> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Seedream 5.0 Pro Layers > Split one image into a base image plus up to 16 independently editable layers. Every layer is a transparent PNG, and each comes back with the coordinates you need to put it back together. Pass exactly one image in `image_list`. `prompt` is optional — leave it out for an automatic split. #### Reading the result Each item in the result carries: - `z_index` — 0 is the base image; layers ascend from 1 - `bounding_box.absolute` — `[left, top, right, bottom]` in the base image's pixels - `bounding_box.normalized` — the same box on a 0-1000 scale, for any canvas size - `name` and `description` — what the layer contains Sort by `z_index`, then place each layer using its bounding box to restore or recompose the artwork. #### Pricing | Tier | Tokens | USD | |---|---|---| | 1K, 1.5K or auto | 14.66 | $0.2932 | | 2K | 15.53 | $0.3106 | Charged per request, not per image. The model decides how many layers to produce, so a request is billed as one base image plus 16 layers regardless of how many come back. Layers are billed at half the rate of a normal image, which is why a split costs far less than 17 separate generations. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated image. ## OpenAPI ````yaml api-reference/image-api/openapi-seedream-5-pro-layers.json POST /api/v1/images/generations openapi: 3.1.0 info: title: GoEnhance API - Seedream 5.0 Pro description: Seedream 5.0 Pro version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/images/generations: post: tags: - ImageAPI summary: Seedream 5.0 Pro Layers description: >- Split one image into a base image plus up to 16 independently editable layers. Every layer is a transparent PNG, and each comes back with the coordinates you need to put it back together. Pass exactly one image in `image_list`. `prompt` is optional — leave it out for an automatic split. #### Reading the result Each item in the result carries: - `z_index` — 0 is the base image; layers ascend from 1 - `bounding_box.absolute` — `[left, top, right, bottom]` in the base image's pixels - `bounding_box.normalized` — the same box on a 0-1000 scale, for any canvas size - `name` and `description` — what the layer contains Sort by `z_index`, then place each layer using its bounding box to restore or recompose the artwork. #### Pricing | Tier | Tokens | USD | |---|---|---| | 1K, 1.5K or auto | 14.66 | $0.2932 | | 2K | 15.53 | $0.3106 | Charged per request, not per image. The model decides how many layers to produce, so a request is billed as one base image plus 16 layers regardless of how many come back. Layers are billed at half the rate of a normal image, which is why a split costs far less than 17 separate generations. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated image. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - seedream-5-pro-layers description: Model name. Must be `seedream-5-pro-layers`. prompt: type: string minLength: 1 maxLength: 2000 description: >- Optional. Leave it out and the model finds and splits the main elements on its own. Provide it to name the elements to split, in plain language or with `` coordinates. image_size: type: string enum: - 1K - 1.5K - 2K - auto default: auto description: >- Output tier. `auto` follows the input image's size. Only tier names are accepted here — pixel values such as 2048x2048 are rejected. image_list: type: array items: type: object properties: url: type: string format: uri required: - url description: The single image to split. Exactly one image is required. minItems: 1 maxItems: 1 output_format: type: string enum: - png - jpeg default: jpeg description: >- Output file format. This only affects the base image — every layer is always a transparent png. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - image_list example: model: seedream-5-pro prompt: A serene Japanese garden at dawn, soft light image_size: 2K ratio: '16:9' responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 5.82 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 5.82 '2': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ````