Google Gemini

AI Model Provider LLM document parsing

This item was not updated in last three versions of the Radar. Should it have appeared in one of the more recent editions, there is a good chance it remains pertinent. However, if the item dates back further, its relevance may have diminished and our current evaluation could vary. Regrettably, our capacity to consistently revisit items from past Radar editions is limited.

Jan 2025

Trial

Google Gemini is Google's latest multimodal AI model, designed to work with various types of information including text, code, audio, images, and video. There are a verity of model categories inpluding Pro (complex logic and reasoning), Flash (high intelligence and speed), Lite (low-cost, high speed), Nano(for fast inference on edge devices)

Models Overview

Provisioning Platform:

MOHARA is trialing use of Gemini for a verity of document parsing and processing tasks due to its exceptionally large context windows and multi-modal contextual understanding. The Gemini models provide high intelligence at very low latency and low cost. Use of these models is also well suited for poc testing as they can be used for free.

WARNING: The free tier does not offer data privacy and must NOT be used with with sensitive company or client data.