> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aireiter.com/llms.txt
> Use this file to discover all available pages before exploring further.
# GPT-Image-2.5 Image Generation
> - Asynchronous processing mode, returns a task ID for subsequent querying
- OpenAI GPT-Image 2.5 family: Flare (faster daily tier) and Sunburst (more stable editing tier)
- Supports text-to-image / image-to-image / reference image editing, with up to 10 reference images
- Supports 14 aspect ratios (including auto), passed via aspect_ratio
- Supports resolution tiers 1K / 2K / 4K, as well as API-specific size custom pixels
- Supports background: `auto` / `opaque` / `transparent` (transparent background returns PNG)
- quality / output_n are not available on this page; each request returns 1 image
- Submitted prompts undergo platform sensitive word / safety moderation; non-compliant content will be directly rejected
export const apiKeyUrl = 'https://aireiter.com/keys';
## Authorizations
All endpoints require authentication using a Bearer Token.
Get an API key:
Visit the API Key Management page to get your API key.
Add to the request header when using:
```
Authorization: Bearer YOUR_API_KEY
```
## Body
Model name, choose one of two:
* `"gpt_image_2_5_flare"` — Flare, faster for daily text-to-image / image editing
* `"gpt_image_2_5_sunburst"` — Sunburst, more emphasis on editing fidelity (characters, layout, product appearance)
There is no bare `gpt-image-2.5` ID. When comparing the two tiers, please keep the prompt, reference images, aspect ratio, and resolution unchanged.
Model parameter object
Text description for image generation
* Supports Chinese and English; detailed descriptions are recommended
* When editing images, clearly specify what to change and what must remain unchanged
* Submissions will undergo platform sensitive word / safety review before processing; violating content will return an error directly
Reference image array; if provided, enters image-to-image / editing mode
* Up to 10 reference images
* If omitted, pure text-to-image mode is used
* Supports the following two formats:
1. Publicly accessible URL
2. Base64 encoding format
* Must use the full Data URI format: `data:image/{format};base64,{base64_data}`
* Supported image formats: jpeg, png, webp
* Example: `data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEAYABg...`
* ⚠️ Note: Must include the `data:image/jpeg;base64,` prefix
Aspect ratio for image generation, default `auto`
Supports the following values:
* `auto` - Automatically select the most appropriate aspect ratio
* `1:1` - Square
* `16:9` / `9:16` - Widescreen landscape / portrait
* `4:3` / `3:4` - Standard landscape / portrait
* `3:2` / `2:3` - Classic landscape / portrait
* `5:4` / `4:5` - Near-square landscape / portrait
* `2:1` / `1:2` - Wide landscape / tall portrait
* `21:9` / `9:21` - Ultra-wide landscape / ultra-tall portrait
Only aspect ratio strings or `auto` are supported; passing pixel dimensions (e.g., `1024x1024`) will directly result in an error. Use `size` for precise pixels.
Resolution tier, default `1K`
* `1K` - Approx. 1024 baseline
* `2K` - Approx. 2048 baseline
* `4K` - Approx. 3840 baseline
Do not pass `resolution` / `aspect_ratio` when passing `size`, otherwise a 400 error is returned.
Custom pixel dimensions (API only, **mutually exclusive** with `aspect_ratio` / `resolution`)
Format is `widthxheight`, e.g., `2048x1536`, `3840x2160`.
**Limitations:**
* Format must be `^\d+x\d+$`
* Both width and height must be multiples of 16
* Neither side can exceed 3840
* Ratio of longer side / shorter side cannot exceed 3:1
* Total pixels (width × height) between **655,360 \~ 8,294,400**
* Mutually exclusive with `aspect_ratio` and `resolution`; passing them together returns 400
Image output background, default `auto`
* `auto` - Model determines whether it is transparent
* `opaque` - Opaque background
* `transparent` - Transparent background, returns PNG with alpha channel
When selecting `transparent`, the platform will automatically output in PNG format, no need to pass `output_format`. `output_format` is not available on this page.
Caller Task ID
User-defined task identifier, required. Use the same value to call `POST /api/openapi/query` when querying results.
## Size × Resolution Mapping Table
`aspect_ratio × resolution` → Actual pixels (`auto` is automatically selected by the model and is not listed in the table):
| aspect\_ratio | `1K` | `2K` | `4K` |
| ------------- | --------- | --------- | --------- |
| `1:1` | 1024×1024 | 2048×2048 | 2880×2880 |
| `3:2` | 1536×1024 | 2048×1360 | 3520×2336 |
| `2:3` | 1024×1536 | 1360×2048 | 2336×3520 |
| `4:3` | 1024×768 | 2048×1536 | 3312×2480 |
| `3:4` | 768×1024 | 1536×2048 | 2480×3312 |
| `5:4` | 1280×1024 | 2560×2048 | 3216×2576 |
| `4:5` | 1024×1280 | 2048×2560 | 2576×3216 |
| `16:9` | 1536×864 | 2048×1152 | 3840×2160 |
| `9:16` | 864×1536 | 1152×2048 | 2160×3840 |
| `2:1` | 2048×1024 | 2688×1344 | 3840×1920 |
| `1:2` | 1024×2048 | 1344×2688 | 1920×3840 |
| `21:9` | 2016×864 | 2688×1152 | 3840×1648 |
| `9:21` | 864×2016 | 1152×2688 | 1648×3840 |
> `3:2` / `2:3` @ 2K is actually 2048×1360 (approximate ratio). If you need aspect ratios not listed in the table, please use `size`.
## Response
Caller task ID, used for querying results
Initial status, fixed as `"pending"`
Estimated credit cost
Creation time (ISO format)
To query the completion status, use `POST https://aireiter.com/api/openapi/query` with the same `out_task_id`. Failed tasks will not deduct credits.
```bash cURL (Flare + aspect_ratio) theme={null}
curl --request POST \
--url https://aireiter.com/api/openapi/submit \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt_image_2_5_flare",
"params": {
"prompt": "An orange cat sitting on a windowsill watching the sunset, watercolor style",
"aspect_ratio": "16:9",
"resolution": "1K"
},
"out_task_id": "my_task_123456"
}'
```
```bash cURL (Sunburst + reference image) theme={null}
curl --request POST \
--url https://aireiter.com/api/openapi/submit \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt_image_2_5_sunburst",
"params": {
"prompt": "Only change the bottle cap to gold, keep the rest of the image unchanged",
"image_url": ["https://example.com/product.png"],
"aspect_ratio": "1:1",
"resolution": "2K"
},
"out_task_id": "my_task_edit_001"
}'
```
```bash cURL (size custom dimensions) theme={null}
curl --request POST \
--url https://aireiter.com/api/openapi/submit \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt_image_2_5_flare",
"params": {
"prompt": "An orange cat sitting on a windowsill watching the sunset, watercolor style",
"size": "2048x1152"
},
"out_task_id": "my_task_size_001"
}'
```
```bash cURL (transparent background) theme={null}
curl --request POST \
--url https://aireiter.com/api/openapi/submit \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt_image_2_5_flare",
"params": {
"prompt": "An orange cat sitting on a windowsill watching the sunset, watercolor style",
"aspect_ratio": "1:1",
"resolution": "1K",
"background": "transparent"
},
"out_task_id": "my_task_bg_001"
}'
```
```python Python theme={null}
import requests
url = "https://aireiter.com/api/openapi/submit"
payload = {
"model": "gpt_image_2_5_flare",
"params": {
"prompt": "An orange cat sitting on a windowsill watching the sunset, watercolor style",
"aspect_ratio": "16:9",
"resolution": "1K"
},
"out_task_id": "my_task_123456"
}
headers = {
"Authorization": "Bearer ",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
```
```javascript JavaScript theme={null}
const url = "https://aireiter.com/api/openapi/submit";
const payload = {
model: "gpt_image_2_5_flare",
params: {
prompt: "An orange cat sitting on a windowsill watching the sunset, watercolor style",
aspect_ratio: "16:9",
resolution: "1K"
},
out_task_id: "my_task_123456"
};
fetch(url, {
method: "POST",
headers: {
Authorization: "Bearer ",
"Content-Type": "application/json"
},
body: JSON.stringify(payload)
})
.then((response) => response.json())
.then((data) => console.log(data));
```
```go Go theme={null}
package main
import (
"bytes"
"encoding/json"
"fmt"
"io"
"net/http"
)
func main() {
url := "https://aireiter.com/api/openapi/submit"
payload := map[string]interface{}{
"model": "gpt_image_2_5_flare",
"params": map[string]interface{}{
"prompt": "An orange cat sitting on a windowsill watching the sunset, watercolor style",
"aspect_ratio": "16:9",
"resolution": "1K",
},
"out_task_id": "my_task_123456",
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer ")
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := io.ReadAll(resp.Body)
fmt.Println(string(body))
}
```
```json 200 theme={null}
{
"statusCode": 200,
"message": "",
"data": {
"out_task_id": "my_task_123456",
"status": "pending",
"estimated_credits": 2,
"created_at": "2026-09-09T06:00:00.000Z"
}
}
```
```json 400 theme={null}
{
"statusCode": 400,
"message": "Invalid request parameters",
"ok": false
}
```
```json 401 theme={null}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key"
}
}
```
```json 433 theme={null}
{
"error": {
"code": 433,
"message": "Insufficient account balance, please top up and try again"
}
}
```
```json 500 theme={null}
{
"error": {
"code": 500,
"message": "Internal server error, please try again later"
}
}
```