Microsoft

MAI Code 2

Generally availableProprietary1.1M contextReasoning

Summary

MAI Code 2 is a proprietary language model from Microsoft, released on 17 Nov 2026. It accepts text and images and generates text, with a 1.1M-token context window and up to 128K output tokens per response.

Microsoft's larger agentic coding model for debugging, multi-file changes and repository-wide reasoning

Last verified 19 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMicrosoft
Release date17 Nov 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window1.1M (1,050,000 tokens) [models.dev]
Max output128K tokens [models.dev]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]

MAI Code 2 API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of MAI Code 2?

MAI Code 2 has a context window of 1,050,000 tokens (1.1M) and can generate up to 128,000 tokens in a single response, according to models.dev.

Is MAI Code 2 open source?

No. MAI Code 2 is a proprietary model; Microsoft has not released its weights.

When was MAI Code 2 released?

Microsoft released MAI Code 2 on 17 Nov 2026, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GPT-6.2 AstraOpenAI17 Nov 20261.1M$8$40Closed
GPT-6.2 Astra ProOpenAI17 Nov 20261.1M$8$40–
Gemini 4 NeonGoogle DeepMind18 Nov 20261M$3$15Closed
Gemini 4 HydrogenGoogle DeepMind12 Nov 20261M$1.50$7.50Closed
Muse EmberMeta9 Nov 20261M$0.10$0.50Closed
Qwen4 MaxAlibaba (Qwen)16 Nov 20261M$1.41$4.24Closed

Change history

  • Added to the directory

Sources