Skip to content
← Models
ClosedMicrosoft AI/10 trustVerified
MAI-Image-2.5 logo

MAI-Image-2.5

Microsoft's first in-house image model, launched at Build 2026.

Visit official page →

About

MAI-Image-2.5 is Microsoft AI's first in-house image generation and editing model, unveiled June 2, 2026 at Microsoft Build as part of the seven-model MAI family. Microsoft describes the family as trained from scratch on commercially licensed data with no distillation from third-party models. At launch it ranked third on the Arena AI text-to-image leaderboard and second in image-to-image editing.

The model uses a diffusion-based approach for text-to-image generation and precise surgical edits that preserve layout and composition. It ships in baseline, Flash, and Pro variants, priced from $0.05 per image on Microsoft Foundry, and is live in PowerPoint with OneDrive rollout following. Flash and Pro variants target throughput and portrait quality respectively.

Specs

Context window

Pricing

Free quota

API access

Weights

Closed — API only

Released

June 2, 2026

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

text-to-imageimage-editingpresentationsenterprise-content

Trust score — 8/10

/10 trustVerified

Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 89; Trending score 82/100 from researcher assessment.

Sources