Current model · Microsoft AI
MAI Image 2.7 benchmarks, pricing and specs
MAI Image 2.7 is a Microsoft AI model released on November 17, 2026 that takes text and image input and produces image. Its price is not published. It scores 1387 Elo on Arena Text-to-Image, #4 of 12 current models (Arena, measured November 17, 2026).
- Arena Text-to-Image
- 1387 Elo#4 of 12 current models
Data verified November 18, 2026 · Dataset 2026-11-18
Specs
Key facts
- Provider
- Microsoft AI
- Model family
- MAI Image
- Release date
- November 17, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- Not reported
- Max output
- Not reported
- Input
- text, image
- Output
- image
- Task families
- image
- Declared capabilities
- image generation, image editing, image to image
Charts
Against every current image model
Where MAI Image 2.7 lands among the current models of its task, on every independent benchmark, on price and on context.
Where it stands
On Arena Text-to-Image, MAI Image 2.7 ranks #4 of 12 current image models. Each bar is the share of current models it beats.
Independent benchmarks
Arena Text-to-Image
#4of 12
1,387 Elo · ahead of 73%
Published rating range 1,375 to 1,399
Arena Image Edit
#4of 11
1,475 Elo · ahead of 70%
Published rating range 1,464 to 1,487
Benchmarks
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Microsoft AI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text-to-Image | 1387 EloPublished rating range 1375 to 1399 | #4 of 12 | November 17, 2026 | Arena · 2026-11-18 |
| Arena Image Edit | 1475 EloPublished rating range 1464 to 1487 | #4 of 11 | November 17, 2026 | Arena · 2026-11-18 |
Fit
Strengths, cautions and best uses
- Strengths
- Microsoft's new flagship image model (November 17, 2026) for generation and fine-grained edits that change an object's color, material or position and leave the rest of the image as it was, with transparent backgrounds for product images, logos and icons
- Arena rates it 1387 for text-to-image and 1475 for image editing on its first boards (November 17, 2026), fourth on both, and level with GPT Image 2.6 Flare (1375 and 1461) within the published ranges
- In public preview in Microsoft Foundry at about $35 per 1,000 images, and through fal, Genspark, OpenRouter and Vercel; MAI Image is also the model family behind Bing Image Creator
- Cautions
- Arena rates it below GPT Image 2.5 Sunburst on both boards (1428 and 1519) and below GPT Image 2.6 Sunburst for generation (1410), on 3,082 and 3,007 votes so far
- Microsoft has published only an approximate price, about $35 per 1,000 images, and no rate per image or resolution, so no price is recorded here
- A preview in Microsoft Foundry, under its preview terms
- Best for
- Edits that must keep the rest of a picture unchanged, such as swapping a product's color or material
- Product images, logos and icons that need transparent backgrounds
From benchmark to production
Building on MAI Image 2.7?
Public scores rarely hold on your own data. We test it against the alternatives on your real tasks, then build the agent or pipeline around the model that wins.
AI Model Cost AuditLaunch price $100, regular price $150
Alternatives
Alternatives to MAI Image 2.7
The closest current image models by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
On score and price
MAI Image 2.7 beside the 4 alternatives listed below, on Arena Text-to-Image.
Arena Text-to-Image
Measured November 17, 2026, higher is better
- MAI Image 2.7
- 1,387
- MiniMax H3-Image
- 1,198
- GPT Image 2.6 Flare
- 1,375
- GPT Image 2.6 Sunburst
- 1,410
- Nano Banana 2.1
- 1,328
MiniMax H3-Image
- 189 points lower on Arena Text-to-Image, 1198 vs 1387
- From MiniMax
GPT Image 2.6 Flare
- 12 points lower on Arena Text-to-Image, 1375 vs 1387
- From OpenAI
GPT Image 2.6 Sunburst
- 23 points higher on Arena Text-to-Image, 1410 vs 1387
- From OpenAI
Nano Banana 2.1
- 59 points lower on Arena Text-to-Image, 1328 vs 1387
- From Google
Further reading
More on MAI Image 2.7
FAQ
MAI Image 2.7 FAQ
How does MAI Image 2.7 score on independent benchmarks?
MAI Image 2.7 scores 1387 Elo on Arena Text-to-Image, #4 of 12 current models (Arena, measured November 17, 2026) and 1475 Elo on Arena Image Edit, #4 of 11 current models (Arena, measured November 17, 2026). These are independent evaluations, not Microsoft AI's own launch figures.
Is MAI Image 2.7 open source or API only?
MAI Image 2.7 is available through Microsoft AI's API only; its weights are not published.
What are the best alternatives to MAI Image 2.7?
The closest current alternatives by price and measured performance are MiniMax H3-Image (189 points lower on Arena Text-to-Image, 1198 vs 1387), GPT Image 2.6 Flare (12 points lower on Arena Text-to-Image, 1375 vs 1387), GPT Image 2.6 Sunburst (23 points higher on Arena Text-to-Image, 1410 vs 1387) and Nano Banana 2.1 (59 points lower on Arena Text-to-Image, 1328 vs 1387).
AI Model Brief
The AI models worth knowing, once a week
What shipped, how it scores on independent benchmarks, what it costs per million tokens and what was deprecated, from the data behind our AI model benchmarks.
We use your address only to send the brief. See our privacy policy.
See this week’s briefSources
Sources
- MAI Image 2.7: Frontier quality at a fraction of the cost · Microsoft AI · official · verified November 18, 2026
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified November 18, 2026 · CC-BY-4.0
All 300 sources behind the benchmarks, with their versions, licenses and notes, are in the source catalog.
Cite this page
Van Data Team. "MAI Image 2.7 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-11-18. https://vandatateam.com/ai-model-benchmarks/mai-image-2-7
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether MAI Image 2.7 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls
