# MAI-Code-1-Flash > A lightweight, agentic coding model from Microsoft AI, built into GitHub Copilot and Visual Studio Code for fast, token-efficient help across everyday software engineering tasks. MAI-Code-1-Flash is a coding model from Microsoft AI built for fast, efficient help in everyday developer workflows. It runs inside GitHub Copilot in Visual Studio Code, where it appears in the model picker and can be selected automatically by Copilot's Auto picker. Microsoft says the model was built end-to-end by its own team using clean and appropriately licensed data. ## What It Is MAI-Code-1-Flash is a lightweight, agentic member of the MAI (Microsoft AI) model family, introduced on June 2, 2026 alongside several other MAI models. According to Microsoft, the model was trained directly with the GitHub Copilot harnesses used in production, so it learns to interact with the surrounding tools and systems involved in agentic coding tasks. The company frames this alignment between training, evaluation, and production as the reason offline improvements should translate into real-world Copilot quality, and positions the model around delivering useful coding help with better efficiency rather than optimizing only for benchmarks. ## Agentic Coding in Developer Environments The model is designed to plan and reason through coding tasks from start to finish and to take initiative across multi-step workflows, making decisions and adapting without waiting for input at each step. The homepage lists fluency across a broad range of programming languages and frameworks, including Python, C++, Java, JavaScript, TypeScript, .NET, HTML, and CSS. Microsoft describes it as custom-trained for native Visual Studio Code integration so it works closely with GitHub Copilot. ## Adaptive Thinking and Token Efficiency Microsoft says MAI-Code-1-Flash was trained with adaptive solution length control, letting it stay concise on simple requests and spend more reasoning budget when a problem requires deeper analysis or broader code changes. The company reports the model solving harder problems with up to 60% fewer tokens on SWE-Bench Verified, which it says reduces latency, lowers cost, and makes interactive workflows feel smoother. It also emphasizes strong instruction-following across single-turn and multi-turn scenarios. ## How Microsoft Positions It Microsoft presents MAI-Code-1-Flash as a price-to-performance alternative to Claude Haiku 4.5, reporting that it leads across the coding benchmarks the company tested, including a roughly 16-point margin on SWE-Bench Pro (the company cites 51.2% versus 35.2%). Microsoft also describes a 186-question adversarial reasoning benchmark on which it reports 85.8% adjusted accuracy, while noting that some categories such as Einstellung traps remained below 50%. These figures are vendor-published results from Microsoft's own announcement. ## Availability The model is rolling out to GitHub Copilot individual users in Visual Studio Code, with Microsoft stating that no additional setup is required. As the rollout progresses, users may see Copilot route tasks to the model through the Auto picker or find it directly in the model picker. Microsoft also offers a web playground for trying MAI models. ## Features - Agentic coding trained for the GitHub Copilot harness - Adaptive thinking that scales reasoning budget to task complexity - Adaptive solution length control for token-efficient responses - Strong single-turn and multi-turn instruction following - Plans and reasons through coding tasks from start to finish - Autonomous multi-step agentic execution - Broad programming language and framework support - Optimized for GitHub Copilot in Visual Studio Code - Available via the GitHub Copilot model picker and Auto picker ## Integrations GitHub Copilot, Visual Studio Code ## Platforms VSC_EXTENSION, WEB ## Pricing Free ## Links - Website: https://microsoft.ai/models/mai-code-1-flash/ - Documentation: https://microsoft.ai/pdf/MAI-Code-1-Flash-Model-Card.PDF - EveryDev.ai: https://www.everydev.ai/tools/mai-code-1-flash