# MAI Image 2.5

> Run MAI Image 2.5 by microsoft online or via API. $0.05/image, no setup.

**URL:** https://inference.sh/apps/microsoft/mai-image-2-5
**Last updated:** 2026-11-11

---

MAI Image 2.5 — Microsoft's photorealistic image generation and editing model with fine-grained pixel-level control.

- app: `microsoft/mai-image-2-5`
- maker: [microsoft](https://inference.sh/apps/microsoft.md)
- category: [image](https://inference.sh/apps/category/image.md)
- input → output: text → image
- tasks: [text to image](https://inference.sh/apps/tag/text-to-image.md), [image editing](https://inference.sh/apps/tag/image-editing.md)
- price: $0.05/image
- runs via: api, javascript and python sdk, belt cli, mcp

## mai-image-2-5 API Guide

### About
mai image 2.5 — microsoft's photorealistic image generation and editing model with fine-grained pixel-level control.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @1w6t49y5 pinned
result = client.run({
        "app": "microsoft/mai-image-2-5@1w6t49y5",
        "input": {
            "prompt": "prompt"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @1w6t49y5 pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "microsoft/mai-image-2-5@1w6t49y5",
        "input": {
            "prompt": "prompt"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "microsoft/mai-image-2-5@1w6t49y5",
        "input": {
            "prompt": "prompt"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "microsoft/mai-image-2-5@1w6t49y5",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **prompt** (string) *required*: Text prompt describing the desired image (3-5000 characters).
- **image** (string): Reference image for editing. When provided, the prompt becomes an edit instruction.
- **num_images** (integer): Number of images to generate (1-4).
- **aspect_ratio** (string): Output aspect ratio.
- **output_format** (string): Output image format.

#### Output
- **description** (string): Model description of the generated image.
- **image** (string): Generated or edited image.

## other image apps

- [Seedream 5.5](https://inference.sh/apps/bytedance/seedream-5-5.md): $0.020 per 1K/1.5K image, $0.035 per 2K image, plus $0.008 per reference image
- [MiniMax H3 Image](https://inference.sh/apps/minimax/h3-image.md): $2.30/M text in, $1.50/M image in, $3.80/M image out (token-based)
- [GPT Image 2.6 Flare](https://inference.sh/apps/openai/gpt-image-2-6-flare.md): $30.00/M output, $5.00/M text input, $8.00/M image input, $0.10/M SVG input, $0.50/M SVG output
- [GPT Image 2.6 Sunburst](https://inference.sh/apps/openai/gpt-image-2-6-sunburst.md): $30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out
- [Gemini Nano Banana 2.1](https://inference.sh/apps/google/gemini-nano-banana-2-1.md): $1.50/M input, $0.0336–$0.1134/image (1K–4K), +$0.014/query Google Search

## faq

### how much does MAI Image 2.5 cost?

$0.05/image. you pay per run from your inference shell credits. no subscription is required.

### how do I run MAI Image 2.5 via api?

call microsoft/mai-image-2-5 with the javascript or python sdk, the rest api, or `belt app run microsoft/mai-image-2-5` from a terminal. the api reference on this page lists every input.

### who makes MAI Image 2.5?

MAI Image 2.5 is made by microsoft and runs on inference shell. every microsoft app is listed at https://inference.sh/apps/microsoft.

### can my agent use MAI Image 2.5?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to MAI Image 2.5?

other image apps on inference shell include Seedream 5.5, MiniMax H3 Image, GPT Image 2.6 Flare, GPT Image 2.6 Sunburst. they run through the same api, so switching is a one-line change.
