to serve a range of industries seeking to integrate AI decision-making into processes that demand speed, reliability, and security. The platform's design focuses on supporting both simple and complex AI workflows, from standard inference requests at the edge to advanced reasoning tasks processed in centralised locations.

Akamai's collaboration with NVIDIA represents an effort to address scaling challenges as organisations pursue broader AI adoption. The combination of distributed infrastructure and purpose-built AI hardware is key to enabling agentic and physical AI to operate with responsiveness geared towards practical, real-world scenarios.