LLM Reference

MAI-Code-1

Released
2026-06-02
Last refreshed
2026-06-15
Status
Researched 45d ago
ProprietaryCommercial use: conditionalCoding

MAI-Code-1 is worth evaluating for coding when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
MAI
Released
2026-06-02
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by

Applied AI products and platforms from Microsoft

Redmond, Washington, United States
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · Microsoft Foundry

About

MAI-Code-1 is Microsoft AI's inference-efficient coding model tuned for the GitHub and developer ecosystem. It is integrated into GitHub Copilot and Visual Studio Code for more capable agentic coding tasks than the lighter Flash variant. Microsoft had not published context window, parameter count, benchmark scores, or standalone token pricing at launch, so treat it as a Copilot-route coding model until more technical details are released.

MAI-Code-1 is a proprietary model in the MAI family. This page tracks provider routes through Microsoft Foundry. No headline benchmark score is tracked for MAI-Code-1 yet.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

When was MAI-Code-1 released?

MAI-Code-1 was released on 2026-06-02.

Which providers offer MAI-Code-1?

MAI-Code-1 is available from 1 provider: Microsoft Foundry.