Multi Image upload for analysis

Please make it possible to upload more than one image for analysis using the new vision model. For example I am using https://llmvision.org/ to process images from a security camera and notify based on movement etc. It works well with Gemini Flash and other LLM. The idea is to upload 3 (or more) images and ask the LLM to describe what it sees. The API limits this to one image per request but when processing a camera feed there is a greater chance of missing context if you can only provide one frame for analysis.