Akamai Launches AI Inference and Agent Sandbox Services, Expanding Its Cloud Services Footprint
On October 29, Akamai released beta versions of two products, Akamai Inference and Akamai Agent Sandbox, allowing users to run AI models on Akamai Cloud and securely execute code generated by AI agents. Akamai Inference supports 12 open-weight models, including OpenAI's gpt-oss-120b, Google's Gemma 4, and Nvidia's Nemotron 3 Ultra, and provides an OpenAI-compatible API. Agent Sandbox is based on WebAssembly isolation technology and restricts code access to computing resources, network connections, and system functions.
Body · AI translation
Akamai corporate logo. (Photo: Akamai)
PC본문_6월 Mouser (in Article)//
AD Manager | AD178089411676 //
// AD Manager | AD178089411676
Akamai Technologies is expanding into artificial intelligence (AI) model operations and agent execution. Beyond selling graphics processing units (GPUs) and servers for cloud environments, the company has added services for running and managing AI models.
Akamai said on Oct. 29 that it launched beta versions of Akamai Inference and Akamai Agent Sandbox. The two products enable users to run AI models on Akamai Cloud and securely execute code generated by AI agents.
Akamai Inference is a service that allows enterprises to deploy AI models and integrate them into production environments. Companies can use publicly available AI models or their own fine-tuned models in applications while reducing the burden of building and managing servers. They can choose between a serverless model that charges based on usage and a dedicated deployment option that allocates resources specifically for running models.
Akamai Inference supports 12 open-weight models, including OpenAI's gpt-oss-120b, Google's Gemma 4 and Nvidia's Nemotron 3 Ultra. Open-weight models make trained model weights publicly available for external use. Companies can integrate these models into their own services or customize them for specific tasks.
The service also supports embedding models used in retrieval-augmented generation (RAG), which searches internal corporate documents and incorporates relevant information into AI-generated responses. It provides an OpenAI-compatible application programming interface (API), allowing companies to switch between models without completely rewriting existing applications.
Akamai Agent Sandbox enables code generated by AI agents to run in isolated environments. It uses WebAssembly-based isolation technology to prevent code from affecting external systems by restricting access to computing resources, network connections and system functions. The company also plans to add capabilities to control agent access permissions.
Akamai aims to support the development, execution and security of AI applications by leveraging its global network, edge infrastructure, cloud storage, and central processing unit (CPU) and GPU resources. The company said its network of more than 4,350 edge locations worldwide allows AI services to be processed closer to users, reducing latency.
Adam Karon, chief operating officer (COO) and general manager of Akamai Cloud, said, "Customers want to build, run and protect AI on a single platform." He added that the two products are designed to add inference and execution layers to the company's existing AI infrastructure.