> ## 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-1.5 Image Generation

> - Asynchronous processing mode, returns a task ID for subsequent queries
- OpenAI GPT Image 1.5, supports text-to-image / image-to-image (reference image editing, multi-image blending)
- Automatically switches to image-to-image when image_url is provided; defaults to text-to-image if omitted
- Supports 3 aspect ratios: 1:1 / 3:2 / 2:3, passed via the aspect_ratio field
- Supports quality tiers: medium (default, faster) / high (slower, richer details)
- Up to 16 reference images, supporting a mix of URLs and base64 strings
- Each request returns 1 image; does not support resolution / size / transparent backgrounds
- Submitted prompts undergo platform sensitive word / safety moderation, and violating content will be directly rejected


export const apiKeyUrl = 'https://aireiter.com/keys';

## Authorizations

<ParamField header="Authorization" type="string" required>
  All endpoints require authentication using a Bearer Token

  Get an API Key:

  Visit the <a href={apiKeyUrl} target="_blank">API Key Management Page</a> to get your API Key

  Add to the request headers when using:

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## Body

<ParamField body="model" type="string" required>
  Model name

  Fixed value: `"gpt_image_1_5"`
</ParamField>

<ParamField body="params" type="object" required>
  Model parameters object

  <Expandable title="params Object Properties">
    <ParamField body="prompt" type="string" required>
      Text description for image generation

      * Supports Chinese and English; detailed descriptions are recommended
      * For image-to-image, clearly specify "what to change" and "what to keep unchanged" (e.g., character face, pose, background)
      * Enclose any text that needs to appear in the image in quotation marks
      * Submissions undergo platform sensitive word / safety review; violations will directly return an error
    </ParamField>

    <ParamField body="image_url" type="string[]">
      Reference image array. Providing this enables image-to-image mode; if omitted, it defaults to text-to-image

      * Up to 16 reference images
      * Maximum 10 MB per image, supports jpeg, png, webp
      * Supports the following two formats:
        1. Publicly accessible URLs
        2. Base64-encoded format
           * Must use the complete Data URI format: `data:image/{format};base64,{base64_data}`
           * Example: `data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEAYABg...`
           * ⚠️ Note: Must include the `data:image/jpeg;base64,` prefix
    </ParamField>

    <ParamField body="aspect_ratio" type="string" default="1:1">
      Aspect ratio for image generation

      Supports the following values:

      * `1:1` - Square (default)
      * `3:2` - Landscape
      * `2:3` - Portrait

      <Warning>
        Only the above 3 values are supported. Passing other ratios (e.g., `16:9`, `auto`) or pixel dimensions (e.g., `1024x1024`) will directly return an error
      </Warning>
    </ParamField>

    <ParamField body="quality" type="string" default="medium">
      Image quality tier

      * `medium` - Balanced, faster generation (default)
      * `high` - Slower, richer details, suitable for final drafts

      It is recommended to use `medium` first to test the prompt and composition, and then use `high` for the final image. Different tiers have different pricing, subject to `estimated_credits` in the submission response.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="out_task_id" type="string" required>
  Caller task ID

  User-defined task identifier, required
</ParamField>

## Instructions

* **Automatic Text-to-Image / Image-to-Image Switching**: Omitting `image_url` defaults to text-to-image; passing 1–16 reference images switches to image-to-image, which can be used for partial editing, outfit changes, background replacement, style transfer, and multi-image composition.
* **Consistent Parameters for Both Modes**: Text-to-image and image-to-image use the same set of parameters and are billed according to the `quality` tier.
* **Output Dimensions**: Determined jointly by `aspect_ratio` and `quality`, with actual pixel dimensions subject to the returned image; if you need 1K / 2K / 4K or more aspect ratios, please use [GPT-Image-2](/en/api-reference/images/gpt-image-2/generation).
* **No Deduction on Failure**: Credits will not be deducted if the task fails.

## Response

<ResponseField name="out_task_id" type="string">
  Initiator task ID, can be used to query results
</ResponseField>

<ResponseField name="status" type="string">
  Initial status, fixed to `"pending"`
</ResponseField>

<ResponseField name="estimated_credits" type="number">
  Estimated credit consumption, varies with `quality` tier
</ResponseField>

<ResponseField name="created_at" type="string">
  Creation time (ISO format)
</ResponseField>

<RequestExample>
  ```bash cURL (Text-to-Image) theme={null}
  curl --request POST \
    --url https://aireiter.com/api/openapi/submit \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "gpt_image_1_5",
      "params": {
        "prompt": "A vintage travel poster with the large headline \"VISIT KYOTO\", temples and cherry blossoms",
        "aspect_ratio": "2:3",
        "quality": "high"
      },
      "out_task_id": "my_task_123456"
    }'
  ```

  ```bash cURL (Image-to-Image) theme={null}
  curl --request POST \
    --url https://aireiter.com/api/openapi/submit \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "gpt_image_1_5",
      "params": {
        "prompt": "Change the background to a sunny beach, keeping the person unchanged",
        "image_url": ["https://example.com/person.jpg"],
        "aspect_ratio": "3:2",
        "quality": "medium"
      },
      "out_task_id": "my_task_edit_001"
    }'
  ```

  ```python Python theme={null}
  import requests

  url = "https://aireiter.com/api/openapi/submit"

  payload = {
      "model": "gpt_image_1_5",
      "params": {
          "prompt": "Change the background to a sunny beach, keeping the person unchanged",
          "image_url": ["https://example.com/person.jpg"],
          "aspect_ratio": "3:2",
          "quality": "medium"
      },
      "out_task_id": "my_task_123456"
  }

  headers = {
      "Authorization": "Bearer <token>",
      "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_1_5",
    params: {
      prompt: "Change the background to a sunny beach, keeping the person unchanged",
      image_url: ["https://example.com/person.jpg"],
      aspect_ratio: "3:2",
      quality: "medium"
    },
    out_task_id: "my_task_123456"
  };

  const headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  };

  fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(payload)
  })
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => console.error('Error:', error));
  ```

  ```go Go theme={null}
  package main

  import (
      "bytes"
      "encoding/json"
      "fmt"
      "io/ioutil"
      "net/http"
  )

  func main() {
      url := "https://aireiter.com/api/openapi/submit"

      payload := map[string]interface{}{
          "model": "gpt_image_1_5",
          "params": map[string]interface{}{
              "prompt":       "Change the background to a sunny beach, keeping the person unchanged",
              "image_url":    []string{"https://example.com/person.jpg"},
              "aspect_ratio": "3:2",
              "quality":      "medium",
          },
          "out_task_id": "my_task_123456",
      }

      jsonData, _ := json.Marshal(payload)

      req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
      req.Header.Set("Authorization", "Bearer <token>")
      req.Header.Set("Content-Type", "application/json")

      client := &http.Client{}
      resp, err := client.Do(req)
      if err != nil {
          panic(err)
      }
      defer resp.Body.Close()

      body, _ := ioutil.ReadAll(resp.Body)
      fmt.Println(string(body))
  }
  ```

  ```java Java theme={null}
  import java.net.http.HttpClient;
  import java.net.http.HttpRequest;
  import java.net.http.HttpResponse;
  import java.net.URI;

  public class Main {
      public static void main(String[] args) throws Exception {
          String url = "https://aireiter.com/api/openapi/submit";

          String payload = """
          {
            "model": "gpt_image_1_5",
            "params": {
              "prompt": "Change the background to a sunny beach, keeping the person unchanged",
              "image_url": ["https://example.com/person.jpg"],
              "aspect_ratio": "3:2",
              "quality": "medium"
            },
            "out_task_id": "my_task_123456"
          }
          """;

          HttpClient client = HttpClient.newHttpClient();
          HttpRequest request = HttpRequest.newBuilder()
              .uri(URI.create(url))
              .header("Authorization", "Bearer <token>")
              .header("Content-Type", "application/json")
              .POST(HttpRequest.BodyPublishers.ofString(payload))
              .build();

          HttpResponse<String> response = client.send(request,
              HttpResponse.BodyHandlers.ofString());

          System.out.println(response.body());
      }
  }
  ```

  ```php PHP theme={null}
  <?php

  $url = "https://aireiter.com/api/openapi/submit";

  $payload = [
      "model" => "gpt_image_1_5",
      "params" => [
          "prompt" => "Change the background to a sunny beach, keeping the person unchanged",
          "image_url" => ["https://example.com/person.jpg"],
          "aspect_ratio" => "3:2",
          "quality" => "medium"
      ],
      "out_task_id" => "my_task_123456"
  ];

  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch, CURLOPT_POST, true);
  curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
  curl_setopt($ch, CURLOPT_HTTPHEADER, [
      "Authorization: Bearer <token>",
      "Content-Type: application/json"
  ]);

  $response = curl_exec($ch);
  curl_close($ch);

  echo $response;
  ?>
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
      "statusCode": 200,
      "message": "",
      "data": {
          "out_task_id": "my_task_123456",
          "status": "pending",
          "created_at": "2026-09-24T06:33:30.012Z"
      }
  }
  ```

  ```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 recharge and try again"
    }
  }
  ```

  ```json 500 theme={null}
  {
    "error": {
      "code": 500,
      "message": "Internal server error, please try again later"
    }
  }
  ```
</ResponseExample>