Google Gemini API

Google Gemini multimodal API via Google AI Studio.

Definition

Gemini API features: 2M context window (Gemini 1.5 Pro), native multimodality (image, video MP4, audio MP3), code execution sandbox, grounding via Google Search, function calling, JSON mode, context caching. Models: Gemini 2.5 Pro / Flash, Gemini 1.5 Pro / Flash, Gemini Nano (Android on-device). Python, Go, Node.js, Dart SDKs.

Origin

Google DeepMind, Gemini 1.0 December 2023, 1.5 February 2024, 2.0 December 2024, 2.5 March 2025.

Usage

Direct competitor to OpenAI and Anthropic. Strength among Google ecosystem customers (GCP, Workspace, Android).

Related terms

• Google DeepMind — éditeur.
• Vertex AI Generative — enterprise version.
• Anthropic Claude API — concurrent.