SSyncDev

MAI Code 2 Flash

SyncDev model directory · Profile updated Nov 18, 2026

Compare with another model

MAI Code 2 Flash is Microsoft AI's low-cost coding model for edits, fixes and explanations, on every GitHub Copilot plan including Free and Student.

Key specifications

Specification score
35.0
Input / 1M tokens
From $0.05
Output / 1M tokens
From $0.25
License
Proprietary

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Indicative GitHub Copilot rates: $0.05 input / $0.005 cached / $0.25 output per 1M until 17 May 2027; then $0.10 / $0.01 / $0.50. Confirm on your Copilot billing page.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Image input

Produces

  • Text output

Capabilities

ReasoningFunction callingVision

What is MAI Code 2 Flash?

Five cents. That is the promotional input price per million tokens for MAI Code 2 Flash in GitHub Copilot, and it explains the model's job better than any benchmark does. Microsoft AI built it for volume: explaining a function, patching a null check, renaming across a file, iterating quickly while you watch.

It also has the widest reach of anything Microsoft launched at Ignite on 17 November 2026. Every Copilot plan gets it, Free and Student included.

Price card

  • Input: $0.05 per 1M tokens (promotional)
  • Cached input: $0.005
  • Output: $0.25
  • After 17 May 2027: $0.10, $0.01 and $0.50

Those are indicative usage-based rates, so confirm them on your own Copilot billing page. Microsoft says the model lands around 65% of GPT-6 Luna's price and about 20% of Claude Haiku 5.5's while staying comparable to both on three coding benchmarks. That comparison is publisher-reported.

Replacing 1.1 Flash on a deadline

If your team pinned MAI-Code-1.1-Flash, you have a date to work to. GitHub deprecates it across Copilot on 18 December 2026 and points users to the latest MAI Code Flash model. Enterprise admins may need to enable the new model in their model policy before then, although new models are switched on by default unless someone has turned that off.

Do the migration now, while both are live.

Surfaces and status

In Copilot it appears in the model picker in VS Code, Visual Studio, the CLI, the cloud agent, the Copilot app, github.com, GitHub Mobile, JetBrains, Xcode and Eclipse. Outside GitHub, it is in a limited-access preview in Microsoft Foundry, sometimes labelled a private preview; either way you will need approval. OpenRouter and Vercel are listed as coming soon. No context window or model ID for direct API use has been published.

A variant called MAI Work Flash, optimised from this model, runs inside Microsoft 365 and Fabric IQ features. It is not offered on its own.

Where Flash stops being the cheap option

Light models get expensive when they need three attempts. Pick twenty small tickets from your backlog and log how many Flash closes on the first try. Then hand the failures to MAI Code 2 and price both runs together. For tab-completion-sized work Flash should win comfortably. For anything touching several files, the full model often costs less in the end. You can weigh other light coders on the code generation page or browse the Microsoft provider page.

How to evaluate MAI Code 2 Flash

Compare the model on the work you need to complete.

Tasks and inputs

MAI Code 2 Flash is listed for Text generation, Coding & Code Generation. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

The listed route has starting rates of $0.05 input and $0.25 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.

Frequently asked questions

It is available on Copilot Free and Student plans as well as paid plans, and billed under usage-based billing at $0.05 input and $0.25 output per million tokens on promotional rates until 17 May 2027.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

Microsoft

MAI Code 2

MAI Code 2 is Microsoft AI's coding model for multi-file work, debugging and frontend builds, live in GitHub Copilot at $0.50/$2.50 per 1M (promo).

— context

Microsoft

MAI Cyber 2 Flash

MAI Cyber 2 Flash is Microsoft AI's security model for vulnerability discovery and threat investigation, with a 1M-token context, shipping in MDASH.

1M context

Google

Gemini 4 Hydrogen

Gemini 4 Hydrogen is Google's fast, lower-cost Gemini 4 model for everyday coding and agentic execution, with a 1M context, xhigh thinking and a free tier.

1.05M context

OpenAI

GPT-6 Cyber

GPT-6 Cyber is OpenAI's restricted security model for authorised vulnerability investigation, reproduction and fix verification, for Daybreak Red customers.

1.05M context

ricursive

Ripple-65B Preview

Ripple-65B Preview is Ricursive Intelligence's first open model: a dense 65B coding-focused transformer trained from scratch, with a 1M-token context.

1.05M context

particle-ai

Particle-1

Particle-1 is Particle's first software-engineering model, an RL-tuned DeepSeek V4.1 Flash that aims to solve coding tasks with fewer tokens.

1.05M context