microsoft
Microsoft AI: MAI-Image-2.5 Pro
microsoft/mai-image-2.5-pro
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
MAI-Image-2.5 Pro (microsoft/mai-image-2.5-pro) is an image generation model from Microsoft listed in the OpenRouter catalog. According to that listing, it accepts text and image inputs and produces image outputs, and the catalog description characterizes it as producing photorealistic and artistic images from text prompts with support for various aspect ratios, distributed via Azure AI Foundry. The catalog reports a 4096-token context window and support for temperature and max-token parameters. No independent model card or benchmark data was included in this source pack, so these capabilities are catalog claims rather than verified measurements.[1]
Strengths
- The OpenRouter catalog lists both text and image inputs with image output, so it can reportedly be prompted with reference pictures as well as text.[1]
- The catalog description claims it generates photorealistic and artistic images and supports various aspect ratios.[1]
- Per the listing, it exposes temperature and max-token parameters and a 4096-token context window, and is offered through Azure AI Foundry.[1]
Limitations
- All evidence comes from a single OpenRouter catalog entry; an independent model card was not available in this source pack, so reported capabilities are unverified catalog claims.[1]
- The catalog entry contains no benchmark results and lists reasoning support as null, leaving quality and behavior unmeasured.[1]
- Real-world output quality, licensing terms, and content-safety behavior are unknown from this evidence; validate on your own workloads before adoption.[1]
Where to use it
- Worth evaluating for text-to-image generation of photorealistic or artistic visuals, based on the catalog's stated capabilities.[1]
- Could fit workflows that supply an input image alongside a prompt, since the catalog lists image input support.[1]
- Teams using Azure AI Foundry may want to trial it there, as the catalog describes it as available via that platform.[1]
Sources
- [1] OpenRouter catalog · Microsoft AI: MAI-Image-2.5 ProSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.
Specifications
- Model ID
- microsoft/mai-image-2.5-pro
- Canonical ID
- microsoft/mai-image-2.5-pro-20260723
- Creator
- microsoft
- Added to OpenRouter
- 23.07.2026
- Context length
- 4,096
- Modality
- text+image->image
- Input modalities
- text, image
- Output modalities
- image
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | output: image |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Azure | 4,096 | — | — | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.