Alibaba Wan 3.0 Video Extend API Documentation

Alibaba Wan 3.0 Video Extend API Documentation

Playground

Try it on WaveSpeedAI!

Wan 3.0 Video Extend continues an existing video with a newly generated segment, preserving the source video and its original audio while supporting optional audio generation for the extension. It supports 480P / 720P / 1080P output, optional last-frame guidance, and prompt control for the next action and camera movement. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 3.0 Video Extend extends an existing video with a newly generated continuation. Provide a source video and a text prompt describing what should happen next, then choose the extension duration and output resolution.


Why Choose This?

  • Video continuation
    Extend an existing video with a newly generated segment.

  • Prompt-guided progression
    Describe how the scene, subject, motion, camera movement, and environment should continue.

  • Optional last-frame guidance
    Use last_image to guide the final frame of the newly generated segment.

  • 2–30 second extension
    Append a new segment from 2 to 30 seconds long.

  • 480p, 720p, and 1080p output
    Choose the resolution that fits your quality and cost requirements.

  • Audio continuation
    Preserve existing source audio and optionally generate audio for the new segment.


Parameters

ParameterRequiredDescription
promptYesPositive prompt describing how the video should continue, including subject action, motion, camera movement, scene progression, and visual direction.
videoYesSource video URL. Inputs longer than 120 seconds are automatically trimmed to their last 120 seconds before extension.
last_imageNoOptional last-frame image used to guide the ending of the generated continuation. Supports URL or Base64-encoded data.
resolutionNoOutput resolution: 480p, 720p, or 1080p. Default: 720p.
durationNoLength of the new segment to append, in seconds. Range: 2–30. Default: 5.
enable_prompt_expansionNoEnable automatic prompt optimization and expansion. Default: false.
enable_audioNoGenerate audio for the newly appended segment. Existing source audio is preserved. Default: true.
seedNoRandom seed for generation. Use -1 for a random seed.

How to Use

  1. Upload a source video — Provide the video you want to continue.
  2. Write a continuation prompt — Describe what should happen after the existing footage ends.
  3. Add last-frame guidance optional — Use last_image when the final frame of the extension needs stronger control.
  4. Choose resolution — Select 480p, 720p, or 1080p.
  5. Set extension duration — Choose how many new seconds to append, from 2 to 30.
  6. Configure prompt expansion optional — Enable enable_prompt_expansion when you want the prompt optimized automatically.
  7. Configure audio optional — Keep enable_audio enabled when the newly generated segment should include generated audio.
  8. Set seed optional — Use a fixed seed for reproducible generation, or -1 for random generation.
  9. Submit — Generate the extended video and retrieve the output.

Pricing

Pricing is based only on the newly generated extension duration and selected resolution.

The source video duration is not included in the pricing calculation.

Billed extension duration is rounded up to the next whole second and limited to the 2–30s range.

ResolutionPer 5sPer Billed Second
480p$0.25$0.05
720p$0.50$0.10
1080p$1.00$0.20

Example Costs

Extension Duration480p720p1080p
2s$0.10$0.20$0.40
5s$0.25$0.50$1.00
10s$0.50$1.00$2.00
20s$1.00$2.00$4.00
30s$1.50$3.00$6.00

Best Use Cases

  • Video continuation — Extend an existing clip while continuing its scene and motion.
  • Narrative extension — Continue a story, action, or character sequence beyond the original ending.
  • Longer creative sequences — Build longer videos by progressively extending shorter clips.
  • Scene progression — Continue camera movement, environmental motion, or subject actions.
  • Last-frame-controlled extension — Use last_image to guide how the newly generated continuation should end.
  • Social and marketing content — Extend short clips into longer promotional or narrative videos.

Pro Tips

  • Describe what should happen after the existing video ends, rather than restating only what is already visible.
  • Keep subject identity, direction of movement, camera motion, and environment consistent in the prompt when continuity matters.
  • Use last_image when the extension needs to arrive at a specific final composition or scene state.
  • Use shorter extensions while testing continuation direction, then increase duration after the motion is working well.
  • Use 480p for lower-cost testing before generating higher-resolution results.
  • Enable enable_prompt_expansion when the continuation instruction is short or needs additional detail.
  • Set a fixed seed when comparing prompts or parameter changes.

Notes

  • video and prompt are required.
  • duration controls only the length of the newly generated segment.
  • Extension duration supports 2–30 seconds and defaults to 5.
  • Source videos longer than 120 seconds are automatically trimmed to their last 120 seconds.
  • The retained source video duration does not affect the generation price.
  • Existing source audio is preserved.
  • enable_audio controls audio generation for the new segment and defaults to true.
  • enable_prompt_expansion defaults to false.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "resolution": "720p",
  "duration": 5,
  "enable_prompt_expansion": false,
  "enable_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/video-extend" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
videostringYes-Source video URL. Inputs longer than 120 seconds are automatically trimmed to their last 120 seconds before extension.
last_imagestringNo--The last frame image for generating the video (optional). Supports URL or Base64-encoded data.
resolutionstringNo720p480p, 720p, 1080pThe resolution of the generated video.
durationintegerNo52 ~ 30Length in seconds of the NEW segment to append (2-30). Final output duration is the retained source duration plus this value.
enable_prompt_expansionbooleanNofalse-If set to true, the prompt optimizer will be enabled.
enable_audiobooleanNotrue-Generate audio for the new segment. Existing source audio is preserved.
seedintegerNo--The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.