curl --request POST \
  --url https://gengen.farm/api/gengen/v1/contents/generations/tasks \
  --header 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "dreamina-seedance-2-0-260128",
    "mode": "text_to_video",
    "prompt": "A kitten yawns at the camera in warm morning light.",
    "contentPreFilter": true,
    "controls": {
      "duration": 5,
      "resolution": "720p",
      "ratio": "16:9",
      "generateAudio": true,
      "watermark": false
    }
  }'

{
  "id": "seedance20:cgt-20260419-abcdef1234567890",
  "model": "dreamina-seedance-2-0-260128",
  "status": "pending",
  "outputs": {
    "videos": [],
    "images": []
  }
}

{
  "error_code": "gengen.model_required",
  "error_params": {
    "field": "model"
  },
  "error": "A model is required"
}

{
  "error_code": "gengen.auth_required",
  "error": "Missing Authorization bearer token"
}

{
  "error_code": "seedance.insufficient_balance",
  "error": "Insufficient available balance"
}

{
  "error_code": "gengen.api_key_revoked",
  "error": "GENGEN API key has been revoked"
}

{
  "error_code": "<string>",
  "error_params": {},
  "error": "<string>"
}

Video API

Create a video generation task

Submit an asynchronous BytePlus Seedance video generation task. This reference intentionally documents only the BytePlus models and parameters, even though other providers use the same public GENGEN endpoint.

For Seedance 2.5, each reference video or audio clip must be 2–30 seconds long. You can provide up to 10 reference videos and 10 reference audio clips. The combined duration of all reference videos and the combined duration of all reference audio clips must each stay within 30 seconds.

For Seedance 2.5 omni-reference workflows, an explicitly supplied multimodal_reference, video_modify, or video_extend mode is mapped to BytePlus’s reference, edit, or extend task-type hint. If mode is omitted, the upstream hint remains at its default auto behavior. Edit and extend requests require prompts with clear matching intent.

POST

contents

generations

tasks

curl --request POST \
  --url https://gengen.farm/api/gengen/v1/contents/generations/tasks \
  --header 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "dreamina-seedance-2-0-260128",
    "mode": "text_to_video",
    "prompt": "A kitten yawns at the camera in warm morning light.",
    "contentPreFilter": true,
    "controls": {
      "duration": 5,
      "resolution": "720p",
      "ratio": "16:9",
      "generateAudio": true,
      "watermark": false
    }
  }'

{
  "id": "seedance20:cgt-20260419-abcdef1234567890",
  "model": "dreamina-seedance-2-0-260128",
  "status": "pending",
  "outputs": {
    "videos": [],
    "images": []
  }
}

{
  "error_code": "gengen.model_required",
  "error_params": {
    "field": "model"
  },
  "error": "A model is required"
}

{
  "error_code": "gengen.auth_required",
  "error": "Missing Authorization bearer token"
}

{
  "error_code": "seedance.insufficient_balance",
  "error": "Insufficient available balance"
}

{
  "error_code": "gengen.api_key_revoked",
  "error": "GENGEN API key has been revoked"
}

{
  "error_code": "<string>",
  "error_params": {},
  "error": "<string>"
}

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 upstream providers 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.

For Seedance 2.5, 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-2-0-260128 — 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-2-0-260128,

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.

contentPreFilter

boolean

default:true

Apply content pre-filtering before submitting the task.

assets

object

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

Show child attributes

controls

object

Output and task controls supported by BytePlus Seedance.

Show child attributes

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.

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

Show child attributes

createdAt

string<date-time>

updatedAt

string<date-time>

statusUpdateTime

string<date-time>

failureReason

string

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

any

output_format

enum<string>

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

Available options:

mp4,

mov

Reference

BytePlus

OpenAI

Kling

Higgsfield

MiniMax

Happy Horse

Google

WonderClip

Flash VSR

Wan

Qwen

Create a video generation task

Authorizations

Body

Response