SEEAPISEEAPI
Developer CenterDocs
Get API Key
  • Getting Started
  • Authentication
  • List Model Prices
  • Create a Generation
  • Get Task Details
Image Models
Alibaba
Black Forest Labs
ByteDance
Google
Grok
MiniMax
OpenAI
SeeAPI
Video Models
Alibaba
ByteDance
Google
Grok
Kling
Lightricks
MiniMax
PixVerse
Runway
SeeAPI
Vidu
Music Models
Text Models
Templates
  • 24K Magic AI API
  • Alors on Danse API
  • Apartment Dance API
  • Christmas Dance Trend API
  • Crazy Frog AI API
  • Enzo Fernandez Celebration API
  • Goodbye 2026, Welcome 2027 API
  • Hotel Lobby AI API
  • Neon Duo Dance API
  • Rap Video API
  • Rumpelstiltskin AI Dance API

Policies

  • Data Handling & Privacy
  • Terms of Service
  • Privacy Policy
  • Commercial Use Policy
www.seeapi.com

One AI API for every leading model. Create images, videos, music, and multimodal AI assets online, or build with one unified API.

Follow SeeAPI
𝕏
Explore
  • AI Model Collections
  • AI Tool Alternatives
Developers
  • AI Models
  • API Pricing
  • AI Integrations
  • API Keys
  • Documentation
Support
  • Pricing
  • [email protected]
Legal
  • Privacy Policy
  • Refund Policy
  • Terms & Conditions

Copyright 2026 © SeeAPI. All rights reserved.

GROWCRAFT PTE. LTD.

·5 RAFFLES PLACE, #06-00, RAFFLES PLACE MRT STATION, SINGAPORE 048618

Text to ImageImage to ImageLayer Decomposition

Seedream 5.5 · Layer Decomposition

Split one JPEG or PNG image into a base image and separate transparent PNG layers with Seedream 5.5. The request creates an asynchronous task; query the task or receive a webhook to download the layer images.

Developer API pricing

Provider: SeeAPI

USD estimate: $0.0037 / credit · Estimated equivalent, not an additional charge.

Layer decomposition

1K / 1.5K: 2 credits + 4.9 credits × max_images (≈ $0.007 + $0.018 × max_images)

2K / auto: 2 credits + 8.5 credits × max_images (≈ $0.007 + $0.032 × max_images)

Precharge amounts. Credits are reserved when the task is created. After delivery, the task is billed by actual usage and the difference is settled automatically: unused credits are refunded and any shortfall is charged.

Request

POST/v1/generations
AuthorizationSend your API key in the Authorization header using the Bearer scheme.Authorization: Bearer ****************

Header Params

stringrequired

A new, stable key for each generation request. Reuse it only when retrying the same request body.

max length: 255
Example:
order-20260818-001

Body Params

application/json
stringrequired

The model ID shown in the selected model's API documentation.

Allowed:seedream-5-5
Default:
seedream-5-5
Example:
seedream-5-5
stringrequired

Layer Decomposition. Use the Endpoint ID shown in this model's API documentation.

Allowed:layer-decomposition
Default:
layer-decomposition
Example:
layer-decomposition
stringoptional

Optional public Provider ID. Omit it to use the Endpoint default Provider (seeapi).

Allowed:seeapi
Default:
seeapi
Example:
seeapi
objectrequired

Layer Decomposition parameters for the selected Provider. See the Provider parameters below.

Provider parameters

SeeAPIseeapiDefault Provider
stringoptional

Describes which elements to separate into layers. Leave it empty to let the model detect the main elements automatically.

  • Up to 2,000 characters.
  • Mark a region with <bbox>x1 y1 x2 y2</bbox>: x1 y1 is the top-left corner and x2 y2 is the bottom-right corner.
  • Coordinates are normalized to 0–1000 relative to the input image width and height.
  • Example: Separate the title text <bbox>179 58 809 197</bbox> and the parrot <bbox>330 274 641 991</bbox> into independent layers.
max: 2000max length: 2000
array <uri>required

The image to decompose into layers. Pass a publicly accessible image URL.

  • Provide exactly one image.
  • Supported formats: JPEG and PNG. WebP is not supported.
  • Maximum file size: 10 MB.
  • The input image is included in the final charge of every task.
min items: 1max items: 1
Example:
["https://client.example.com/input.png"]
stringoptional

Output size tier for the base image and the separated layers.

  • auto keeps the input image size within the 1K–2K range.
  • Billing: 1K and 1.5K use the standard per-image rate; 2K and auto use the 2K per-image rate.
Allowed:auto1K1.5K2K
Default:
auto
stringoptional

File format of the base image. Separated layers are always returned as PNG with transparency.

  • Choosing jpeg only changes the base image; the separated layers stay PNG.
Allowed:pngjpeg
Default:
png
numberoptional

Maximum number of images to return, including the base image. The model decides how many layers it can separate, so a task can return fewer images than requested.

  • Must be an integer.
  • One request creates one task, and every returned image is listed in generation.result.assets.
  • When the task is created, credits for the maximum image count at the selected resolution are reserved as precharge_credit.
  • After delivery, the task is settled by the number of images actually returned plus the input image, and any unused precharge is refunded.
min: 2max: 10
Default:
5
booleanoptional

Tries to recognize text in the image so it can be separated into its own layers.

Default:
false
booleanoptional

Enables the content safety check for this task.

  • Set it to false to turn the check off.
Default:
true
string <uri>optional

An absolute HTTPS URL that receives the terminal generation Webhook.

  • Recommended in production so you receive the result without frequent polling.
max length: 2048
Example:
https://client.example.com/webhooks/seeapi

Responses

202Generation accepted and processing
Bodyapplication/json
  • Images are not included in this response. Query the task or wait for the webhook; when status is succeeded, the base image and the layers are listed in generation.result.assets.
objectrequired
stringrequired

Task ID. Use it to query the task status and results.

Example:
task_xxx
stringrequired
Example:
seedream-5-5
stringrequired
Example:
layer-decomposition
stringrequired
Allowed:seeapi
  • seeapi: SeeAPI
Example:
seeapi
stringrequired

Task status. A new task starts as processing; check the final status with Get Task Details or a webhook.

Allowed:processing
Example:
processing
numberrequired

Public credits reserved before provider-cost settlement. Values can include up to three decimal places.

  • Calculated from resolution and max_images when the task is created.
Example:
44.5
numberrequired

Consumed public credits, with up to three decimal places. In prepaid mode, the reserved amount is reported separately as precharge_credit.

  • Stays 0 while the task is processing. After the images are delivered, it shows the final charge based on the images actually returned.
Example:
0
numberrequired

Refunded public credits, with up to three decimal places.

Example:
0
string <date-time>required
Example:
2026-08-18T10:00:00Z
string <date-time>required
Example:
2026-08-18T10:00:00Z
booleanrequired

Whether this response is an idempotent replay of an earlier request.

Example:
false
200Idempotent replay of an existing generation request
Bodyapplication/json
objectrequired
stringrequired

Task ID. Use it to query the task status and results.

Example:
task_xxx
stringrequired
Example:
seedream-5-5
stringrequired
Example:
layer-decomposition
stringrequired
Allowed:seeapi
  • seeapi: SeeAPI
Example:
seeapi
stringrequired

Task status. A new task starts as processing; check the final status with Get Task Details or a webhook.

Allowed:processing
Example:
processing
numberrequired

Public credits reserved before provider-cost settlement. Values can include up to three decimal places.

  • Calculated from resolution and max_images when the task is created.
Example:
44.5
numberrequired

Consumed public credits, with up to three decimal places. In prepaid mode, the reserved amount is reported separately as precharge_credit.

  • Stays 0 while the task is processing. After the images are delivered, it shows the final charge based on the images actually returned.
Example:
0
numberrequired

Refunded public credits, with up to three decimal places.

Example:
0
string <date-time>required
Example:
2026-08-18T10:00:00Z
string <date-time>required
Example:
2026-08-18T10:00:00Z
booleanrequired

Whether this response is an idempotent replay of an earlier request.

Example:
false
400

Invalid JSON, parameters, Schema, or API Policy

401

Invalid API Key or authentication failed

402

Insufficient credits

  • Your balance must cover the full precharge, which is calculated from resolution and max_images.
403

The current request is not allowed

404

Model, Endpoint, or task not found

409

Idempotency conflict or the same request is still being created

413

Request body is too large

429

Too many requests

503

Service temporarily unavailable

Query Task Status

After submitting a task, use the unified query endpoint to check progress and retrieve results:

Get Task DetailsLearn how to query task status and retrieve generation results

In production, pass callback_url to receive the result instead of polling frequently.

Callbacks

Manage the secret used to verify generation webhook signatures. Callback URLs are supplied when you create each generation.

Webhook flow

Callback URL per generation.

Webhook signing key

Related Resources

Market Overview

Explore all available models

Credits & Billing

View credit balance, plans, and billing activity

Usage

Review API usage and credit consumption

Code Examples
Request
const response = await fetch("https://api.seeapi.com/v1/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Idempotency-Key": "order-20260818-001",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "seedream-5-5",
  "endpoint": "layer-decomposition",
  "provider": "seeapi",
  "input": {
    "input_images": [
      "https://client.example.com/input.png"
    ],
    "resolution": "auto",
    "output_format": "png",
    "max_images": 5,
    "text_recognition": false,
    "nsfw_checker": true
  },
  "callback_url": "https://client.example.com/webhooks/seeapi"
})
});

const result = await response.json();
ResponseHTTP 202
{
  "generation": {
    "id": "task_xxx",
    "model": "seedream-5-5",
    "endpoint": "layer-decomposition",
    "provider": "seeapi",
    "status": "processing",
    "precharge_credit": 44.5,
    "consumed_credits": 0,
    "refunded_credits": 0,
    "created_at": "2026-08-18T10:00:00Z",
    "updated_at": "2026-08-18T10:00:00Z"
  },
  "idempotent": false
}
PreviousSeedream 5.5 · Image to ImageNextSeedream 5.0 Pro · Text to Image
Request
const response = await fetch("https://api.seeapi.com/v1/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Idempotency-Key": "order-20260818-001",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "seedream-5-5",
  "endpoint": "layer-decomposition",
  "provider": "seeapi",
  "input": {
    "input_images": [
      "https://client.example.com/input.png"
    ],
    "resolution": "auto",
    "output_format": "png",
    "max_images": 5,
    "text_recognition": false,
    "nsfw_checker": true
  },
  "callback_url": "https://client.example.com/webhooks/seeapi"
})
});

const result = await response.json();
ResponseHTTP 202
{
  "generation": {
    "id": "task_xxx",
    "model": "seedream-5-5",
    "endpoint": "layer-decomposition",
    "provider": "seeapi",
    "status": "processing",
    "precharge_credit": 44.5,
    "consumed_credits": 0,
    "refunded_credits": 0,
    "created_at": "2026-08-18T10:00:00Z",
    "updated_at": "2026-08-18T10:00:00Z"
  },
  "idempotent": false
}