Microsoft MAI-Image-2.5 for photorealistic and artistic text-to-image generation.
Added Jun 3, 2026
Approx. Price
$0.005 per image
Model Type
text-to-image
Settings
Generation controls available for this model.
Images Per Run
Up to 1
Output images
Input Images
Up to 1
Reference/edit images accepted • Route max 30 MB
Output Sizes
Aspect Ratio
Default
auto
Number of Images
Default
1
Resolution
Default
auto
Options (8)
auto (Auto), 1:1 (Square), 16:9 (Landscape), 9:16 (Portrait) +4 more
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#5 / 147
ELO
1303.0
Appearances
15,606
95% CI
-9/9
Image Editing
#3 / 67
ELO
1257.0
Appearances
11,289
95% CI
-8/8
Release Date 2026-06 · Matched as MAI-Image-2.5
Artificial Analysis APIRelated image models
Compare MAI-Image-2.5 with similar models from the same provider or model family.
Muse Image
meta/muse-image/text-to-imageMeta Muse Image generates high-fidelity images with strong instruction following, detailed typography, plots, and QR codes. Upload up to 10 reference images to switch automatically to edit mode.
Recraft V4 Style Pro
recraft-ai/recraft-v4-style-pro/text-to-imageRecraft V4 Style Pro creates premium raster images that consistently follow up to 10 style references or a reusable Recraft Pro style ID.
Recraft V4 Style Pro Vector
recraft-ai/recraft-v4-style-pro/text-to-vectorRecraft V4 Style Pro Vector generates premium vector graphics that consistently follow up to 10 style references or a reusable Recraft Pro style ID.
Recraft V4 Style
recraft-ai/recraft-v4-style/text-to-imageRecraft V4 Style creates consistent raster assets from a prompt plus up to 10 style references or a reusable Recraft style ID.
Recraft V4 Style Vector
recraft-ai/recraft-v4-style/text-to-vectorRecraft V4 Style Vector creates consistent vector assets from a prompt plus up to 10 style references or a reusable Recraft style ID.
Krea 2 Turbo
wavespeed-ai/krea-v2/turboKrea 2 Turbo is a fast 12.9B open-weights image model with native 1K and 2K generation plus optional image-to-image guidance.