Image by Author
Google has stepped up in the AI race with the release of its latest experimental models. Following DeepSeek and OpenAI, Google has announced Gemini 2.0 Flash, along with two new experimental models: Gemini 2.0 Pro and Gemini 2.0 Flash-Lite. According to the Google DeepMind team, Gemini 2.0 Pro is their most advanced model yet, excelling in coding performance and handling complex prompts.
In this tutorial, we will learn how to generate a Google API key and use it to access Gemini 2.0 Pro locally via the Msty app. This simple guide will help you experience the latest state-of-the-art AI models without restrictions—and it’s completely free.
What is Gemini 2.0 Pro?
Gemini 2.0 Pro is a cutting-edge multimodal AI model from Google DeepMind, part of the broader Gemini family. Released on January 30, 2025, as an experimental model for developers and Gemini Advanced users, it represents a significant leap in AI capabilities.
Key features include:
- Unmatched coding performance and the ability to handle complex prompts with advanced reasoning and world knowledge.
- A massive context window of 2 million tokens, allowing it to process and analyze extensive information.
- The ability to call tools like Google Search and execute code, enhancing its versatility.
Gemini 2.0 Pro is designed to integrate seamlessly across Google’s ecosystem, offering developers a powerful platform for testing and innovation.
Generating the API Key from Google AI Studio
Visit the Google AI Studio website: https://aistudio.google.com/ and sign into your Google account. You will be directed to the AI playground as shown below. Before generating the API key, ensure that you have access to the Gemini 2.0 Pro mode by clicking on the “Model” tab in the top right corner.
Image from Google AI Studio
After that, click on the blue button in the top left labeled “Generate API Key.” Make sure to copy the API key and save it in a secure place. We will use this API key in the Msty app.
Image from Google AI Studio
Setting up Msty Application
Go to https://msty.app/ and download the latest version of the Msty application.
Image from msty.app
Launch the Msty app and click on the settings gear button in the bottom left corner. Then click on the “Remote Model Provider” tab and press the “+ Add Remote Model Provider” button. Select the provider as Google Gemini, as shown below.
Next, click on the “+ Add Custom Model” button and enter the Gemini Pro model tag: “gemini-2.0-pro-exp-02-05,” then press the “Add” button as shown below.
Using Gemini 2.0 Pro Locally
To access the model, go to the chat window and select the “gemini-2.0-pro-exp-02-05” model from the model selector menu.
After that, start asking questions as if you are using ChatGPT. It provides highly detailed, accurate, and fast responses compared to OpenAI’s o3-mini.
Final Thoughts
I always recommend that people test LLMs and multimodal AI locally, either by downloading the model file or connecting via the API. This allows you to have the same AI experience that you are used to, along with your own customizations and preferences.
Abid Ali Awan (@1abidaliawan) is a certified data scientist professional who loves building machine learning models. Currently, he is focusing on content creation and writing technical blogs on machine learning and data science technologies. Abid holds a Master’s degree in technology management and a bachelor’s degree in telecommunication engineering. His vision is to build an AI product using a graph neural network for students struggling with mental illness.