Nano GPT logo
NanoGPT

MAI-Image-2.6 Flash

microsoft/mai-image-2.6-flash
BackTry Model

MAI-Image-2.6 Flash

microsoft/mai-image-2.6-flash
BackTry Model

A faster, lower-cost MAI image model for product visuals, creative drafts, and edits to an uploaded image.

Added Sep 4, 2026

Approx. Price

$0.033 per image

Model Type

both

Settings

Generation controls available for this model.

Images Per Run

Up to 4

Output images

Input Images

Up to 1

Reference/edit images accepted • Route max 30 MB

Output Sizes

Square
Portrait
Landscape
up to 1,536px

Aspect Ratio

Default

1:1

Number of Images

Default

1

Resolution

Default

1024x1024

Options (8)

1024x1024, 1152x864, 864x1152, 1536x1024 +4 more

Benchmarks

Human preference benchmarks sourced from Artificial Analysis.

Text to Image

#8 / 157

ELO

1100.0

Appearances

5,141

95% CI

-10/10

Image Editing

#4 / 74

ELO

1110.0

Appearances

5,422

95% CI

-9/9

Release Date 2026-09 · Matched as MAI-Image-2.6-Flash

Artificial Analysis API

Examples

Loading examples…

Compare MAI-Image-2.6 Flash with similar models from the same provider or model family.

MAI-Image-2.6

microsoft/mai-image-2.6

Microsoft’s image model for detailed photography, product imagery, accurate lettering, and precise edits to an uploaded image.

MAI-Image-2.5

microsoft/mai-image-2.5/text-to-image

Microsoft MAI-Image-2.5 for photorealistic and artistic text-to-image generation.

FLUX.2 [flash]

flux-2-flash

FLUX.2 [flash] is a fast text-to-image model built for low-latency, high-volume generation with realistic renders and crisp on-image text. A strong default for rapid iteration, batch pipelines, and production creatives.

FLUX.2 [flash] Edit

flux-2-flash-image-to-image

FLUX.2 [flash] Edit delivers prompt-based image editing for fast style shifts, background changes, and targeted retouching while keeping composition stable.

Gemini Image Edit

gemini-flash-edit

Replaced by Nano Banana. Edit an existing image using Gemini based on a text prompt. Google-based, so quite censored.

Bria FIBO Generate 1.5

bria/fibo-generate-1.5/text-to-image

Bria FIBO Generate 1.5 creates commercially safe images from text prompts, with optional reference-image guidance, photoreal styling, structured prompts, and up to 4MP output.