Microsoft MAI Code 2
Microsoft's everyday enterprise coding model from Ignite 2026: 98% of GPT-6.1 Sol's averaged coding score at ~40% of the cost and 96% of Claude Opus 5.5's at ~5% (vendor-reported, promo pricing). Not tuned for science or very long-horizon agent work.
Interactive Token Cost Estimator (MAI Code 2)
Architectural Strengths & Target Workloads
- Averaged DeepSWE 1.1 / Terminal Bench 2.1 / SWE-Atlas / FrontierCode 1.1: 98% of GPT-6.1 Sol (vendor-reported)
- Preferred over GPT-6 Sol 64% of the time in blind frontend evaluations
- $0.025 / 1M cached input in Copilot (promo)
Primary Engineering Workloads: Everyday Multi-File Changes · Debugging & Refactoring · Dashboards & Frontend UI.
Frequently Asked Questions (MAI Code 2)
How much does Microsoft MAI Code 2 cost per 1M tokens?
Microsoft MAI Code 2 is priced at $0.50 per 1M uncached input tokens, $0.03 per 1M cached input tokens, and $2.50 per 1M output tokens (GitHub Copilot (Pro, Pro+, Max, Business, Enterprise) at 50% promo rates until May 17, 2027; then $1.00 / $0.05 / $5.00 per 1M. Max output not published (128K placeholder). OpenRouter, Vercel, OpenCode, Kilo announced as "soon".).
What is the context window of Microsoft MAI Code 2?
It supports up to 1.05M tokens (per Microsoft via AI Ping) (1,050,000 tokens) and a maximum generation output of 128,000 tokens.
MAI Code 2 and Code 2 Flash: Microsoft's In-House Coding Models Land in GitHub Copilot at $0.50 / $2.50 and $0.05 / $0.25
At Ignite 2026, Microsoft AI released seven models built for price-performance rather than the frontier. The two that matter most to developers are already in Copilot's model picker. Microsoft says it gets near GPT-6.1 Sol on everyday coding at 40% of the price, and the Flash model is free-tier eligible.
Read Full Technical Dispatch (5 min read) →