Application service provider featuring application programming interface (API) software for running models on edge network for inference, providing AI inference API, and SDKs to add edge devices to networks and run models using their unused compute, and accessing distributed edge computing infrastructure for artificial intelligence inference; Providing on-line non-downloadable software using artificial intelligence (AI) for AI inference optimization, compute efficiency, and deploying and scaling artificial intelligence models; Software as a service (SAAS) services featuring software for AI inference optimization, compute efficiency, distributed AI model deployment, and routing and processing artificial intelligence workloads across distributed computing networks; Providing online non-downloadable computer software platforms for distributed AI inference, edge computing, and AI model deployment