- Home
- Image model comparison
- MAI-Image-2.5 vs. Niji 7
Microsoft AIMidjourneyImage model matchup
MAI-Image-2.5vs.Niji 7
Which one is better?
Niji 7 has no test of our own, no arena rating and no API price yet.
MAI-Image-2.5
Rank 29 of 108
Niji 7
not tested yet
MAI-Image-2.5
Rank 9 of 21
Niji 7
not in the arena
MAI-Image-2.5
Niji 7
Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench Image v2 run; prices compared with 28 models with an API price.
Test images from GraduallyBench Image v2
Same task, the first image of each.

No image from the four fixed tasks for Niji 7 yet.
Result for “Typography and layout”:only MAI-Image-2.5 tested
What the rating looks at: Legible text, hierarchy, and composition.
“Ahead”: the 95 % ranges of both values do not overlap. “Slightly ahead”: a higher value, but the ranges overlap.
Missing image run for Niji 7
No Midjourney subscription was available for the GraduallyBench Image v2 test. Last checked November 2, 2026. With authorized access, select the exact model version and run the missing tasks.
DocumentationSubscription and API
MAI-Image-2.5
- Subscription
- No Microsoft AI subscription includes this model. Through other providers from €16 a month (Magnific Premium, with limited credits). 6 plans in Germany.
- Via API
- $0.048 per image, 100 images $4.81.
- Weights
- Closed weights.
Niji 7
- Subscription
- At Midjourney from $10 a month (Midjourney Basic). 4 plans in Germany.
- Via API
- No API price known (access: Web app).
- Weights
- Unknown.
Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.
Arena rating (LMArena) from Nov 13, 2026 · GraduallyBench Image v2 from Nov 7, 2026 · API prices from Nov 12, 2026 · Subscription database from Sep 29, 2026 (48 days old)
All data side by side
The better value is bold. For ratings only when the gap is clear.
| Kennzahl | MAI-Image-2.5 | Niji 7 |
|---|---|---|
| Ratings | ||
| Arena ratingfrom votes by users, higher is better | 1,253 | n/a |
| Arena rank | Rank 9 of 21 | n/a |
| Arena votesmore votes, a safer rating | 59,026 | n/a |
| GraduallyBench Image v2our own benchmark, 0 to 100 | 72 | n/a |
| GraduallyBench Image v2 by task | ||
| Typography and layoutLegible text, hierarchy, and composition | 78 | n/a |
| Product photographyMaterials, reflections, and fine details | 67 | n/a |
| Character and detailAnatomy, clothing, and spatial consistency | 79 | n/a |
| InfographicNumbers, labels, and visual organization | 63 | n/a |
| API price | ||
| Per imagelower is better | $0.048 | n/a |
| 100 images | $4.81 | n/a |
| Profile | ||
| Released | June 2026 | January 2026 |
| Weightsopen means: runs locally | proprietary | unknown |
| Lifecycle | Preview in Microsoft Foundry | no notice |
| Access | API, Web app | Web app |
| Parameters | 20 billion | not published |
| Largest output | 1,048,576 pixels | not consistently published |
| Plans in Germanynaming exactly this model | 6 | 4 |
API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.
Sources: MAI-Image-2.5 model source, status source (verified Aug 15, 2026) · Niji 7 model source (verified Nov 1, 2026)
Arena ratings by category
From blind votes on Artificial Analysis and LMArena; the sources are named under the card. “Ahead” means the lead is clear.
No shared arena score in the stored snapshot
The stored benchmark database contains no measurement for MAI-Image-2.5 and Niji 7 from the same arena and category. Older model versions are not used as substitutes.