gemini-2.5-flash-lite

This tutorial demonstrates building a stateful chat application using React and the Gemini API. It leverages React's state management to maintain conversation history (`messages`, `input`, `isLoading`), automatically scrolling to new messages using `useRef` and `useEffect`. The core functionality lies in `callGeminiAPI`, which sends the entire conversation history to the Gemini API for context-aware responses, incorporating exponential backoff for error handling. The UI, built with JSX and Tailwind CSS, displays messages differently based on sender (user/model) and includes a simple input form. The complete code is provided for a functional application.

Gemini, a multimodal model, processes text, images, videos, and audio. Multimodal prompts combine different data types (e.g., an image and a question) in a single request. The API accepts an array of "parts," each a text string or inline data (like a base64-encoded image). A Python example demonstrates sending an image and text prompt to the Gemini API to analyze the image. Best practices include specific instructions, placing images before text in the `contents` array, and using the correct MIME type for image data.

A quickstart on making your first request to the Gemini API to generate text.