Skip to main content
POST

Authorizations

​
Authorization
string
header
default:${YOUR_API_KEY}
required

Neural4D API key using the Bearer scheme.

Body

application/json
​
model
enum<string>
required

Video generation model identifier. Parameter defaults and allowed values depend on the selected model.

Available options:
bytedance/seedance-2.0
Example:

"bytedance/seedance-2.0"

​
prompt
string
required

Required text instruction describing the video to generate.

Required string length: 1 - 1000
​
output_with_audio
boolean
default:true

Whether to generate native audio with the video.

​
resolution
enum<string>
default:720p

Resolution allowed by the selected video model.

Available options:
480p,
720p,
1080p,
4K
Example:

"720p"

​
aspect_ratio
enum<string>
default:16:9

Aspect ratio allowed by the selected video model.

Available options:
1:1,
16:9,
9:16,
4:3,
3:4
Example:

"16:9"

​
duration
enum<integer>
default:5

Duration allowed by the selected video model, in seconds.

Available options:
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15
Required range: 4 <= x <= 15
​
n
integer
default:1

Number of video generation tasks to create.

Required range: 1 <= x <= 4
​
frame_images
object[]

First-frame and last-frame images uploaded through POST /openapi/v1/files. Supported formats are JPG, JPEG, PNG, and WEBP. Each frame_type may appear at most once, and every item requires file_id.

Required array length: 1 - 2 elements
​
input_references
object[]

Uploaded image, video, and audio reference assets. Images support JPG, JPEG, PNG, and WEBP; videos support MP4 and MOV; audio supports MP3 and WAV. The endpoint accepts up to six images, four videos, and two audio files. Each audio file must be 2 to 15 seconds and no larger than 15 MB, and the combined audio duration must not exceed 15 seconds. Audio must be accompanied by at least one image or video. The downstream request body must not exceed 64 MB; do not Base64-encode large files. Every item declares its media type and requires file_id.

Required array length: 1 - 12 elements

One typed image, video, or audio reference using a file ID returned by the file upload endpoint.

Response

Generation tasks accepted

​
id
string
required

Batch task ID returned by the generation request.

Example:

"normal-video-c50fe63e-699d-4d61-93f5-2099ab159d6d"

​
data
object[]
required

Generated child items created by the request.

Minimum array length: 1
​
status
enum<string>
required

Current status shared by the submitted video tasks.

Available options:
queued,
processing,
succeeded,
failed
​
created_at
integer<int64>
required

Unix timestamp in seconds when the batch task was created.

​
mode
enum<string>
required

Video generation mode shared by the submitted tasks.

Available options:
text_to_video,
first_frame_image_to_video,
first_last_frame_image_to_video,
reference_to_video
​
model
enum<string>
required

Video generation model used by the submitted tasks.

Available options:
bytedance/seedance-2.0,
bytedance/seedance-2.0-fast,
google/veo-3.1,
xai/grok-imagine
​
usage
object

Total credits charged for the submitted tasks when available.