Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.6per run·~16 / $10
A steam train races across an endless desert at sunset while a masked female outlaw rides beside it on a black horse. She leaps onto the moving train, fights her way across the roof, and reaches a guarded carriage carrying a frightened young prisoner. As soldiers surround them, she cuts the carriage loose, sending it down a different track toward a distant canyon. Epic western action film, fast-paced camera movement, dynamic horseback tracking shots, dramatic close combat, sweeping aerial views, flying dust, golden sunset, practical stunt realism, anamorphic lens flares, cinematic scale.
Wan 3.0 Reference-to-Video combines reference images, videos, and audio with a prompt to create coherent video scenes. It supports multimodal reference guidance for character consistency, object control, motion direction, audio style, and scene composition.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text prompt describing the desired scene, subject, motion, camera movement, lighting, and style. |
| reference_images | Conditional | Up to 10 reference images. At least one reference media array is required. |
| reference_videos | Conditional | Up to 5 reference video inputs. Each video must be MP4 or MOV, 1–15 seconds, 240–4096 pixels on each side, no more than 8:1 aspect ratio, and no more than 100 MB. Total reference video duration must not exceed 15 seconds. |
| reference_audios | Conditional | Up to 5 reference audio files. Total reference audio duration must not exceed 15 seconds. |
| resolution | No | Output resolution: 480p, 720p, or 1080p. Default: 720p. |
| aspect_ratio | No | Output aspect ratio. Default: 16:9. |
| duration | No | Output duration in seconds. Range: 2–30. Default: 5. |
| thinking_mode | No | Enable deep-thinking mode for more deliberate prompt interpretation. Default: false. |
| enable_audio | No | Include audio in the output. Default: true. |
| seed | No | Random seed from 0 to 2147483647. |
At least one of reference_images, reference_videos, or reference_audios is required.
480p for lower-cost drafts, 720p for balanced output, or 1080p for higher quality.2 to 30 seconds.enable_audio enabled when audio is needed.thinking_mode for complex prompts with multiple reference requirements.Pricing is based on output resolution and billed duration.
Billed duration is rounded up to the next whole second and clamped to the 2–30s range.
| Resolution | Per 5s | Per second |
|---|---|---|
| 480p | $0.35 | $0.07 |
| 720p | $0.65 | $0.13 |
| 1080p | $1.40 | $0.28 |
| Resolution | 2s | 5s | 10s | 30s |
|---|---|---|---|---|
| 480p | $0.14 | $0.35 | $0.70 | $2.10 |
| 720p | $0.26 | $0.65 | $1.30 | $3.90 |
| 1080p | $0.56 | $1.40 | $2.80 | $8.40 |
480p for quick drafts and 1080p for higher-quality output.thinking_mode for prompts that combine multiple references or detailed scene requirements.seed when you want more reproducible results.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 3.0 Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"thinking_mode": false,
"enable_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video" \
-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=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"thinking_mode": false,
"enable_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
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",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"thinking_mode": 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/reference-to-video", 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 = task.get("urls", {}).get("get") or 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"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Wan 3.0 Reference To Video is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity. 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-reference-to-video.
Wan 3.0 Reference To Video starts at $0.60 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`, `aspect_ratio`, `resolution`, `duration`, `seed`, `reference_images`. 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-reference-to-video.
Median end-to-end generation time on WaveSpeedAI is around 731 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
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.