ai/list101

MAI Code 2

microsoft.ai

Coding model for debugging, multi-file implementation, repository reasoning, and interface development, available through eligible paid GitHub Copilot plans.

Llm ModelsDeveloper Tools
Visit website
Screenshot of MAI Code 2 official website
Pricing
Paid
Available on
GitHub Copilot
Category
Llm Models

What is MAI Code 2?

MAI Code 2 is Microsoft's coding model for repository-based software engineering. It accepts text and images and produces text.

GitHub lists it as generally available in Copilot and recommends it for deep reasoning and complex, multistep coding. It is relevant to developers and engineering teams working on changes that require understanding relationships across a codebase.

Key features

Coordinated repository changes

Supports multi-file implementation, refactoring, debugging and test-driven verification.

Repository questions and terminal work

Answers codebase questions and supports multistep shell, file and search workflows, depending on deployment.

Visual coding context

Accepts screenshots and UI mockups for coding tasks.

Configurable reasoning

Supports low, medium, high, xhigh and max reasoning effort.

Who is it for?

Maintainers tracing repository bugs

Ask for an explanation of a failure and a proposed fix across the affected files.

Engineers coordinating refactors

Describe a structural change and request an implementation with relevant verification.

Frontend developers using mockups

Provide a UI reference and ask for a corresponding implementation in an existing project.

How to use MAI Code 2

  1. Check that MAI Code 2 is available for your Copilot plan and client, and that your organization permits model switching.
  2. Open Copilot Chat and choose MAI Code 2 from the model dropdown.
  3. Provide the task and relevant repository context or visual reference.
  4. Review proposed changes and run appropriate project checks before accepting the result.

MAI Code 2 pricing

Paid

Copilot usage consumes plan allowances, with metered token usage converted into GitHub AI Credits. Additional usage follows the plan's billing rules.

Copilot metered usage, promotional rates

USD 0.50 input, USD 0.025 cached input and USD 2.50 output per million tokens
Metered token consumption converted into GitHub AI Credits

Promotional model rates until May 17, 2027; these are usage rates rather than subscription prices. Starting May 17, 2027, rates become USD 1 input, USD 0.05 cached input and USD 5 output per million tokens.

Check current pricing ↗

What to know before you use it

  • Access depends on Copilot plan and client. Organization owners can restrict models, and Business organizations must permit model switching.
  • The documented release is hosted only; model weights are not distributed for download or local deployment.
  • Long sessions can repeat calls, drift or stop before verification; quality can decline near the context limit. Higher reasoning effort increases latency and token usage without guaranteeing improvement.
  • The release is optimized for English code production only. Other languages and uncommon programming languages have limited evaluation.

Frequently asked questions

Is MAI Code 2 available in GitHub Copilot?

Yes. GitHub lists it as generally available, subject to plan, client and organization model policies.

Does selecting it in Chat change inline suggestions?

No. Changing the Copilot Chat model does not change the model used for inline suggestions.

When should I consider MAI Code 2 Flash?

GitHub positions Flash for fast code completions, explanations and everyday coding. MAI Code 2 is positioned for deeper reasoning and complex multistep work.

MAI Code 2 alternatives

MAI Code 2 Flash

Consider Flash for fast code completions and explanations; GitHub recommends MAI Code 2 for deeper reasoning and complex multistep coding.