[{"data":1,"prerenderedAt":12},["ShallowReactive",2],{"stack-tr-en-gemini":3},{"tagline":4,"description":5,"strengths":6,"useCase":11},"Google's multimodal models, available via API.","Gemini is Google's family of multimodal models, capable of reasoning over text, images, audio, and video with long context. Accessible via the Gemini API and Vertex AI, it integrates naturally into applications and IT systems already on Google Cloud.",[7,8,9,10],"Natively multimodal: text, image, audio, and video input.","Long context window for documents and extended conversations.","Available via Gemini API and Vertex AI (GCP governance).","Seamless integration with the Google Cloud ecosystem.","Multimodal analysis, RAG on long documents, Google Cloud integration.",1792675978921]