The list of available models in Github Copilot keeps growing. Whereas last year you could already use GPT-4o, o1, o1-mini and Claud Sonnet 3.5, now you can also try OpenAI o3 and Google Gemini 2.0 Flash.
About Gemini 2.0 Flash
The Gemini 2.0 Flash model is a highly efficient, large language model (LLM) designed for high-volume, high-frequency tasks. It excels in multimodal reasoning, handling inputs like text, images, and audio, and providing text outputs. With a context window of 1 million tokens, it can process vast amounts of information quickly and accurately. Gemini 2.0 Flash is optimized for speed and practicality, making it ideal for everyday tasks, coding, and complex problem-solving.
GitHub Copilot uses Gemini 2.0 Flash hosted on Google Cloud Platform (GCP). When using Gemini 2.0 Flash, prompts and metadata are sent to GCP, which makes the following data commitment: Gemini doesn't use your prompts, or its responses, as data to train its models.
About OpenAI o3
The OpenAI o3 model is a generative pre-trained transformer designed for advanced reasoning and problem-solving tasks. It builds on the capabilities of its predecessor, the o1 model, and is optimized for complex tasks like coding, mathematics, and science1. The o3 model features improved logical reasoning, better memory retention, and enhanced problem-solving capabilities. It also includes a smaller variant, o3-mini, which offers similar functionalities with reduced computational requirements.
Activating these models
If you have an individual Copilot license, you can activate these models using the following steps:
- On any Github page, click on your profile in the top right corner, and click on Your Copilot:
- You arrive on the Copilot settings page, where you can enable the new models:
If your Copilot license is managed through an organization, you can activate these models using the following steps:
- On any Github page, click on your profile in the top right corner, and click on Your organizations:
- Click on Settings for the organization you want to configure.
- Go to Copilot in the Code, planning, automation section and select Models from the dropdown:
- Change the settings to Enabled for the models that you want to allow:
That’s it!
More information
Multi model support in Github Copilot
Using Gemini 2.0 Flash in GitHub Copilot - GitHub Docs
The next chapter of the Gemini era for developers - Google Developers Blog