Seedream 5.0 Pro

Model id seedream-5.0-pro · ByteDance · image · 2 modes: text-to-image, image-to-image.

This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls get_model with the mode.

Text To Image

Mode text-to-image. Text to image.

Input

Field	Type	Required	Allowed	Default	Description
`prompt`	string	Yes	up to 32,000 characters		What the image should show, or the changes to make.
`image_size`	string		`square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`, `auto_2K`, `auto_1K`	`auto_2K`	Output size.
`num_images`	integer		1 to 4		How many images to generate in one call.

Pricing

3.27–6.53 credits/image; default 6.53 at auto_2K. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "seedream-5.0-pro",
  "mode": "text-to-image",
  "input": {
    "prompt": "Studio photo of a ceramic mug with steam, soft morning light"
  }
}

Image To Image

Mode image-to-image. Edit or combine reference images.

Input

Field	Type	Required	Allowed	Default	Description
`prompt`	string	Yes	up to 32,000 characters		What the image should show, or the changes to make.
`image_size`	string		`square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`, `auto_2K`, `auto_1K`	`auto_2K`	Output size.
`num_images`	integer		1 to 4		How many images to generate in one call.
`references`	File list	Yes	1 to 10 items		References the output must follow. The kind of each one (image, video, audio) is read from the file; per-kind limits are in the mode’s `capabilities.references`.

References: up to 10: 10 images. Assets, URLs and elements are accepted.

Pricing

3.27–6.53 credits/image; default 6.53 at auto_2K. Editing: +0.22 per additional reference after the first, per output image. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "seedream-5.0-pro",
  "mode": "image-to-image",
  "input": {
    "prompt": "Studio photo of a ceramic mug with steam, soft morning light, keeping the look of the reference",
    "references": [
      "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24"
    ]
  }
}

Models

Video

Image

Audio

Seedream 5.0 Pro

Text To Image

Input

Pricing

Example

Image To Image

Input

Pricing

Example

​Text To Image

​Input

​Pricing

​Example

​Image To Image

​Input

​Pricing

​Example

Text To Image

Input

Pricing

Example

Image To Image

Input

Pricing

Example