Microsoft Mai Image 2.5 Pro Edit

Microsoft Mai Image 2.5 Pro Edit

Playground

Microsoft MAI Image 2.5 Pro Image Edit transforms source images with natural-language instructions, applying precise edits while preserving the details that should remain unchanged for creative design, product visuals, marketing assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Microsoft MAI Image 2.5 Pro Edit transforms a source image with natural-language instructions. It is built for precise visual changes, layout-aware refinement, and preservation-focused editing where identity, composition, or important source details should remain unchanged.

Why Choose This?

• Instruction-based image editing
  Edit an existing image by describing the desired change in natural language.

• Preservation-focused results
  Modify selected visual details while keeping important source elements unchanged.

• Layout-aware refinement
  Apply edits to background, objects, lighting, style, or composition while maintaining a coherent final image.

• Flexible aspect ratios
  Use auto for model-selected framing or choose a specific aspect ratio when needed.

• Standard output formats
  Export edited images as jpeg, png, or webp.

Parameters

How to Use

1. Upload your source image — Provide the image you want to edit.
2. Write your edit prompt — Describe the requested change and clearly state what should remain unchanged.
3. Choose aspect ratio — Select a fixed aspect ratio or use auto for model-selected framing.
4. Choose output format — Select jpeg, png, or webp when needed.
5. Submit — Generate the edited image and retrieve the output URL.

Pricing

Pricing includes a base image editing cost plus a prompt length surcharge.

Example Costs

Best Use Cases

• Background editing — Change, clean up, or restyle image backgrounds.
• Object and lighting changes — Modify objects, colors, lighting, mood, or scene details.
• Product image refinement — Improve product visuals for marketing, ecommerce, and presentation.
• Portrait and scene edits — Adjust style, composition, atmosphere, or visual details while preserving key identity.
• Layout-aware image iteration — Refine existing images for campaigns, social media, and design workflows.

Pro Tips

• Describe both the requested change and the details that must stay unchanged.
• Use a clear source image with the main subject visible.
• Keep the edit instruction focused and specific.
• Use auto when the source composition should guide the output ratio.
• Use png for high-quality general output, jpeg for smaller files, and webp for web-friendly images.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |