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": {
      "urls": ["https://example.com/your-image.jpg"],
      "prompt": "A cinematic shot with smooth camera movement, gentle wind blowing",
      "duration": "5"
    }
  }'
{
  "taskId": "task_clxxxxxxxxxxxxxx"
}
Bring your images to life — provide 1 or 2 images and Seedance 2.0 generates a video from them.

How It Works

  1. You provide 1 or 2 images as the starting point
  2. Optionally add a text prompt to guide the motion and style
  3. Seedance 2.0 generates a video (4–15 seconds) that animates your images
  4. You poll the task status or receive a webhook when the video is ready

Single Image vs Two Images

ModeInputResult
1 imageOne image as the first frameVideo animates outward from that image
2 imagesFirst frame + last frameVideo generates a smooth transition between the two images

Pricing

Standard (seedance-20)

DurationCreditsPriceWith 4K Upscale
4s160$0.80272 credits ($1.36)
5s200$1.00340 credits ($1.70)
8s320$1.60544 credits ($2.72)
10s400$2.00680 credits ($3.40)
15s600$3.001020 credits ($5.10)

Fast (seedance2-fast)

DurationCreditsPriceWith 4K Upscale
4s112$0.56224 credits ($1.12)
5s140$0.70280 credits ($1.40)
8s224$1.12448 credits ($2.24)
10s280$1.40560 credits ($2.80)
15s420$2.10840 credits ($4.20)
Standard rate: 40 credits/sec. Fast rate: 28 credits/sec. 4K upscale: adds 28 credits/sec.1 credit = $0.005 (200 credits = $1).Fast mode generates videos ~2x faster with slightly reduced quality. Use seedance2-fast as the model value.

Authentication

Get API Key: API Key Management Page
Authorization: Bearer YOUR_API_KEY

Parameters

ParameterTypeRequiredDescription
modelstringYesseedance-20 (standard) or seedance2-fast (faster, lower cost)
callBackUrlstringNoWebhook URL to receive task completion notification
inputsobjectYesGeneration parameters (see below)

inputs

ParameterTypeRequiredDescription
urlsarrayYesImage URL(s) to animate. Provide 1 image (first frame) or 2 images (first + last frame). Images must be publicly accessible URLs.
promptstringNoText description to guide the motion, camera movement, and style. Max 4000 characters. While optional, adding a prompt significantly improves results.
durationstringNoVideo length in seconds: "4" to "15". Defaults to "5" if omitted. Directly affects cost (40 credits/sec standard, 28 credits/sec fast).
aspectRatiostringNoAspect ratio: 16:9, 9:16, 1:1, 3:4, 4:3, 21:9. Defaults to 16:9.
modestringNokeyframe (default) — treats image(s) as structural anchor frames. reference — treats images as visual style references; enables Omni Reference mode with video and audio support.
upscaleResolutionstringNoSet to 4k to upscale the output to 4K resolution. Adds 28 credits/sec to the base cost.
Image requirements:
  • Must be publicly accessible URLs (JPEG, PNG, or WebP)
  • Maximum 2 images
  • If providing 2 images, the first is used as the opening frame and the second as the ending frame

Mode: keyframe vs reference

ModeBehaviorWhen to Use
keyframe (default)Image is used as the actual first/last frame of the videoYou want the video to start/end with your exact image
referenceImage is used as visual style guidance, not a literal frameYou want the video to match the look/feel of your image, but not necessarily start from it

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 urls, invalid image URL, 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": {
      "urls": ["https://example.com/your-image.jpg"],
      "prompt": "A cinematic shot with smooth camera movement, gentle wind blowing",
      "duration": "5"
    }
  }'
{
  "taskId": "task_clxxxxxxxxxxxxxx"
}