OpenAI’s o3 and o4-mini Models Now Available in GitHub Copilot and GitHub Models
o4-mini is now rolling out across all paid GitHub Copilot plans
OpenAI’s latest reasoning models—o3 and o4-mini—are now integrated into GitHub Copilot and GitHub Models, bringing advanced coding intelligence and structured reasoning to your development workflow.
"o4-mini is now rolling out across all paid GitHub Copilot plans and o3 is available to Enterprise and Pro+ plans. You can access them through the model picker in Visual Studio Code and in GitHub Copilot Chat on github.com," GitHub said in a blog post.
o3 is the most capable model in the o-series, ideal for complex coding and problem-solving tasks. o4-mini offers efficient performance with low latency, multimodal support, and enterprise-grade tools integration.
GitHub
Optimised for real-world use, both models support function calling, structured outputs, and long-context understanding (up to 200K tokens), helping developers tackle everything from debugging to building agentic tools.
Access & Availability
- o4-mini: Rolling out across all paid Copilot plans
- o3: Available to Enterprise and Pro+ users
Admins can enable model access via Copilot settings.
Both models are also available in the GitHub Models playground—enabling developers to build, test, and iterate with greater speed and precision.
OpenAI released both models recently, calling them the smartest models released by them to date.
"Critically, these models are trained to reason about when and how to use tools to produce detailed and thoughtful answers in the right output formats, typically in under a minute, to solve more complex problems. This allows them to tackle multi-faceted questions more effectively, a step toward a more agentic ChatGPT that can independently execute tasks on your behalf," OpenAI said in a blog postto.
