Google sells Gemini through two front doors that share a model family but differ in authentication, quotas, data terms and surrounding services. The Gemini Developer API (keys from Google AI Studio) is the fastest path to a prototype; Google Cloud's enterprise platform, called Vertex AI until Google Cloud Next in April 2026 and now Gemini Enterprise Agent Platform, adds IAM, VPC Service Controls, regional data residency, Model Garden, provisioned throughput and managed agent hosting. Many docs, SDK parameters and console labels still say Vertex AI, so this course teaches both names.
You will use the Google Gen AI SDK against both endpoints, compare the legacy generateContent interface with the Interactions API that Google made generally available in June 2026 and now recommends for new projects (and the features, such as batch and explicit caching, that still require generateContent), and control thinking, multimodal inputs and structured output. You will ground answers in Google Search, URL context and your own data, lower cost with implicit and explicit context caching and batch jobs, and size quotas and provisioned throughput. The agent modules cover the Agent Development Kit, deployment to Agent Runtime (formerly Agent Engine) and the Live API for real-time voice. The course ends with Model Garden partner and open models, Gen AI evals, and the security controls regulated organizations ask about first. Facts are as of October 2026.