The Gemini API from Vertex AI gives you access to the latest generative models from Google — the Gemini family of models.
Generally speaking, the "Vertex AI Gemini API" is actually just a set of
endpoints within the larger Vertex AI API surface
(aiplatform.googleapis.com
).
These endpoints are specifically for inference using the Gemini models.
Various products and interfaces provide access to the Vertex AI Gemini API:
Vertex AI in Firebase client SDKs (this documentation): SDKs that allow you to call the Gemini API directly from your mobile and web apps. They're available for Apple platforms, Android, Web, and Flutter.
Vertex AI server SDKs: SDKs that allow you to call the Gemini API server-side. They're available for Python, Go, Node.js, and Java.
REST API: Direct endpoints for the Gemini API.
Vertex AI Studio: A web UI "playground" where you can design, test, and customize your prompts.
Next steps
Try out the capabilities of the Gemini API
- Build multi-turn conversations (chat).
- Generate text from text-only prompts.
- Generate text from multimodal prompts (including text, images, PDFs, video, and audio).
- Generate structured output (like JSON) from both text and multimodal prompts.
- Use function calling to connect generative models to external systems and information.