Akamai Launches AI Inference and Agent Sandbox Tools
Akamai Technologies introduced Akamai Inference and Akamai Agent Sandbox to provide enterprises with a secure, unified platform for deploying and running AI workloads.
Akamai Technologies launched Akamai Inference and Akamai Agent Sandbox to expand its AI stack within Akamai Cloud. These tools provide enterprises with a unified platform to build, run, and secure AI applications across core data centers and more than 4,350 edge locations.
Akamai Inference offers managed access to custom and open-weight models through OpenAI-compatible APIs, supporting both dedicated and serverless deployment. To complement this, the Akamai Agent Sandbox uses WebAssembly isolation to create secure, isolated execution environments for AI agents, limiting their access to memory and compute resources.
To power these services, the company expanded its GPU fleet with NVIDIA Blackwell Ultra GPU clusters and announced plans to integrate the NVIDIA Vera Rubin platform in 2027. Adam Karon, COO and GM of Akamai Cloud, stated that the company's strategy is based on the belief that AI inference will represent the majority of enterprise investment.