Skip to main content

Microsoft AIImage modelPublic preview

MAI Image 2.7

Summary

MAI Image 2.7 generates images from text and can make targeted edits to existing images. Microsoft offers it in public preview in Foundry.

All specifications

Input and output

Input
Text and images.
Source: Input
Output
Images.
Source: Output
Input limit
32,000 tokens according to Foundry documentation.
Source: Input limit
Capabilities
Text-to-image generation and image editing. Both variants support transparent backgrounds.
Source: Capabilities

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Available in public preview through Microsoft Foundry, MAI Labs, and selected partners.
Source: Access
Shutdown
None announced
no source

API

Model ID in Foundry
MAI-Image-2.7
Source: Model ID in Foundry

Further details

Foundry model version
Nov 2, 2026
Source: Foundry model version
Initial preview
Image editing became available in MAI Playground, Arena, and Artificial Analysis on October 27, 2026. The Foundry preview with image generation followed on November 17.
Source: Initial preview
Weights and license
Proprietary hosted model. Public downloadable weights and a model license are not specified.
Source: Weights and license

Prices

Launch price
About $35 per 1,000 images according to Microsoft.Source