One-page reference: latency budgets per feature, four topology layers, cost-per-minute envelope, and the five-step decision tree.
Download free PDF
The book · Volume 6 of 7
AI for Video: A Complete Guide to Intelligence in Video Products: From Models and Inference to Computer Vision, Speech, Search, and Generative Video
This cheat sheet lines up latency budgets per feature, four topology layers and a cost-per-minute envelope, then walks a five-step tree to place each AI feature. Volume 6 covers AI deployment topology in depth: the AI feature lifecycle, device, edge and cloud topologies, model artifacts and the ML minimum needed to make placement decisions. Written by Nikolay Sapunov, CEO at Fora Soft.
Deciding whether your video AI features should run on device, edge or cloud?
List the AI features you plan, and we will place each one in a deployment topology with a latency and cost-per-minute estimate. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
