# MAI Image API: size, editing and errors

Source: https://ofox.io/docs/develop/models/mai-image

Microsoft's image generation and editing models, three in total, called through the OpenAI-compatible API in much the same way as GPT Image: text to image uses `/v1/images/generations`, and editing uses `/v1/images/edits`.

## Choosing a model

**Model IDs (copy them exactly)**

- MAI Image 2.5 Pro: `microsoft/mai-image-2.5-pro` — Complex compositions; consistent people and objects
- MAI Image 2.5: `microsoft/mai-image-2.5` — Precise local edits
- MAI Image 2.5 Flash: `microsoft/mai-image-2.5-flash` — Low latency; batch generation

All three take the same parameters; in our tests a 1024×1024 image takes about 12 to 25 seconds. For live prices, see the [model page](https://ofox.io/models/microsoft/mai-image-2.5).

## Text to image

**Python**

```python filename="mai_image.py"
import base64
from openai import OpenAI

client = OpenAI(api_key="YOUR_OFOX_API_KEY", base_url="https://api.ofox.io/v1", timeout=600)

resp = client.images.generate(
    model="microsoft/mai-image-2.5-flash",
    prompt="A red apple on a white table",
    size="1024x1024",
)

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

**cURL**

```bash filename="Terminal"
curl https://api.ofox.io/v1/images/generations \
  --max-time 600 \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "microsoft/mai-image-2.5-flash",
    "prompt": "A red apple on a white table",
    "size": "1024x1024"
  }' | jq -r '.data[0].b64_json' | base64 --decode > output.png
```

## Size (`size`)

**Key point**:`size` only sets the aspect ratio. Output is about 1 megapixel, and passing a larger size does not increase the resolution.

| Requested `size` | Actual output |
|---|---|
| Omitted | 1024×1024 |
| `1024x1024`, `2048x2048`, `4096x4096` | 1024×1024 |
| `1536x1024` | 1248×832 |
| `1024x1536` | 832×1248 |
| `100x100` | 768×768 |

- The output keeps the requested aspect ratio, with total pixels adjusted to about 1 million; a size that is too small produces 768×768.
- For higher resolutions, use [Nano Banana Pro](https://ofox.io/docs/develop/models/nano-banana) (up to 4K) or [GPT Image](https://ofox.io/docs/develop/models/gpt-image).

## Image editing

```bash filename="Terminal"
curl https://api.ofox.io/v1/images/edits \
  --max-time 600 \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -F model=microsoft/mai-image-2.5 \
  -F prompt="Make the apple purple, keep everything else the same" \
  -F image=@apple.jpg \
  | jq -r '.data[0].b64_json' | base64 --decode > apple_purple.png
```

Reference images count as input tokens; see `usage.input_tokens_details.image_tokens` in the response. We measured 576 tokens for one 768×768 reference image.

## Common errors
| Error | Cause | Fix |
|---|---|---|
| Request timeout | The client timeout is too short | Set the timeout to 300 seconds or more |
| `404 model_not_found` | Model ID misspelled | Copy the model ID from this page |

For multiple images, send several requests concurrently, one image per request.

## FAQ

**Can MAI Image generate 2K or 4K images?**

No. size only sets the aspect ratio, and the output is about 1 megapixel in total. In our tests both 2048x2048 and 4096x4096 produced 1024x1024. For higher resolutions, use Nano Banana Pro or GPT Image.

**How do I edit images with MAI Image?**

Use /v1/images/edits and upload the image file as a multipart form, the same way as with GPT Image.