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

# GPT Image 2.5 Ext Sunburst

> Select Sunburst GPT Image 2.5 Ext with gpt-image-2.5-ext-sunburst.

`gpt-image-2.5-ext-sunburst` is the Sunburst alias for GPT Image 2.5 Ext. It maps to the same Ext contract and prices as [`gpt-image-2.5-ext`](/api-manual/image/gpt-image-2-5-ext). Use this ID when a client can send only `model` and not `version`.

| Property    | Value                                                                      |
| ----------- | -------------------------------------------------------------------------- |
| Model ID    | `gpt-image-2.5-ext-sunburst`                                               |
| Version     | Sunburst (`version` must be `sunburst` if sent)                            |
| Resolutions | `1K`, `2K`, `4K` (default `1K`)                                            |
| Size        | `auto` (default) or a supported ratio                                      |
| Count       | integer `n` from 1 to 4 (default `1`)                                      |
| Price       | Same as Ext: \$0.0085 / \$0.014 / \$0.021 per delivered 1K / 2K / 4K image |

Do not send `version: "flare"` with this model ID. Billing, references, async headers, and response shapes are identical to the canonical Ext page.

<ParamField body="model" type="string" required>
  Set to `gpt-image-2.5-ext-sunburst`.
</ParamField>

<ParamField body="prompt" type="string" required>
  Describe the subject, composition, lighting, and style.
</ParamField>

<ParamField body="version" type="string" default="sunburst">
  Omit this field or set it to `sunburst`.
</ParamField>

<ParamField body="resolution" type="string" default="1K">
  Use `1K`, `2K`, or `4K`.
</ParamField>

<ParamField body="size" type="string" default="auto">
  Use `auto`, `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `5:4`, `4:5`, or `21:9`.
</ParamField>

<ParamField body="n" type="integer" default="1">
  Request 1 to 4 images.
</ParamField>

<ParamField body="image_urls" type="string[]">
  Optional. Up to 16 public image URLs or PNG/JPEG/WebP Data URLs. References do not change the price.
</ParamField>

## Request

```bash theme={null}
curl https://api.freemodel.app/v1/images/generations \
  -H "Authorization: Bearer $FREEMODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-ext-sunburst",
    "prompt": "Preserve the product and replace the background with warm linen",
    "resolution": "2K",
    "size": "4:5",
    "n": 1,
    "image_urls": ["https://example.com/product.png"]
  }'
```

A successful wait returns `data[].url`. Send `Prefer: respond-async` and poll [`GET /v1/tasks/{id}`](/api-reference/task-status) when you want a gateway task immediately. See [GPT Image 2.5 Ext](/api-manual/image/gpt-image-2-5-ext) for the full parameter and billing rules.

<Card title="Open the model playground" icon="wand-magic-sparkles" href="https://freemodel.app/models/gpt-image-2-5-ext">
  Run Ext from the FreeModel model page. Choose Sunburst there or send this model ID.
</Card>