Akamai Inference Cloud deploys Nvidia AI Grid

Nvidia GTC 2026 is turning out to be a bit of a coming-out party for Akamai's Inference Cloud. Akamai's Inference Cloud is the first global implementation of Nvidia AI Grid, which routes AI workloads across edge networks for lower latency and cost with improved performance.

Akamai has been advancing its Inference Cloud in recent weeks. Using its expertise in distributed compute, Akamai first expanded into offering cloud workloads and now has focused on expanding inference from data centers to the edge.

At Nvidia GTC 2026, Akamai said it has integrated Nvidia's infrastructure into its own to create a distributed grid for AI inference. The latest evolution of Akamai Inference Cloud, which received a shoutout in Nvidia CEO Jensen Huang's keynote, is the first to operationalize AI Grid. Nvidia GTC 2026 features a broad vision for AI inference and how it applies to agentic workloads.

Nvidia GTC 2026

• Palantir and Nvidia build sovereign, on-premises AI reference architecture
• Nvidia Nemotron: Much needed open-source model champion in US

"Our AI Grid intelligent orchestration gives AI factories a way to scale inference outward leveraging the same distributed architecture that revolutionized content delivery to route AI workloads across 4,400 locations, at the right cost, at the right time," said Adam Karon, Chief Operating Officer of Akamai's cloud unit.

The tight partnership with Nvidia and its focus on edge and inference puts Akamai in good position given that its network is globally distributed. Akamai is gaining workloads with caching and routing orchestration, egress allowances and 4,400 edge locations.

Akamai's bet is that Inference Cloud will gain AI workloads due to lower latency and costs and be seen as an enabler for AI agents.

Scaling Inference Cloud

The company's Inference Cloud is built in partnership with Nvidia and has a distributed architecture that uses Nvidia's Blackwell AI infrastructure. Akamai announced Inference Cloud in October and announced the following in the months leading up to Nvidia GTC.

Inference Cloud is latest in a cloud plan that formed in 2023 and expanded with the help of Nvidia

• Akamai's IaaS vision: Become your cloud alternative
• Akamai launches Gecko, aims to combine cloud compute, edge networks
• Akamai launches Akamai App Platform as it scales cloud business

Here’s a look at how Akamai has scaled Inference Cloud in recent months.

Inference Cloud launch. Inference cloud features Nvidia RTX PRO Servers, featuring Nvidia RTX PRO 6000 Blackwell Server Edition GPUs, Nvidia BlueField-3 DPUs, and Nvidia AI Enterprise software with Akamai's distributed cloud computing infrastructure and global edge network.

Akamai said Inference Cloud was designed to extend AI factories to enable various agentic use cases and physical AI.

Use cases surge. In November, Akamai said early uses cases for Inference Cloud showing demand were 8k video workflows, live video intelligence, recommendation engines, assistive agents and AI powered fitting room experiences.

Partnerships added. Akamai said it was partnering with Visa to bring identity, user recognition and security controls to agentic commerce. The company also said it launched a partner program for independent software vendors.

Scale and GPU acquisitions. Akamai said in March that it has acquired thousands of Nvidia Blackwell GPUs to scale its Inference Cloud. The company also outlined the technical details of a $200 million services agreement inked with US tech company. Akamai disclosed the deal on its fourth quarter earnings call.

"We believe the AI market is entering a critical transition point, the first inning of a long game to come, where inference or the execution of queries against a trained model is the new frontier. This requires purpose-built infrastructure to enable distributed low-latency, globally scalable AI at the edge with response times measured in a few tens of milliseconds," said Akamai CEO Dr. Tom Leighton.