> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MAI-Image 2.7 Is Live: No. 1 in Image Editing

> Microsoft's MAI-Image 2.7 and 2.7-Flash are live on APIYI: No. 1 on Artificial Analysis image editing (1,215 Elo), up to 2048×2048 output, transparent backgrounds, and up to five reference images. $0.12 / $0.06 per request regardless of size; about $0.10 per flagship image with a 20% top-up bonus.

## Key Takeaways

* **Top of the image editing board**: 1,215 Elo on Artificial Analysis AA-Image-Editing v2.1 — 4 points ahead of GPT Image 2.6 Sunburst and 64 points above the previous MAI-Image-2.6
* **New provider specs**: maximum output rises from 1536×1536 to **2048×2048** (4,194,304 pixels), **transparent backgrounds** are now supported, and edits accept up to five reference images
* **Per-request pricing unchanged**: \$0.12 / \$0.06 per image, the same for 2048 and 1024, and the same for one reference image or five
* **Effective cost is lower**: with the current top 20% top-up bonus, the flagship lands at about \$0.10 per image and Flash at about \$0.05
* **Migration is a model-name change**: endpoints, parameters and error behavior match 2.6; APIYI has verified 2048 output, transparent backgrounds and multi-reference edits in production

## Background

**MAI-Image 2.7** and **MAI-Image-2.7-Flash** are the newest image models from Microsoft AI, announced on November 17, 2026 at Microsoft Ignite and available in public preview on Microsoft Foundry.

The line moves fast: MAI-Image-2.6 arrived in September 2026; an editing-only 2.7 Preview followed on October 27 (No. 3 on the Arena image editing board); the November 17 release adds text-to-image generation, a cheaper Flash variant, and Canvas, an interactive image workspace in MAI Labs powered by Flash. Microsoft says MAI Image is now the default image model behind Bing Image Creator.

For APIYI users there are two concrete changes: **maximum output rises from 1536×1536 to 2048×2048**, and **transparent backgrounds are now supported**. Pricing stays at the same per-request rates as the previous generation.

> [!NOTE]
>
> **Release status**: both models are in public preview; Microsoft has not announced a GA date. APIYI serves them through the official Microsoft channel, with model IDs `MAI-Image-2.7` and `MAI-Image-2.7-Flash`. Model names are case-sensitive.

## Deep Dive

### Benchmarks

Artificial Analysis **AA-Image-Editing v2.1**, as of November 20, 2026:

| Model | Editing Elo | Samples |
| - | - | - |
| **MAI-Image-2.7** | **1,215 (No. 1)** | 5,526 |
| GPT Image 2.6 Sunburst (max) | 1,211 | 6,600 |
| GPT Image 2.6 Flare (max) | 1,205 | 6,836 |
| **MAI-Image-2.7-Flash** | **1,179 (No. 7)** | 5,929 |
| MAI-Image-2.6 | 1,151 | 17,434 |
| MAI-Image-2.6-Flash | 1,145 | 11,545 |

Text-to-image is a different story. On **AA-Image-T2I v2.1**, 2.7 ranks No. 4 (1,214), behind three OpenAI GPT-Image-2.6 / 2.5 models; 2.7-Flash ranks No. 11 (1,158).

A few notes:

* **Editing is the strength here**: 2.7 is 64 points above 2.6, and Flash matches or beats some previous-generation flagships. Microsoft says it reaches the frontier in enhancement and restoration, reasoning-based edits, scene and style, and text and symbol editing
* **The 4-point lead is within the error bars**: the confidence intervals for 1,215 and 1,211 (about ±13) overlap, so the top of the editing board is effectively a tie
* **Do not pick a text-to-image model from this board alone**: 2.7 trails GPT-Image-2.6 Sunburst by 47 points on T2I. If generation quality is the priority, compare against the GPT-Image-2.6 line first
* **Do not mix leaderboard versions**: Artificial Analysis changed to the v2.1 methodology in August; older scores are not directly comparable

On Arena, Microsoft reports that 2.7 makes it the second-best lab in both text-to-image and single-image editing, behind OpenAI (vendor-reported; the production release is new to the board and votes are still accumulating).

### Key Features

> [card] 2048×2048 output
>
> Pixel ceiling rises from 2,359,296 to **4,194,304** (+78%), so e-commerce hero images and posters skip an upscale step

> [card] Transparent backgrounds
>
> Send `background: "transparent"` to get a PNG with an alpha channel — ready for stickers, icons and product cutouts

> [card] One to five reference images
>
> Multi-image fusion in the edits endpoint, referenced as image 1, image 2 and so on; the number of references does not change the price

> [card] Precise local edits
>
> Change an object's color, material or position while keeping the rest of the frame intact, with better consistency across successive edits

### Technical Specs

| Item | Spec |
| - | - |
| Architecture | Diffusion model trained with flow-matching loss (per Microsoft Foundry) |
| Context | 32K input / 4,096 output tokens (provider specification) |
| Max output | **2048×2048** (4,194,304 pixels) |
| Size parameters | `width` + `height`, integers, must be paired; each dimension at least 768 |
| Size rounding | Rounded down to a multiple of 16 (tested: 1000×1000 → 992×992) |
| Default size | 1024×1024 |
| Output format | PNG via `b64_json` only; RGBA with transparent backgrounds |
| Images per request | 1 for generation; `n` works on the edits endpoint |
| Reference images | 1–5 uploaded files on edits (repeat `image[]`) |
| Endpoints | `/v1/images/generations` and `/v1/images/edits` only |
| Parameter limits | `response_format`, `seed`, `negative_prompt` return 400; `size` is silently ignored |

Latency measured on APIYI's production gateway on November 20, 2026 (1024×1024 unless noted):

| Scenario | Latency |
| - | - |
| `MAI-Image-2.7-Flash` generation | 20.8–22.1 s |
| `MAI-Image-2.7` generation at 2048×2048 | 61.9 s |
| `MAI-Image-2.7-Flash` generation at 2048×2048 | 37.9 s |
| `MAI-Image-2.7-Flash` edit with one reference | 22.1 s |
| `MAI-Image-2.7` edit with two references | 38.9 s |

> [!WARNING]
>
> **2048×2048 responses are large**: the tested PNG was about 6.5 MB, roughly 8.6 MB after base64 encoding. Raise response-body limits on your client, reverse proxy and serverless platform, or you will see timeouts and truncated responses.

## Practical Use

### Recommended Scenarios

* **E-commerce and advertising images**: generate at `2048×2048` directly; use the two-image edit to place a product into a scene
* **Transparent assets**: stickers, app icons and product cutouts via `background: "transparent"`
* **Brand asset reuse**: up to five reference images to combine a logo, a product and a person in one frame
* **Posters and signage**: wrap Chinese text in quotes — 2.7-Flash rendered shop signs, couplets and chalkboards correctly in testing

### Code Example

```python theme={null}
from openai import OpenAI
import base64

client = OpenAI(
    api_key="sk-your-apiyi-key",
    base_url="https://api.apiyi.com/v1",
    timeout=240.0,  # 2048×2048 took about 62 s in testing; leave headroom
)

resp = client.images.generate(
    model="MAI-Image-2.7",
    prompt="A minimalist red apple icon, flat vector style",
    # width / height / background are not standard OpenAI SDK fields; pass them in extra_body
    extra_body={"width": 2048, "height": 2048, "background": "transparent"},
)

with open("apple.png", "wb") as f:
    f.write(base64.b64decode(resp.data[0].b64_json))
```

### Best Practices

* **Scale timeouts with size**: at least 120 s for 1024, at least 180 s for 2048. The image API is synchronous with no task ID — if the client disconnects, the result is lost but the request is still billed
* **Use `width` + `height`**: the generation endpoint silently ignores `size` and always returns 1024×1024
* **Remove three parameters when migrating**: `response_format`, `seed` and `negative_prompt` all return 400 on this series
* **Upload files for edits**: image URLs and base64 JSON are rejected; repeat `image[]` for multiple references, never `image` + `image2`
* **Do not select it in chat clients**: this series returns 404 on `/v1/chat/completions`, so Cherry Studio, LobeChat and similar tools will not work

## Pricing and Availability

### Pricing

| Model | APIYI price | 2048×2048 | Transparent background |
| - | - | - | - |
| **`MAI-Image-2.7`** | **\$0.12 per request** | ✅ | ✅ |
| **`MAI-Image-2.7-Flash`** | **\$0.06 per request** | ✅ | ✅ |
| `MAI-Image-2.6` | \$0.12 per request | ❌ (1536×1536 max) | ❌ |
| `MAI-Image-2.6-Flash` | \$0.06 per request | ❌ (1536×1536 max) | ❌ |

**Billed per request, independent of size and reference count**: 1024×1024, 1536×1536 and 2048×2048 cost the same, and an edit with one reference image costs the same as one with five. The provider bills by image tokens, so larger images cost more (about \$35 per 1,000 images at 1024×1024); APIYI converts that into a flat per-image price so budgets are predictable to the image.

With the current top **20% top-up bonus**, the flagship works out to about **\$0.10 per image** and Flash to about **\$0.05** (bonus tiers depend on the single top-up amount; see the promotion page).

> [!NOTE]
>
> Model prices are aligned with the provider and may change; the table above is for reference only. The **Model Pricing** tab in the top navigation is authoritative: [Model Pricing](https://docs.apiyi.com/en/models/index.md).

Available groups: `Default` and `SVIP`, both at 1.0x. Any new key can call the models without an application.

### Stacking Top-up Bonuses

The per-request prices above stack with APIYI's top-up bonuses: the top tier is 20% for a single top-up of \$3,000 or more, which brings the flagship to about \$0.10 per image. See [Top-up Promotions](https://docs.apiyi.com/en/faq/recharge-promotions.md) for tiers and rules.

## Conclusion

MAI-Image 2.7 is a meaningful upgrade in editing plus a larger canvas: No. 1 on the editing board, 2048×2048 output, transparent backgrounds — while APIYI's per-request prices stay at \$0.12 / \$0.06.

* **Editing, retouching, local replacement**: use 2.7; use 2.7-Flash for volume drafts and variations at half the cost
* **Need 2048×2048 or transparent backgrounds**: only the 2.7 series supports them; 2.6 remains available but caps at 1536×1536
* **Pure text-to-image with maximum quality**: 2.7 ranks No. 4 on T2I, behind the GPT-Image-2.6 line — compare before switching
* **Already on 2.6**: migration is a model-name change; endpoints and parameters are identical

Full parameters, Playground and an agent-ready integration prompt are on the [MAI-Image 2.7 page](https://docs.apiyi.com/en/api-capabilities/mai-image/overview.md). The launch note is in [Live Updates](https://docs.apiyi.com/en/live/2026-11/mai-image-2-7).

> [!NOTE]
>
> **Sources** (retrieved November 20, 2026): Microsoft announcement `microsoft.ai/news/introducing-mai-image-2-7/` (November 17, 2026); MAI-Image 2.7 model card and Foundry catalog `ai.azure.com/catalog/models/MAI-Image-2.7`; Artificial Analysis image editing and text-to-image leaderboards `artificialanalysis.ai/image/leaderboard` (data as of November 20, 2026); APIYI pricing API and production gateway tests (November 20, 2026; report in `code-test/MAI/1120-MAI-Image-2.7-接入测试/`).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.