Seedance 1.5 Pro Video-Extend

Overview

Seedance 1.5 Pro Video-Extend turns short source clips into longer videos with natural motion continuation, stable aesthetics, and a clean final output. APIXO analyzes the source video and applies its video extension workflow to produce a longer continuation through the standard async task API. It is a strong fit for extending ad creatives, short-drama shots, talking-head clips, and other short-form scenes where you want the next moment of the same shot instead of a brand-new composition.

Capability	Value
Model ID	`seedance-1-5-pro-extend`
Required mode	`video-extend`
Source input	Exactly 1 public video URL in `video_urls`
Prompt length	3-2500 characters
Resolutions	`480p`, `720p`, `1080p`
Duration	4-12 seconds
Audio	Required `sound` toggle
Aspect handling	Adaptive continuation based on the source clip; no public `aspect_ratio` field
Reproducibility	Optional `seed` support
Output	Final stitched video URL in `resultJson.resultUrls`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/seedance-1-5-pro-extend`	Submit a video extend task
`GET`	`/statusTask/seedance-1-5-pro-extend?taskId={taskId}`	Poll task status and retrieve the final stitched video

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request extends a short source clip and returns a new taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/seedance-1-5-pro-extend" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "video-extend",
      "prompt": "keep the same framing, smile at the camera, then ride away naturally",
      "resolution": "480p",
      "duration": 4,
      "sound": false,
      "camera_fixed": true,
      "video_urls": [
        "https://example.com/source.mp4"
      ]
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/seedance-1-5-pro-extend?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/xxx.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965695412,
    "costTime": 84483
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "API_SERVICE_UNAVAILABLE",
    "failMsg": "Video extend processing is temporarily unavailable",
    "createTime": 1767965610929,
    "completeTime": 1767965620132,
    "costTime": 9203
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

{
  "request_type": "async",
  "input": {
    "mode": "video-extend",
    "prompt": "continue the same shot with a gentle smile and then a smooth ride-away",
    "video_urls": [
      "https://example.com/source.mp4"
    ],
    "resolution": "720p",
    "duration": 8,
    "sound": true,
    "camera_fixed": true,
    "seed": 123456,
    "watermark": false
  }
}

Parameters

request_type

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

input

object

required

Seedance 1.5 Pro Video-Extend input parameters.

Show properties

mode

string

default:"video-extend"

required

Required public mode for this model. Supported values: video-extend.

prompt

string

required

Continuation prompt for the next moment of the same shot. Supports 3-2500 characters after trimming.

video_urls

string[]

required

Source clip URLs. Provide exactly 1 public video URL. APIXO analyzes the tail of this clip before generating the continuation.

resolution

string

required

Output resolution for the continuation workflow. Supported values: 480p, 720p, 1080p.

duration

integer

required

Requested extension duration in seconds. Accepts integer values from 4 to 12; numeric strings are also accepted by the backend.

sound

boolean

required

Whether to generate audio with the extended segment. Use true for generated sound, or false for a silent result.

camera_fixed

boolean

default:"true"

Whether to keep the camera behavior stable during continuation. Supported values: true, false. If omitted, the backend defaults this field to true.

seed

integer

Optional random seed for more reproducible continuation results. Supported range: 0 to 2147483647.

watermark

boolean

default:"false"

Whether to keep the upstream watermark when the selected route supports it. Supported values: true, false.

Legacy fixed_lens is still accepted for compatibility, but new integrations should use camera_fixed.

Response format

Submit task response

POST /generateTask/seedance-1-5-pro-extend returns a task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique task identifier used with the status endpoint.

Status response fields

taskId

string

Unique task identifier.

state

string

Current task state: processing, success, or failed.

resultJson

string

JSON string containing the final stitched video URLs. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds. Present after completion when available.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/seedance-1-5-pro-extend" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "video-extend",
      "prompt": "continue the same scene with a smooth smile, then leave the frame naturally",
      "video_urls": [
        "https://example.com/source.mp4"
      ],
      "resolution": "720p",
      "duration": 8,
      "sound": true,
      "camera_fixed": true,
      "seed": 123456
    }
  }'

The callback payload uses the same unified response shape as the status endpoint when the task reaches a final state. See Webhooks for delivery requirements and retry behavior.

Billing

Seedance 1.5 Pro Video-Extend uses the same per-second pricing tiers as Seedance 1.5 Pro, so cost stays predictable even though the workflow includes continuation analysis and final stitching.

Resolution	`sound`	Price
`480p`	`false`	`$0.012 / second`
`480p`	`true`	`$0.024 / second`
`720p`	`false`	`$0.024 / second`
`720p`	`true`	`$0.048 / second`
`1080p`	`false`	`$0.052 / second`
`1080p`	`true`	`$0.104 / second`

Total cost is the per-second price multiplied by the requested duration. For example, 720p with sound: false for 8 seconds costs $0.192. For current route and market comparison pricing, see Pricing.

Latency and polling

This workflow includes tail analysis and final stitching in addition to upstream generation, so it may take slightly longer than direct text-to-video or image-to-video generation. In return, you get a cleaner continuation workflow and a single ready-to-use output URL.

Requested duration	Recommended first poll	Poll interval
`4` seconds	45s after task creation	5s-10s
`8` seconds	60s after task creation	5s-10s
`12` seconds	90s after task creation	5s-10s

For production workloads, use callback mode to avoid frequent polling while the continuation and merge steps complete.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, missing required field, unsupported resolution, invalid duration, or malformed source URL array	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or internal processing error	Retry with backoff; contact support if it repeats
`502`	Upstream error	Retry with backoff
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Task failure codes

Fail code	Meaning	What to do
`MISSING_REQUIRED_PARAM`	A required field such as `mode`, `prompt`, `video_urls`, `resolution`, `duration`, or `sound` is missing	Fix the request before retrying
`INVALID_PARAMETER`	One or more fields use an unsupported value or type	Check `mode`, `resolution`, `duration`, `sound`, `camera_fixed`, `seed`, and `watermark`
`API_SERVICE_UNAVAILABLE`	Tail analysis, merge processing, or upstream continuation is temporarily unavailable	Retry later
`SensitiveContent`	The continuation prompt or generated content violated upstream policy	Change the prompt and retry
`RateLimited`	The upstream route rate limited the task	Retry later with backoff
`Timeout`	The workflow did not finish in time	Retry, simplify the prompt, or use callback mode
`Unknown error`	The failure did not match a known public mapping	Retry or contact support with the `taskId`

Common validation fixes

Symptom	Fix
`mode` is rejected	Set `input.mode` to `video-extend`
`video_urls` is rejected	Provide exactly 1 public video URL
`resolution` is rejected	Use `480p`, `720p`, or `1080p`
`duration` is rejected	Send an integer from `4` to `12`
`sound` is rejected	Send a boolean: `true` or `false`
Prompt length error	Keep the trimmed prompt within 3-2500 characters

See Error Codes for the full error reference.

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Task failure codes

​Common validation fixes

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Common validation fixes

Related links