Google Gemini API

Access Google's frontier multimodal AI models (Gemini 3 Pro, 2.5 Flash) to build applications with text, code, image, and video understanding.

The Gemini API delivers direct access to Google's most powerful generative AI models: Integrate Gemini 3 Pro for advanced reasoning or use Gemini 2.5 Flash for speed and efficiency. Leverage its native multimodal capabilities to process and generate content across text, code, images, and video in a single API call. Key features include a massive 1-million-token context window, reliable structured output (JSON), and built-in function calling for connecting the model to external tools and services.

https://ai.google.dev/gemini-api/docs