# MAI-Code-1-Flash

[Canonical model page](https://headlessthrones.com/models/microsoft-mai-code-1-flash) · [Model library](https://headlessthrones.com/models)

Public catalog reference from Headless Thrones. Exact catalog ID: `microsoft-mai-code-1-flash`. Catalog source-check date: 2026-10-23.

This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial.

Current catalog answers

## What to know about MAI-Code-1-Flash

AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.

[Exact model](https://headlessthrones.com/models/microsoft-mai-code-1-flash#model-answer-identity) · [Access](https://headlessthrones.com/models/microsoft-mai-code-1-flash#model-answer-access) · [Dates & knowledge](https://headlessthrones.com/models/microsoft-mai-code-1-flash#model-answer-dates) · [Inputs & outputs](https://headlessthrones.com/models/microsoft-mai-code-1-flash#model-answer-modalities) · [Model details](https://headlessthrones.com/models/microsoft-mai-code-1-flash#model-answer-research)

### Which MAI-Code-1-Flash does this page describe?

MAI-Code-1-Flash is a model record from **Microsoft** in the MAI family. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

The recorded model identifier or checkpoint is `MAI-Code-1-Flash`. Use that exact identifier when checking documentation or a provider listing. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

### How can you access MAI-Code-1-Flash?

The catalog documents **GitHub Copilot** access  for MAI-Code-1-Flash. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

As of the catalog check, this version was listed without confirmed general availability. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

### What dates are documented for MAI-Code-1-Flash?

**Release date: June 2, 2026.** [Source](https://microsoft.ai/news/introducingmai-code-1-flash/) This is a release milestone, not a knowledge or training cutoff. The source labels this “Official launch announcement date.”

Neither a knowledge cutoff nor a training-data cutoff is established here. A release date, repository upload or filename cannot supply those missing dates.

### What can MAI-Code-1-Flash receive and generate?

Documented inputs: **text**. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

Documented outputs: **text**. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.

### What distinguishes MAI-Code-1-Flash?

These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.

**Distribution at announcement**: The June 2026 announcement describes rollout to individual GitHub Copilot users in VS Code through the explicit model picker and Auto routing; it does not establish a standalone public API. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

**Reasoning behavior**: Microsoft describes adaptive response length: concise treatment of simple requests and more reasoning for complex coding work. Its benchmark gains are vendor results rather than tests by Headless Thrones. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

**Training provenance**: Microsoft says MAI-Code-1-Flash was trained from the ground up without distillation from third-party models. This is a publisher provenance statement, not independent verification of the training corpus. [Source](https://microsoft.ai/news/introducingmai-code-1-flash/)

**Catalog qualifications:** Documented model available through GitHub Copilot; a standalone public API and downloadable weights were not verified.

**Evidence still missing here:** context or input capacity and knowledge and training-data cutoffs. Missing documentation is not evidence that a feature is unavailable.

Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model.

Keep the exact version in view

## Other MAI models from Microsoft.

These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.

### [MAI-Code-1.1-Flash](https://headlessthrones.com/models/microsoft-mai-code-1-1-flash)

Open weights · 256,000 context tokens

### [MAI-1-preview](https://headlessthrones.com/models/microsoft-mai-1-preview)

API

### [MAI-Cyber-1-Flash](https://headlessthrones.com/models/microsoft-mai-cyber-1-flash)

MDASH private preview for approved defenders

### [MAI-DS-R1](https://headlessthrones.com/models/microsoft-mai-ds-r1)

Open weights

### [MAI-Thinking-1](https://headlessthrones.com/models/microsoft-mai-thinking-1)

API