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

# GPT Image 2.5 Flare

> Fast GPT Image 2.5 model for image generation and editing.

Fast GPT Image 2.5 model for image generation and editing.

## Model Information

| Field      | Description                 |
| ---------- | --------------------------- |
| `model`    | gpt-image-2.5-flare         |
| `endpoint` | POST /v1/images/generations |

## Capabilities and Usage

* quality supports auto, low, medium, high, xhigh, and max.
* Use auto or WIDTHxHEIGHT for size: both edges are multiples of 16, no edge exceeds 3840 px, aspect ratio is within 1:3-3:1, and total pixels are 655360-8294400. Above 3686400 pixels is experimental.
* Transparent backgrounds require PNG or WebP. Generation uses JSON; editing uses multipart image/image\[] and optional mask. Do not wrap image parameters in metadata.

## Request Example

Set `MIXROUTE_API_KEY` before making the request.

```bash theme={null}
curl --request POST "https://api.mixroute.ai/v1/images/generations" \
  --header "Authorization: Bearer $MIXROUTE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "gpt-image-2.5-flare",
  "prompt": "A red ceramic mug on a plain white background.",
  "n": 1,
  "size": "1024x1024",
  "quality": "low"
}'
```

## Request Fields

| Field     | Description                                         |
| --------- | --------------------------------------------------- |
| `model`   | Required. Use the exact model ID above.             |
| `prompt`  | Required image description, up to 32000 characters. |
| `size`    | auto or valid WIDTHxHEIGHT.                         |
| `quality` | auto, low, medium, high, xhigh, max.                |
| `n`       | 1-10 images; default 1.                             |

For editing, use [GPT Image Edits](/en/api-reference/endpoint/gpt-image-edit).

Complete request format: [gpt-image](/en/api-reference/endpoint/gpt-image).