LLM Reference

MAI-Image-2.5

Released
2026-06-02
Last refreshed
2026-06-15
Status
Researched 45d ago
ProprietaryCommercial use: conditionalMultimodalVision

MAI-Image-2.5 is worth evaluating for vision when its provider route and context window match the workload.

Use it for

  • Teams evaluating vision
  • Workloads that can use a 32k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows
Specifications
Family
MAI
Released
2026-06-02
Context
32k
Architecture
Diffusion
Specialization
image-generation
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by
Microsoft AI

Applied AI products and platforms from Microsoft

Redmond, Washington, United States
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · Microsoft Foundry

Providers(1)
Microsoft Foundry
View 1 provider route
Links
Website

About

MAI-Image-2.5 is a Microsoft AI text-to-image generation and image-to-image editing model. It supports precise edits such as object removal and replacement, attribute changes, inpainting, text updates, and artifact cleanup while preserving composition. Microsoft positions it for high-fidelity portraits, accurate text rendering inside images, and Azure AI Foundry Global Standard deployment across seven regions. It ranked #2 on the Arena AI image editing leaderboard and #3 on the Arena AI text-to-image leaderboard at launch, but no LLMReference-standard numeric image benchmark row is available yet.

MAI-Image-2.5 is a proprietary model in the MAI family. The structured metadata tracks a 32k-token context window and multimodal input. This page tracks provider routes through Microsoft Foundry. No headline benchmark score is tracked for MAI-Image-2.5 yet.

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Microsoft Foundry--
ServerlessPartial

Available via routers & gateways(5)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSMicrosoft Foundry

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionMicrosoft Foundry

Azure AI Foundry Model Router

Router

Microsoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.

PassthroughMicrosoft Foundry

Helicone

Gateway

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.

SubscriptionMicrosoft Foundry

Kong AI Gateway

Gateway

Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.

SubscriptionMicrosoft Foundry

Capabilities

VisionMultimodal

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.

Frequently asked questions

What is the context window of MAI-Image-2.5?

MAI-Image-2.5 has a context window of 32k tokens.

When was MAI-Image-2.5 released?

MAI-Image-2.5 was released on 2026-06-02.

Which providers offer MAI-Image-2.5?

MAI-Image-2.5 is available from 1 provider: Microsoft Foundry.