Skip to main content
POST
doubao-seedream-5.0-flash Interface

Authorizations

Authorization
string
header
required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Body

application/json
model
enum<string>
default:doubao-seedream-5.0-flash
required

Image generation model name

Available options:
doubao-seedream-5.0-flash
Example:

"doubao-seedream-5.0-flash"

prompt
string
required

Prompt describing the image you want to generate, or describing how to edit the input image

Language support: In addition to Chinese and English, Seedream 5.0 Flash also supports Russian, Arabic, Filipino, Thai, Turkish, Korean, Malay, Spanish, Portuguese, Indonesian, French, German, Vietnamese and Japanese.

Length limit: Up to 4000 tokens (about 2,600 Chinese characters or 5,000 English words); exceeding it returns 400 and is not billed.

Recommendation: Keep prompts under 300 Chinese characters or 600 English words. A longer prompt still fits the limit but dilutes the information, and the model may miss details, leaving elements out of the image.

Example:

"A serene lake reflecting the beautiful sunset"

size
string
default:auto

Size of generated image, supports two formats:

Method 1 - Ratio format:

  • auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21
  • Works with the quality parameter to automatically generate an image at the corresponding aspect ratio and resolution, without manually specifying pixels

Method 2 - Pixel format:

  • Width x height, e.g.: 1024x1024, 2048x2048
  • Total pixel range: [921600, 4624220]
  • Aspect ratio range: [1/16, 16]
  • Both width and height must be greater than 14px

Defaults to auto when size is omitted. auto means no explicit ratio: the model decides the composition from the prompt, and the output resolution follows the tier set by quality.

Example:

"16:9"

quality
enum<string>
default:1K

Resolution tier, used with the ratio format of size, defaults to 1K.

Billing:

  • Billed per image, with the same price for 1K, 1.5K, and 2K; 1.5K and 2K offer better image quality at no extra charge
  • Pixel-format size is also billed per image, without pixel-based pricing tiers
Available options:
1K,
1.5K,
2K
Example:

"2K"

prompt_priority
enum<string>
default:standard

Prompt optimization strategy, used to set the prompt optimization mode

Options:

  • standard: Standard mode

Note: Seedream 5.0 Flash only supports standard; passing fast returns 400. Flash already provides faster generation and does not offer a separate fast mode.

Available options:
standard
Example:

"standard"

image_urls
string<uri>[]

List of reference image URLs for image-to-image generation and image editing

Notes:

  • Reference images are free
  • Up to 10 input images per request
  • Image size: no more than 30MB
  • Supported formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif, .heic, .heif
  • Aspect ratio (width/height): [1/16, 16]
  • Both width and height must be greater than 14px
  • Total pixels: [196, 6000×6000]
  • Image URLs must be directly accessible to the server or trigger a direct download when accessed (such URLs typically end in an image extension such as .png or .jpg)
Maximum array length: 10
Example:
output_format
enum<string>
default:jpeg

Output image format

Options:

  • png: PNG format
  • jpeg: JPEG format

Note: With background=transparent, output is always png: omitting output_format automatically selects png, while specifying jpeg is rejected.

Available options:
png,
jpeg
Example:

"jpeg"

watermark
boolean
default:false

Whether to add a watermark to the generated image

Example:

false

background
enum<string>
default:opaque

Transparency channel setting

Options:

  • opaque: Standard opaque background (default)
  • transparent: Preserve the existing alpha channel of the input image

transparent preserves the input image’s existing transparent background; it does not remove the background.

Restrictions (only for transparent):

  • Exactly 1 input image is required
  • The input must be a PNG with at least one transparent pixel; webp, jpeg, other formats, or PNG files without transparent pixels are rejected by the model (failed tasks are fully refunded)
  • Output is always png: omitting output_format automatically selects png, while specifying output_format=jpeg is rejected
Available options:
opaque,
transparent
Example:

"opaque"

callback_url
string<uri>

HTTPS callback address after task completion

Callback Timing:

  • Triggered when task is completed, failed, or cancelled
  • Sent after billing confirmation is completed

Security Restrictions:

  • Only HTTPS protocol is supported
  • Callback to internal IP addresses is prohibited (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
  • URL length must not exceed 2048 characters

Callback Mechanism:

  • Timeout: 10 seconds
  • Maximum 3 retries on failure (retries after 1 second/2 seconds/4 seconds)
  • Callback response body format is consistent with the task query API response format
  • Callback address returning 2xx status code is considered successful, other status codes will trigger retry
Example:

"https://your-domain.com/webhooks/image-task-completed"

Response

Image generation task created successfully

created
integer

Task creation timestamp

Example:

1757165031

id
string

Task ID

Example:

"task-unified-1757165031-seedream5flash"

model
string

Actual model name used

Example:

"doubao-seedream-5.0-flash"

object
enum<string>

Specific task type

Available options:
image.generation.task
progress
integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100
Example:

0

status
enum<string>

Task status

Available options:
pending,
processing,
completed,
failed
Example:

"pending"

task_info
object

Async task information

type
enum<string>

Task output type

Available options:
text,
image,
audio,
video
Example:

"image"

usage
object

Usage and billing information