Video generation is always asynchronous . You’ll receive a generation ID immediately, then poll for the result. Processing typically takes 20–180 seconds depending on the model.
Request
Authorization: Bearer nb_YOUR_API_KEY
Text description of the video to generate.
Starting image URL for image-to-video generation. When provided, the video animates from this image.
Video duration in seconds. Supported values: 5 or 10 (model-dependent).
Output aspect ratio: 16:9, 9:16, 1:1
Elements to avoid in the video.
Request Example
cURL — Text to Video
cURL — Image to Video
Python
curl -X POST https://neuralbox.top/api/v2/generate \
-H "Authorization: Bearer nb_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-v2.1",
"prompt": "A time-lapse of a blooming flower, macro photography, soft natural light",
"duration": 5,
"aspect_ratio": "16:9"
}'
Initial Response (Pending)
{
"id" : 18500 ,
"status" : "pending" ,
"model_slug" : "kling-v2.1" ,
"processing_ms" : null ,
"created_at" : "2026-03-08T12:05:00Z"
}
Completed Response
{
"id" : 18500 ,
"status" : "completed" ,
"model_slug" : "kling-v2.1" ,
"result_url" : "https://storage.neuralbox.top/generations/18500.mp4" ,
"tokens_spent" : 26 ,
"result_metadata" : { "duration" : 5 , "width" : 1920 , "height" : 1080 },
"created_at" : "2026-03-08T12:05:00Z" ,
"completed_at" : "2026-03-08T12:05:55Z"
}
Model Comparison
Model Tokens Speed Best For luma-flash215–93 Fast (~20–30s) Quick prototypes kling-v2.126–94 Medium (~45–90s) Versatile, high quality minimax-video88 Medium (~60s) Character consistency luma-ray242–180 Medium (~60–120s) Cinematic quality mj-video-480p / mj-video-720p50–320 Slow (~90s) Artistic style
Token cost depends on duration and resolution. Use Calculate Price for exact cost.