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.
Idle
$0.5per run·~20 / $10
Continue directly as he reads the message and looks toward the woman across the table. She gives him a subtle nod, stands, and begins walking toward the casino exit. He leaves his cards behind and follows her. The camera follows beside them through the crowd, ending on the rotating cameras overhead. Preserve both characters, clothing, casino setting, and elegant thriller tone.
Continue the scene smoothly: the man keeps walking forward along the rainy street, natural steady movement, consistent lighting and camera motion.
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.
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.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Positive prompt describing how the video should continue, including subject action, motion, camera movement, scene progression, and visual direction. |
| video | Yes | Source video URL. Inputs longer than 120 seconds are automatically trimmed to their last 120 seconds before extension. |
| last_image | No | Optional last-frame image used to guide the ending of the generated continuation. Supports URL or Base64-encoded data. |
| resolution | No | Output resolution: 480p, 720p, or 1080p. Default: 720p. |
| duration | No | Length of the new segment to append, in seconds. Range: 2–30. Default: 5. |
| enable_prompt_expansion | No | Enable automatic prompt optimization and expansion. Default: false. |
| enable_audio | No | Generate audio for the newly appended segment. Existing source audio is preserved. Default: true. |
| seed | No | Random seed for generation. Use -1 for a random seed. |
last_image when the final frame of the extension needs stronger control.480p, 720p, or 1080p.2 to 30.enable_prompt_expansion when you want the prompt optimized automatically.enable_audio enabled when the newly generated segment should include generated audio.-1 for random generation.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.
| Resolution | Per 5s | Per Billed Second |
|---|---|---|
| 480p | $0.25 | $0.05 |
| 720p | $0.50 | $0.10 |
| 1080p | $1.00 | $0.20 |
| Extension Duration | 480p | 720p | 1080p |
|---|---|---|---|
| 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 | $6.00 |
last_image to guide how the newly generated continuation should end.last_image when the extension needs to arrive at a specific final composition or scene state.duration after the motion is working well.480p for lower-cost testing before generating higher-resolution results.enable_prompt_expansion when the continuation instruction is short or needs additional detail.seed when comparing prompts or parameter changes.video and prompt are required.duration controls only the length of the newly generated segment.2–30 seconds and defaults to 5.120 seconds are automatically trimmed to their last 120 seconds.enable_audio controls audio generation for the new segment and defaults to true.enable_prompt_expansion defaults to false.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/video-extend with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 3.0 Video Extend below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": false,
"enable_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/video-extend" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/video-extend";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": false,
"enable_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": False,
"enable_audio": True
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/video-extend", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Wan 3.0 Video Extend is a Alibaba model for video extension, exposed as a REST API 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. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-3.0-video-extend.
Wan 3.0 Video Extend starts at $0.50 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `video`, `resolution`, `duration`, `seed`, `enable_audio`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-3.0-video-extend.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.