Leveraging the Gemini Pro Vision model for image understanding, multimodal prompts and accessibility

1. Which of the following Gemini models supports image prompting?

   Gemini Pro

   Gemini Ultra

   Gemini Pro Vision & Gemini Ultra Vision

   Gemini Nano

2. What does the error “[400 Bad Request] Image input modality is not enabled for models/gemini-pro” suggest is going wrong when calling the Gemini API?

   The developer’s API key was not valid

   The image sent to the API was too large

   The image sent to the API was offensive

   The developer forgot to encode the image into Base 64 encoding

   The developer did not select an image modality compatible model

3. The Gemini model can solve basic geometric or logic based problems based on images:

   True

   False

error_outline An error occurred when grading the quiz. Please try again.