Google Gemini Can Now Discuss Multiple Photos in One Prompt

Google has recently added a much-requested improvement to its Gemini AI platform, making it easier for users to interact with the chatbot using multiple files or images at once. To better understand what has changed now, know that before this update, Gemini supported only a file or an image per prompt. This was a limitation for people who wanted to ask questions about multiple documents or compare images. Now, with the new update, users can upload up to 10 files or images in one go. This change applies to both the free version of Gemini and the Gemini Advanced plan.

The update is available on the Gemini web version and is being gradually released on the Android and iOS apps. Some users may not see the feature right away because Google is rolling it out in phases. This is common with major updates, so don’t worry if you don’t see the update right away. 

How to use the feature

To use the feature, you can click or tap on the plus (+) icon next to the chat input box. This opens your file browser or gallery. Select multiple files at once. However, the number of images in one prompt is capped at 10 so if you try to upload more than 10 items, Gemini will show a message saying you’ve hit the limit and some files were not uploaded.

The latest development in Google’s Gemini AI, specifically its multiple image upload feature, marks a significant step in catching up with competitors like OpenAI’s ChatGPT and others in the multimodal AI space. Below is a comparison of Gemini’s multiple image upload capabilities with its main competitors, focusing on functionality, limitations, and user experience as of May 6, 2025.

Previously, Gemini was limited to single-image uploads, with additional images replacing the previous one, which was a major drawback. With the latest update, that changes. The AI chatbot can now analyse up to 10 images in a single prompt, elaborating on their contents and providing insights, which reduces the time needed compared to uploading images individually. 

Gemini’s closest competitor- OpenAI’s ChatGPT also supports multiple image uploads on both free and paid tiers (ChatGPT Plus, Team, Enterprise), with no specific limit on the number of images per prompt mentioned in recent sources.  It is available across web and mobile apps, with a broader file format support compared to Gemini. 

Copilot, powered by GPT-4, supports image uploads and analysis, including multiple images, given its integration with Microsoft’s ecosystem. Perplexity also supports image uploads, but multiple image uploads are not a focal point. It’s more focused on real-time web search and research.

Gemini’s addition of multiple image uploads closes a critical gap with ChatGPT, which has long supported this feature. The ability to handle up to 10 images per prompt and integrate with Google Workspace makes Gemini a strong choice for users in Google’s ecosystem, particularly for image-heavy tasks like creative workflows or technical analysis. 

Read more: Google To Roll Out Gemini AI for Kids under 13: Report