Skip to main content
POST
/
api
/
v1
/
jobs
/
createTask
curl -X POST https://kinovi.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-20",
    "inputs": {
      "prompt": "A serene mountain landscape at golden hour, cinematic camera slowly panning right",
      "duration": "5",
      "aspectRatio": "16:9"
    }
  }'

{
  "taskId": "task_clxxxxxxxxxxxxxx"
}

Documentation Index

Fetch the complete documentation index at: https://seedance2-pro.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

Generate videos purely from text descriptions — no images needed.

​
How It Works

  1. You send a text prompt describing the video you want
  2. Seedance 2.0 generates a video (4–15 seconds) based on your description
  3. You poll the task status or receive a webhook when the video is ready

​
Pricing

ResolutionPro (seedance-20)Fast (seedance2-fast)
1080p (default)83 cr/sec—
720p40 cr/sec28 cr/sec
480p15 cr/sec10 cr/sec
4K Upscale+28 cr/sec+28 cr/sec
A 5-second 720p video costs 200 credits ($1.00) with Pro, or 140 credits ($0.70) with Fast. See Pricing for full plan comparison.

​
Parameters

ParameterTypeRequiredDescription
modelstringYesseedance-20 (seedance2.0-pro) or seedance2-fast (seedance2.0-fast)
callBackUrlstringNoWebhook URL to receive task completion notification
inputsobjectYesGeneration parameters (see below)

​
inputs

ParameterTypeRequiredDescription
promptstringYesText description of the video you want to generate. Be specific about scenes, motions, camera movements, lighting, and style. Max 4000 characters.
durationstringNoVideo length in seconds: "4" to "15". Defaults to "5" if omitted.
aspectRatiostringNoAspect ratio: 16:9, 9:16, 1:1, 3:4, 4:3, 21:9. Defaults to 16:9 for text-to-video.
modestringNokeyframe (default) — normal generation. reference — enables Omni Reference mode with multi-material support (images, videos, audio).
outputResolutionstringNoOutput resolution: 1080p (default), 720p, or 480p.
upscaleResolutionstringNoSet to 4k to upscale the output to 4K resolution.

​
Prompt Tips

Write better prompts for better results:
  • Be specific about motion: “camera slowly panning right” is better than “moving camera”
  • Describe lighting and atmosphere: “golden hour warm light” vs just “daytime”
  • Include style keywords: “cinematic”, “documentary”, “anime”, “watercolor”
  • Mention camera angles: “low angle shot”, “aerial view”, “close-up”
  • Keep it concise: Focus on the key visual elements rather than writing a paragraph

​
Response

​
Status Values

StatusDescription
waitingTask queued, waiting to start
generatingVideo is being generated (typically 1–3 minutes)
successGeneration completed, video URL available in output
failGeneration failed, check error field for details

​
Error Codes

HTTP StatusDescriptionCommon Cause
200Success—
400Invalid parametersMissing prompt, invalid duration value
401Authentication failedInvalid or missing API key
402Insufficient creditsNot enough credits for the requested duration
429Concurrency limit exceededToo many tasks in progress, wait for some to complete
500Server errorInternal error, retry later
curl -X POST https://kinovi.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-20",
    "inputs": {
      "prompt": "A serene mountain landscape at golden hour, cinematic camera slowly panning right",
      "duration": "5",
      "aspectRatio": "16:9"
    }
  }'

{
  "taskId": "task_clxxxxxxxxxxxxxx"
}