Microsoft Mai Image 2.5 Pro Text To Image API Documentation

Microsoft Mai Image 2.5 Pro Text To Image API Documentation

Playground

Microsoft MAI Image 2.5 Pro Text-to-Image generates polished, detailed images from natural-language prompts, with strong prompt understanding, clean composition, and high-quality visual output for creative designs, 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 Text to Image generates polished, detailed images from natural-language prompts. It supports flexible aspect ratios and common image output formats for creative, marketing, and production workflows.

Why Choose This?

• High-quality image generation
  Create polished and detailed images from text prompts.

• Flexible aspect ratios
  Use auto to let the model choose a suitable ratio, or select a fixed layout when needed.

• Readable typography support
  Generate images that can include text, labels, posters, or layout-driven visual elements.

• Simple output controls
  Choose the output format based on your workflow needs.

• Standard image output
  Generated images are returned as URLs in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Write your prompt — Describe the subject, composition, style, lighting, and any text that should appear in the image.
2. Choose aspect ratio — Select a fixed aspect ratio or use auto for model-selected framing.
3. Choose output format — Select jpeg, png, or webp when needed.
4. Submit — Generate the image and retrieve the output URL.

Pricing

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

Example Costs

Best Use Cases

• Marketing visuals — Generate campaign images, social graphics, and promotional assets.
• Product concepts — Create product scenes, branded creative assets, and visual mockups.
• Detailed illustrations — Generate polished scenes with strong composition and visual detail.
• Typography-led images — Create images that include readable text, labels, posters, or graphic layouts.
• Creative production — Produce high-quality images for design, content, and advertising workflows.

Pro Tips

• Describe the subject, composition, lighting, and style in one focused prompt.
• Put exact wording in quotation marks when text must appear in the image.
• Use auto when composition matters more than a fixed canvas ratio.
• Use png for high-quality general output, jpeg for smaller files, and webp for web-friendly images.
• Keep prompts clear and specific when layout or typography accuracy matters.

## 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 |