Overview
MAI Code 2 Flash is the lighter sibling of MAI Code 2, announced by Microsoft AI on 17 November 2026. Microsoft aims it at high-volume work such as code explanations, targeted edits, routine fixes and rapid iterations.
Microsoft says it performs comparably to GPT-6 Luna and Claude Haiku 5.5 at a fraction of their cost, and its model page puts the cost at one-fifth of Haiku's. These are Microsoft's own results, shown at a 50% promotional price.
MAI Code 2 Flash is available in GitHub Copilot and in limited-access preview on Microsoft Foundry. The launch post states no context window, parameter count or per-token price.
| Released | 2026-11-17 |
|---|---|
| License | Proprietary |
| Weights | API only |
| Modalities | Text |
| Status | Available |
Strengths
- Built for high-volume, low-effort coding tasks such as quick edits and routine fixes
- Comparable to GPT-6 Luna and Claude Haiku 5.5 at a fraction of the cost, per Microsoft
- Available in GitHub Copilot at launch
Best for
- Reach for it for code explanations and targeted edits
- Reach for it for routine fixes and fast iteration loops
- Reach for MAI Code 2 instead for deep debugging and repo-wide changes
MAI Code (coding models) — every version
The full lineage of the MAI Code (coding models) line, newest first. Every version has its own page — click any to compare specs, benchmarks and pricing.
| Version | Released | Context | License |
|---|---|---|---|
| MAI Code 2current | 2026-11-17 | — | Proprietary |
| MAI Code 2 Flash | 2026-11-17 | — | Proprietary |
FAQ
Where can I use MAI Code 2 Flash?
MAI Code 2 Flash is available in GitHub Copilot and in limited-access preview in Microsoft Foundry. Microsoft lists OpenRouter, Vercel, Hermes, Open Code and Kilo as coming soon.
How is MAI Code 2 Flash different from MAI Code 2?
Microsoft positions MAI Code 2 Flash for high-volume routine work such as explanations, targeted edits and fixes, while MAI Code 2 targets deep debugging, multi-file implementation and repo-wide reasoning.
