Skip to main content
POST

Authorizations

Authorization
string
header
required

A workspace API key beginning with gengen_live_.

Body

application/json

Normalized GENGEN request for BytePlus Seedance video models. Other models share this endpoint but have separate reference pages and request parameter sets. Seedance 2.5 accepts up to 10 reference videos and 10 reference audio clips. Each clip must be 2–30 seconds long, and each media type has a separate 30-second combined-duration limit.

Seedance 2.5 Flash supports up to 10 images, 5 videos including the source, and 5 audio clips, with the same duration limits. Flash supports only 480p/720p and does not support Draft workflows.

For Seedance 2.5 (including Flash), explicitly supplied omni-reference modes are converted to BytePlus task-type hints. Omitted modes retain BytePlus's default auto classification behavior.

model
enum<string>
required

Supported BytePlus Seedance model IDs:

  • dreamina-seedance-2-5-260628 — Seedance 2.5
  • dreamina-seedance-2-5-flash-261115 — Seedance 2.5 Flash
  • dreamina-seedance-2-0-260128 — Seedance 2.0
  • dreamina-seedance-2-0-fast-260128 — Seedance 2.0 Fast
  • dreamina-seedance-2-0-mini-260615 — Seedance 2.0 Mini
  • seedance-1-5-pro-251215 — Seedance 1.5 Pro
Available options:
dreamina-seedance-2-5-260628,
dreamina-seedance-2-5-flash-261115,
dreamina-seedance-2-0-260128,
dreamina-seedance-2-0-fast-260128,
dreamina-seedance-2-0-mini-260615,
seedance-1-5-pro-251215
Example:

"dreamina-seedance-2-0-260128"

mode
enum<string>

Generation mode. If omitted, GENGEN attempts to infer the mode from the supplied assets for request construction, but does not send an explicit Seedance 2.5 task-type hint; BytePlus therefore keeps its default auto classification behavior. Seedance 2.5, 2.0, 2.0 Fast, and 2.0 Mini support all six values. Seedance 1.5 Pro supports only text_to_video, image_first_frame, and image_first_last_frame.

Supported values:

  • text_to_video — generate from a text prompt
  • image_first_frame — animate a first-frame image
  • image_first_last_frame — interpolate between first and last frames
  • multimodal_reference — guide generation with image, video, or audio references; maps to Seedance 2.5 task type reference
  • video_modify — edit an existing source video; maps to Seedance 2.5 task type edit
  • video_extend — extend an existing source video; maps to Seedance 2.5 task type extend

Explicit Seedance 2.5 omni-reference modes enable submission-time validation of their task-specific constraints. BytePlus still checks prompt intent during processing. A conflicting prompt can fail asynchronously with InvalidParameter.TaskTypeMismatch. Automatic classification can return InvalidParameter.TaskTypeConstraint asynchronously when the inferred task conflicts with supplied controls.

Available options:
text_to_video,
image_first_frame,
image_first_last_frame,
multimodal_reference,
video_modify,
video_extend
prompt
string

Creative text instruction. Required for text_to_video, video_modify, and video_extend. A video-editing prompt must clearly describe the intended edit, such as adding, removing, replacing, or changing content. A video-extension prompt must clearly ask to extend or continue the source video. Recommended for every other BytePlus Seedance mode. Refer to audio clips as Audio 1, Audio 2, etc., following their one-based order in assets.referenceAudios, independently of images and videos.

contentPreFilter
boolean
default:true

Apply content pre-filtering before submitting the task.

assets
object

Image, video, and audio inputs supported by BytePlus Seedance.

controls
object

Output and task controls supported by BytePlus Seedance.

providerOptions
object

Response

The task was accepted or completed synchronously by the selected provider.

Standard task fields are listed first. Additional provider-native and legacy aliases can be appended for compatibility.

id
string
required

Public GENGEN task ID.

model
string
required

Public model ID selected for the task.

status
string
required

Task state. Common values include pending, queued, running, processing, succeeded, completed, failed, cancelled, and expired.

outputs
object
required
stage
enum<string>

Present during local reference preparation or queuing; omitted for provider-native states.

Available options:
preparingAssets,
queued,
failed
message
string

Optional informational notice for a Seedance task that is still processing more than 420 seconds after upstream creation. This notice is omitted otherwise; existing upstream passthrough messages are unchanged.

Example:

"Video generation is taking longer than usual. Seedance may be experiencing high demand. Your video is still generating."

draft
boolean

Whether this Seedance output is a draft preview.

draftTaskId
string

Public GENGEN source draft ID for a finalized video.

createdAt
string<date-time>
updatedAt
string<date-time>
statusUpdateTime
string<date-time>
failureReason
string
error

Structured task failure or a compatibility error.

created_at

Compatibility timestamp returned by a provider or legacy endpoint.

updated_at

Compatibility timestamp returned by a provider or legacy endpoint.

status_update_time

Compatibility timestamp returned by a provider or legacy endpoint.

failure_reason
string
task_id
string

Compatibility alias for id.

video_url
string<uri> | null

Compatibility alias for the first video output.

videos
string<uri>[]

Compatibility alias for outputs.videos.

enhanced_prompt
string
detail
any
task_info
any
content
any
output
any
data
any
usage
object

Model-specific usage on successful retrieval. Seedance reports token counts when supplied. Other providers publish their own fields in the corresponding task reference.

output_format
enum<string>

Compatibility-only provider field containing the effective Seedance 2.5 output format.

Available options:
mp4,
mov