LLM Reference

MAI-Image-2

mai-image-2

Researched 3d ago

Last refreshed 2026-05-19. Next refresh: weekly.

ProprietaryMultimodalVision

MAI-Image-2 is worth evaluating for vision when its provider route and context window match the workload.

Decision context: Vision task fit, 1 tracked provider route, and research from 2026-05-19.

Use it for

  • Teams evaluating vision
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows

Cheapest output

$33.00

Microsoft Foundry per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-05-19

Researched 3d ago

fresh

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MRoute
Microsoft Foundry$5.00$33.00
Serverless

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

Microsoft AI second-generation image generation model. 2x faster than its predecessor, with improved handling of natural lighting, diverse skin tones, and in-image text. Ranked top-3 on Arena.ai leaderboard at launch. Available via MAI Playground and Microsoft Foundry API; rolling out to Copilot and Bing Image Creator. Official announcement: march 19, 2026.

MAI-Image-2 input tokens at $5/1M, output at $33/1M.

Capabilities

VisionMultimodal

Rankings

Specifications

FamilyMAI
Released2026-03-19
ArchitectureDiffusion
Specializationimage
Trainingfinetuned

Created by

Applied AI products and platforms from Microsoft

Redmond, Washington, United States
Website

Providers(1)