Radar / AI coding tools / MAI Code 2 and Code 2 Flash
MAI Code 2 and Code 2 Flash: Microsoft's own coding models land in Copilot
Microsoft's in-house coding models debut at Ignite: MAI Code 2 for deep debugging and multi-file work, and a lighter Flash for quick edits, both generally available in GitHub Copilot.
Why it matters
Microsoft claims Code 2 delivers 96% of Claude Opus 5.5's coding quality at 5% of the cost and 98% of GPT-6.1 Sol's at 40% - its own models are now a direct Copilot alternative to OpenAI and Anthropic.
What you could build with it
An indie developer could build a pull-request review service for small teams that runs MAI Code 2 over every change, flagging risky edits and suggesting fixes, and charge per repository per month - the low per-task cost makes the unit economics work where frontier models would not.
Does it hold up?
Generally available in GitHub Copilot from launch day, so Copilot users can switch models in the picker immediately; the headline price claims rest on a 50% promotional price and Microsoft's own benchmarks, and the models are explicitly not tuned for long-horizon agentic work yet.
Built with MAI Code 2 and Code 2 Flash
- Microsoft Launches MAI Code 2 Coding Models in GitHub Copilotai-parabellum · Launch breakdown with Copilot plan eligibility: Code 2 on Pro, Pro+, Max, Business and Enterprise; Flash also on Free and Student.
- MAI Code 2 vs Flash: Copilot access and three benchmarkspromptszone · Benchmark table: Code 2 leads DeepSWE 1.1 at 73.2% while Flash leads SWE Atlas, plus the Dec 18 retirement date for MAI-Code-1.1-Flash.
- Microsoft launches specialized AI models, claiming steep savings over rivalssuperpowerdaily · Ignite overview: the seven-model MAI family, including Cyber 2 Flash and Image 2.7, and the caveat that the price claims use a 50% promotional price.
Learn more
First spotted on article: source.
More AI coding tools
Chrome DevTools MCP: give your coding agent a real browserOfficial MCP server from the Chrome team that lets coding agents drive a live Chrome — console, network, traces…coding · JEV 0.82Orca: the agent development environment for running coding-agent fleetsStably AI's open-source desktop app for running many CLI coding agents side by side — Claude Code, Codex, Cursor and…coding · JEV 0.78Open Code Review: Alibaba's hybrid AI code reviewer, now past 50,000 starsAlibaba's open-source code review CLI (Apache 2.0) pairs deterministic rules with an LLM agent to review git diffs…coding · JEV 0.77Astryx: Meta's agent-ready design system, open sourceMeta open-sourced the React 19 + StyleX design system behind 13,000 internal apps: 150+ accessible components, themes…coding · JEV 0.76GitHub Spec Kit — spec-driven development for coding agentsGitHub's open-source toolkit that gives any coding agent a structured spec, plan, tasks, implement workflow, so specs…coding · JEV 0.75shadcn/improve: audit with your best model, execute with your cheapestAn MIT-licensed Agent Skill that audits any codebase across nine categories with parallel subagents, vets its own…coding · JEV 0.75
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.