XBAI API
Video ModelsSeedance

Seedance 2.5 Global

Seedance 2.5 through the global route. Text-to-video, first/last frames, or multimodal references, 4 to 30 seconds.

POST/api/v1/jobs/createTask

Seedance 2.5 Global runs Seedance 2.5 through an overseas generation route. It supports text-to-video, first/last-frame image-to-video, and multimodal references that combine a prompt with up to 30 images, 10 videos and 10 audio clips. It produces 4 to 30 seconds of 480p or 720p video, can generate a matching audio track, and supports video extension and MOV output.

Set model to seedance-2.5-global. The request is asynchronous: store the returned taskId, then query the task or wait for the callback.

Request example

cURL
curl -X POST https://api.xbaiapi.com/api/v1/jobs/createTask \
  -H "Authorization: Bearer xb-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5-global",
    "input": {
      "prompt": "a city intersection on a rainy night, neon reflected on wet asphalt, slow push-in",
      "resolution": "720p",
      "duration": 10,
      "ratio": "16:9",
      "generateAudio": true,
      "imageUrls": ["https://example.com/street.jpg"]
    },
    "callBackUrl": "https://your-server.com/webhook"
  }'

Parameters

FieldTypeRequiredNotes
modelstringYesFixed value seedance-2.5-global
input.promptstringConditionalUp to 20480 characters; optional for first/last-frame image-to-video
input.resolutionstringNo480p or 720p, defaults to 720p
input.durationnumberNoInteger seconds from 4 to 30, defaults to 5. Smart duration -1 is currently unavailable
input.ratiostringNoadaptive, 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9. Defaults to adaptive; must be adaptive with first/last frames
input.generateAudiobooleanNoDefaults to true
input.firstFrameUrlstringNoFirst frame, up to 30 MB; providing it selects image-to-video and is required in that mode
input.lastFrameUrlstringNoOptional last frame, up to 30 MB; requires a first frame
input.imageUrlsstring[]NoUp to 30 reference images, up to 50 MB each
input.videoUrlsstring[]NoUp to 10 reference videos, 2 to 30 seconds and up to 50 MB each; total duration at most 30 seconds
input.audioUrlsstring[]NoUp to 10 reference audio clips, 2 to 30 seconds and up to 50 MB each; total duration at most 30 seconds; requires a reference image or video
input.webSearchbooleanNoWeb search enhancement, text-to-video only; defaults to false
input.realPersonModebooleanNoReal person mode, image-to-video and multimodal only; defaults to true
input.conversionSlotsstring[]NoAsset conversion slots, image-to-video and multimodal only; defaults to ["all"]; image-to-video accepts firstFrameUrl and lastFrameUrl; multimodal accepts image1 through image30 and video1 through video10
input.omniReferenceTaskTypestringNoMultimodal only. auto, reference, or extend; defaults to auto. extend continues a video and requires videoUrls with ratio set to adaptive
input.outputFormatstringNomp4 or mov; defaults to mp4
input.watermarkbooleanNoAdd a watermark; defaults to false
input.returnLastFramebooleanNoRequest a last frame; defaults to false. The public task result still returns only the video
input.seednumberNoInteger from -1 to 2147483647; defaults to -1
callBackUrlstringNoOmit it and poll the query endpoint instead

A prompt alone uses text-to-video, firstFrameUrl selects first/last-frame image-to-video, and reference lists use the multimodal endpoint. First/last frames cannot be combined with reference lists. Media can be a publicly reachable HTTP(S) URL or a Base64 media data URI. File sizes and durations are checked by the generation service.

Your account is charged by output duration at the same per-second rates as Seedance 2.0, using the reference video rate when videoUrls is present. See pricing.

Response

Success response
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "xb_a1b2c3d4e5f6...",
    "creditsCharged": 330
  }
}

When the task succeeds, read the video URL from resultJson.resultUrls in the query response.

On this page