[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3

Model Endpoints vs APIs

☁️ The Vertex AI Ecosystem 10m 150 BASE XP

Deployment Paradigms

Vertex AI offers two distinct ways to interact with models:

  • Foundation Model APIs: Serverless endpoints for Gemini models. You just call the API, and Google handles the scaling. You pay per token or character.
  • Custom Endpoints: When you fine-tune an open-source model (like Llama 3) from the Model Garden, you deploy it to a dedicated Endpoint. You pay per hour for the underlying Compute Engine VMs (GPUs/TPUs).
SYNAPSE VERIFICATION
QUERY 1 // 1
How are you billed when using the Gemini Foundation Model API on Vertex AI?
Per hour of GPU usage
Per token or character processed
A flat monthly fee
Per training epoch
Watch: 139x Rust Speedup
Google Vertex AI Academy | Free Interactive Course | Infinity AI