> ## 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.

# Seedream 5.0 Flash Layerize Layer Separation

> - Asynchronous processing mode, returning a task ID for subsequent queries
- Splits an image into a background layer + up to 16 independently editable transparent PNG layers
- Each layer includes name, description, z_index, and bounding_box
- Post-billing mode: Checks balance upon submission and settles based on the actual number of output images after task completion (the background layer and each layer count as 1 image each)


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 header when using:

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

## Body

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

  Fixed value: `"seedream_v5_flash_layerize"`
</ParamField>

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

  <Expandable title="params Object Properties">
    <ParamField body="image_url" type="string | string[]" required>
      Original image to separate

      * Required, and only **1 image** can be passed
      * Supported image formats: png, jpeg; maximum 30 MB per image
      * Total pixel range: 262,144 – 36,000,000, aspect ratio range: 1:16 – 16:1
      * Supports the following two formats:
        1. Publicly accessible URL
        2. Base64 encoded format
           * Must use the full 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; Base64 image size cannot exceed 10 MB
    </ParamField>

    <ParamField body="prompt" type="string">
      Layer separation prompt (Optional)

      * When provided, separates specified elements according to the prompt, for example `Separate the title text and the parrot into independent layers`
      * You can use `<bbox>x1 y1 x2 y2</bbox>` to specify precise element positions with normalized coordinates from 0–1000, for example `Separate the parrot <bbox>330 274 641 991</bbox> into a layer`
      * If omitted or fewer than 4 characters, the model automatically identifies key elements in the image
      * Maximum 5,000 characters
    </ParamField>

    <ParamField body="resolution" type="string" default="auto">
      Output resolution tier

      * `auto` - Automatically selected based on the original image dimensions (Default)
      * `1K` - 1K resolution
      * `1.5K` - 1.5K resolution
      * `2K` - 2K resolution

      The base image maintains the aspect ratio of the original image, and each layer maintains the aspect ratio of its corresponding element in the original image.
    </ParamField>

    <ParamField body="output_format" type="string" default="png">
      Output format of the base image

      * `png` - PNG (Default)
      * `jpeg` - JPEG

      Only controls the base image format; separated layers are fixed as transparent PNG.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="callback_url" type="string">
  Callback URL after task completion
</ParamField>

<ParamField body="metadata" type="object">
  Custom metadata, returned as-is
</ParamField>

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

  User-defined task identifier, required
</ParamField>

## Response

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

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

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

After the task is completed, retrieve the results via the query endpoint: `data.output` contains the base image and each layer, and the billed image count is the number of elements in `output`.

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://aireiter.com/api/openapi/submit \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "seedream_v5_flash_layerize",
      "params": {
        "image_url": "https://example.com/poster.png",
        "prompt": "Separate the title text and the parrot into independent layers",
        "resolution": "auto",
        "output_format": "png"
      },
      "out_task_id": "my_task_123456"
    }'
  ```

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

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

  payload = {
      "model": "seedream_v5_flash_layerize",
      "params": {
          "image_url": "https://example.com/poster.png",
          "prompt": "Separate the title text and the parrot into independent layers",
          "resolution": "auto",
          "output_format": "png"
      },
      "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: "seedream_v5_flash_layerize",
    params: {
      image_url: "https://example.com/poster.png",
      prompt: "Separate the title text and the parrot into independent layers",
      resolution: "auto",
      output_format: "png"
    },
    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": "seedream_v5_flash_layerize",
          "params": map[string]interface{}{
              "image_url": "https://example.com/poster.png",
              "prompt": "Separate the title text and the parrot into independent layers",
              "resolution": "auto",
              "output_format": "png",
          },
          "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": "seedream_v5_flash_layerize",
            "params": {
              "image_url": "https://example.com/poster.png",
              "prompt": "Separate the title text and the parrot into independent layers",
              "resolution": "auto",
              "output_format": "png"
            },
            "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" => "seedream_v5_flash_layerize",
      "params" => [
          "image_url" => "https://example.com/poster.png",
          "prompt" => "Separate the title text and the parrot into independent layers",
          "resolution" => "auto",
          "output_format" => "png"
      ],
      "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;
  ?>
  ```

  ```ruby Ruby theme={null}
  require 'net/http'
  require 'json'
  require 'uri'

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

  payload = {
    model: "seedream_v5_flash_layerize",
    params: {
      image_url: "https://example.com/poster.png",
      prompt: "Separate the title text and the parrot into independent layers",
      resolution: "auto",
      output_format: "png"
    },
    out_task_id: "my_task_123456"
  }

  http = Net::HTTP.new(url.host, url.port)
  http.use_ssl = true

  request = Net::HTTP::Post.new(url)
  request["Authorization"] = "Bearer <token>"
  request["Content-Type"] = "application/json"
  request.body = payload.to_json

  response = http.request(request)
  puts response.body
  ```

  ```swift Swift theme={null}
  import Foundation

  let url = URL(string: "https://aireiter.com/api/openapi/submit")!

  let payload: [String: Any] = [
      "model": "seedream_v5_flash_layerize",
      "params": [
          "image_url": "https://example.com/poster.png",
          "prompt": "Separate the title text and the parrot into independent layers",
          "resolution": "auto",
          "output_format": "png"
      ],
      "out_task_id": "my_task_123456"
  ]

  var request = URLRequest(url: url)
  request.httpMethod = "POST"
  request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
  request.setValue("application/json", forHTTPHeaderField: "Content-Type")
  request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

  let task = URLSession.shared.dataTask(with: request) { data, response, error in
      if let error = error {
          print("Error: \(error)")
          return
      }

      if let data = data, let responseString = String(data: data, encoding: .utf8) {
          print(responseString)
      }
  }

  task.resume()
  ```

  ```csharp C# theme={null}
  using System;
  using System.Net.Http;
  using System.Text;
  using System.Threading.Tasks;

  class Program
  {
      static async Task Main(string[] args)
      {
          var url = "https://aireiter.com/api/openapi/submit";

          var payload = @"{
                ""model"": ""seedream_v5_flash_layerize"",
                ""params"": {
                  ""image_url"": ""https://example.com/poster.png"",
                  ""prompt"": ""Separate the title text and the parrot into independent layers"",
                  ""resolution"": ""auto"",
                  ""output_format"": ""png""
                },
                ""out_task_id"": ""my_task_123456""
              }";

          using var client = new HttpClient();
          client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

          var content = new StringContent(payload, Encoding.UTF8, "application/json");
          var response = await client.PostAsync(url, content);
          var result = await response.Content.ReadAsStringAsync();

          Console.WriteLine(result);
      }
  }
  ```

  ```c C theme={null}
  #include <stdio.h>
  #include <curl/curl.h>

  int main(void) {
      CURL *curl;
      CURLcode res;

      curl_global_init(CURL_GLOBAL_DEFAULT);
      curl = curl_easy_init();

      if(curl) {
          const char *url = "https://aireiter.com/api/openapi/submit";
          const char *payload = "{\"model\":\"seedream_v5_flash_layerize\",\"params\":{\"image_url\":\"https://example.com/poster.png\",\"prompt\":\"Separate the title text and the parrot into independent layers\",\"resolution\":\"auto\",\"output_format\":\"png\"},\"out_task_id\":\"my_task_123456\"}";

          struct curl_slist *headers = NULL;
          headers = curl_slist_append(headers, "Authorization: Bearer <token>");
          headers = curl_slist_append(headers, "Content-Type: application/json");

          curl_easy_setopt(curl, CURLOPT_URL, url);
          curl_easy_setopt(curl, CURLOPT_POSTFIELDS, payload);
          curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);

          res = curl_easy_perform(curl);

          if(res != CURLE_OK) {
              fprintf(stderr, "curl_easy_perform() failed: %s\n",
                      curl_easy_strerror(res));
          }

          curl_slist_free_all(headers);
          curl_easy_cleanup(curl);
      }

      curl_global_cleanup();
      return 0;
  }
  ```

  ```objectivec Objective-C theme={null}
  #import <Foundation/Foundation.h>

  int main(int argc, const char * argv[]) {
      @autoreleasepool {
          NSURL *url = [NSURL URLWithString:@"https://aireiter.com/api/openapi/submit"];

          NSDictionary *payload = @{
              @"model": @"seedream_v5_flash_layerize",
              @"params": @{
                  @"image_url": @"https://example.com/poster.png",
                  @"prompt": @"Separate the title text and the parrot into independent layers",
                  @"resolution": @"auto",
                  @"output_format": @"png"
              },
              @"out_task_id": @"my_task_123456"
          };

          NSError *error;
          NSData *jsonData = [NSJSONSerialization dataWithJSONObject:payload
                                                            options:0
                                                              error:&error];

          NSMutableURLRequest *request = [NSMutableURLRequest requestWithURL:url];
          [request setHTTPMethod:@"POST"];
          [request setValue:@"Bearer <token>" forHTTPHeaderField:@"Authorization"];
          [request setValue:@"application/json" forHTTPHeaderField:@"Content-Type"];
          [request setHTTPBody:jsonData];

          NSURLSessionDataTask *task = [[NSURLSession sharedSession]
              dataTaskWithRequest:request
              completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {
                  if (error) {
                      NSLog(@"Error: %@", error);
                      return;
                  }
                  NSString *result = [[NSString alloc] initWithData:data
                                                          encoding:NSUTF8StringEncoding];
                  NSLog(@"%@", result);
              }];

          [task resume];
          [[NSRunLoop mainRunLoop] run];
      }
      return 0;
  }
  ```

  ```ocaml OCaml theme={null}
  (* Requires cohttp and yojson libraries *)
  open Lwt
  open Cohttp
  open Cohttp_lwt_unix

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

  let payload = {|{
    "model": "seedream_v5_flash_layerize",
    "params": {
      "image_url": "https://example.com/poster.png",
      "prompt": "Separate the title text and the parrot into independent layers",
      "resolution": "auto",
      "output_format": "png"
    },
    "out_task_id": "my_task_123456"
  }|}

  let () =
    let headers = Header.init ()
      |> fun h -> Header.add h "Authorization" "Bearer <token>"
      |> fun h -> Header.add h "Content-Type" "application/json"
    in
    let body = Cohttp_lwt.Body.of_string payload in

    let response = Client.post ~headers ~body (Uri.of_string url) >>= fun (resp, body) ->
      body |> Cohttp_lwt.Body.to_string >|= fun body_str ->
      print_endline body_str
    in
    Lwt_main.run response
  ```

  ```dart Dart theme={null}
  import 'dart:convert';
  import 'package:http/http.dart' as http;

  void main() async {
    final url = Uri.parse('https://aireiter.com/api/openapi/submit');

    final payload = {
      'model': 'seedream_v5_flash_layerize',
      'params': {
        'image_url': 'https://example.com/poster.png',
        'prompt': 'Separate the title text and the parrot into independent layers',
        'resolution': 'auto',
        'output_format': 'png'
      },
      'out_task_id': 'my_task_123456'
    };

    final response = await http.post(
      url,
      headers: {
        'Authorization': 'Bearer <token>',
        'Content-Type': 'application/json'
      },
      body: jsonEncode(payload),
    );

    print(response.body);
  }
  ```

  ```r R theme={null}
  library(httr)
  library(jsonlite)

  url <- "https://aireiter.com/api/openapi/submit"

  payload <- list(
    model = "seedream_v5_flash_layerize",
    params = list(
      image_url = "https://example.com/poster.png",
      prompt = "Separate the title text and the parrot into independent layers",
      resolution = "auto",
      output_format = "png"
    ),
    out_task_id = "my_task_123456"
  )

  response <- POST(
    url,
    add_headers(
      Authorization = "Bearer <token>",
      `Content-Type` = "application/json"
    ),
    body = toJSON(payload, auto_unbox = TRUE),
    encode = "raw"
  )

  cat(content(response, "text"))
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "statusCode": 200,
    "message": "",
    "data": {
      "out_task_id": "my_task_123456",
      "status": "pending",
      "created_at": "2026-10-16T06:03:28.242Z"
    }
  }
  ```

  ```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"
    }
  }
  ```
</ResponseExample>

## 查询任务结果

After the task is submitted, use the `POST /api/openapi/query` endpoint to poll the task status until `status` is `completed` or `failed`. After the task is completed, the `output` field returns the list of layers.

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://aireiter.com/api/openapi/query \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "out_task_id": "my_task_123456"
    }'
  ```
</RequestExample>

### Query Response - Layer Output Structure

After the task is completed, `output` is an array of layer objects, where each layer contains `url` and `metadata`:

<ResponseField name="output" type="array">
  List of layers, each element is a layer object, up to 17 in total (1 base image + 16 layers)

  <Expandable title="Layer Object Properties">
    <ResponseField name="url" type="string">
      The image URL of this layer. The base image format is determined by `output_format`, while the remaining layers are transparent PNGs
    </ResponseField>

    <ResponseField name="metadata" type="object">
      Layer metadata

      <Expandable title="metadata Properties">
        <ResponseField name="kind" type="string">
          Fixed value `"layer"`, indicating that this is a layer output
        </ResponseField>

        <ResponseField name="z_index" type="number">
          Layer hierarchy index

          * `z_index = 0`: Base image (full background), `bounding_box` is `null`
          * `z_index ≥ 1`: Foreground layers, arranged in back-to-front order
        </ResponseField>

        <ResponseField name="bounding_box" type="object | null">
          The position area of the layer in the original image

          `null` for the base image (z\_index=0); for the remaining layers, a coordinate object is returned:

          <Expandable title="bounding_box Properties">
            <ResponseField name="absolute" type="array">
              Absolute pixel coordinates `[x1, y1, x2, y2]`, based on the output base image resolution
            </ResponseField>

            <ResponseField name="normalized" type="array">
              Normalized coordinates `[x1, y1, x2, y2]`, range 0–1000
            </ResponseField>
          </Expandable>
        </ResponseField>

        <ResponseField name="name" type="string | null">
          Layer name, `null` for the base image
        </ResponseField>

        <ResponseField name="description" type="string | null">
          Layer description, `null` for the base image
        </ResponseField>
      </Expandable>
    </ResponseField>
  </Expandable>
</ResponseField>

### Query Response Example

<ResponseExample>
  ```json 200 theme={null}
  {
    "statusCode": 200,
    "message": "",
    "data": {
      "out_task_id": "my_task_123456",
      "status": "completed",
      "created_at": "2026-10-16T06:03:28.000Z",
      "completed_at": "2026-10-16T06:04:26.000Z",
      "output": [
        {
          "url": "https://static.aireiter.com/upload/example/layer-0.png",
          "metadata": {
            "kind": "layer",
            "z_index": 0,
            "bounding_box": null,
            "name": null,
            "description": null
          }
        },
        {
          "url": "https://static.aireiter.com/upload/example/layer-1.png",
          "metadata": {
            "kind": "layer",
            "z_index": 1,
            "bounding_box": {
              "absolute": [755, 47, 1776, 855],
              "normalized": [393, 43, 924, 785]
            },
            "name": "Canyon and sunset sky",
            "description": "Distant canyon, winding river valley, setting sun and orange gradient sky, without the car and road"
          }
        },
        {
          "url": "https://static.aireiter.com/upload/example/layer-2.png",
          "metadata": {
            "kind": "layer",
            "z_index": 2,
            "bounding_box": {
              "absolute": [0, 707, 1920, 1088],
              "normalized": [0, 650, 999, 999]
            },
            "name": "Gravel road",
            "description": "Gravel dirt road under the car, including stones and tire tracks"
          }
        },
        {
          "url": "https://static.aireiter.com/upload/example/layer-3.png",
          "metadata": {
            "kind": "layer",
            "z_index": 3,
            "bounding_box": {
              "absolute": [232, 184, 1529, 858],
              "normalized": [121, 169, 796, 788]
            },
            "name": "Blue rally car",
            "description": "The whole blue rally car including body, wheels and windows"
          }
        }
      ]
    }
  }
  ```

  > The example above only shows 4 elements; 2–17 elements are actually returned (base image + up to 16 layers), determined by the original image content and prompt. The language of the layer name and description follows the prompt.
</ResponseExample>

> The result image URLs are temporarily stored. Please download and save them to your own storage promptly.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.