ZMIME
Microsoft · image model · Released Nov 17, 2026

MAI-Image-2.7

MAI-Image-2.7 is an image model from Microsoft, released Nov 17, 2026. It handles text to image and image editing.

  • New
  • Image model
  • Proprietary
  • Text to image
  • Image editing
Arena score
1,475#4 of 64 · image editing
Starting price
—Not published
Largest size
—Not published
References
Yesinput images for editing
Quality & price

How it rates and what it costs

Image editing arena
1,475 ±11#4 of 64 · 3,007 votes

Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Nov 17, 2026.

Specifications

The details

Lab
Microsoft
Type
Image model
Listed on OpenRouter
Nov 17, 2026
Released
Nov 17, 2026
Inputs
Text prompts, Reference images
Output
Images
Can do
Text to image, Image editing
Weights
Proprietary
Availability
1 API host

OpenRouter listing

Same lab

More image models from Microsoft

Questions

About MAI-Image-2.7

How good is MAI-Image-2.7?

In blind side-by-side votes, MAI-Image-2.7 scores 1,475 for image editing (#4 of 64). Higher is better; scores within about 22 points of each other are effectively tied.

Who makes MAI-Image-2.7?

MAI-Image-2.7 is an image model from Microsoft, released Nov 17, 2026.

What can MAI-Image-2.7 do?

MAI-Image-2.7 accepts text prompts and reference images and produces images. In practice: text to image and image editing.

Is MAI-Image-2.7 open source?

No. MAI-Image-2.7 is proprietary; you use it through an API or partner apps.

Where can I use MAI-Image-2.7?

It is listed by 1 API host we track.

What are the alternatives to MAI-Image-2.7?

The closest image models from other labs, by release date, are GPT Image 2.6 Flare (OpenAI, Nov 4, 2026), Nano Banana 2.1 (Google, Oct 6, 2026), FLUX 3 Image (Black Forest Labs, Oct 5, 2026) and Arrow 2 (QuiverAI, Sep 16, 2026).