Introduction
Wan 3.0 Pro Video extend continues a clip you already have. Send it as video_url, and add a prompt for what happens next if you want one. The final frame of your clip becomes the opening frame of a new Wan 3.0 Pro image-to-video shot of 2 to 30 seconds, and the two are joined into one MP4: your original first, then the continuation, with the repeated seam frame removed. The new segment also comes back as its own file, so you can keep extending or edit the pieces separately.
Key features & highlights
Continuity comes from the last frame. Wardrobe, set, light and where everyone stands carry over because the new segment literally starts on your final frame. Motion does not carry over the same way: the model sees one still, not the whole clip, so describe the movement you want to continue instead of assuming it will keep its speed or direction.
You can choose the ending. last_image_url is an optional target end frame: the new segment closes exactly on that image, which suits a product that has to return to its hero angle or a move that has to land on a fixed composition. Without it, the model decides how the shot ends.
The tiers are those of Wan 3.0 Pro image-to-video: 1080p, 2k and 4k. A native render tops out at 1080p, so 2k and 4k are enlarged from it, and there is no 480p or 720p tier.
One file back, plus the new piece on its own. The joined result is an H.264 MP4 with AAC sound. It keeps your clip’s frame rate and its framing, with no black bars. To line the seam up, the picture may be trimmed or adjusted by a few percent at the edges. If the model returns a noticeably different shape, the new segment is scaled to fill your frame and centered, cropping what spills over. Sound from your source stays; sound generated for the new segment follows it; a silent side is padded with silence so picture and sound stay in step at the seam. The second asset in the output is the new segment alone, ready for another extend or for an editor.
Everything else is Wan 3.0 Pro image-to-video: the same content range and the same per-second price, and a failed generation is refunded the same way. If the generation succeeds but the join itself cannot be built, the task fails and the charge is refunded.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | No | Optional. Describe what happens next: the action that follows and the camera move. at least 1 characters · at most 20000 characters |
video_url | Yes | The clip to continue: MP4, MOV or WebM, up to 60 seconds. Its final frame becomes the opening frame of the new segment, so cut it on a clean, sharp frame. at least 1 characters |
last_image_url | No | Optional target end frame: the new segment closes exactly on this image, used as its last frame rather than as loose guidance. at least 1 characters |
resolution | No | Resolution tier of the new segment: 1080p, 2k or 4k, default 1080p. |
duration_seconds | No | Length of the new segment: any whole number from 2 to 30, or -1 to let the model choose, in which case 30 seconds are held up front and the charge settles on the length delivered. |
generate_audio | No | On by default, so the new segment comes with generated sound. Your source keeps its own sound either way; when one side is silent, the joined file is padded with silence. Default: |
enable_prompt_expansion | No | On by default. The prompt is expanded before generation, which helps thin briefs and fights you on precise ones, so switch it off once your prompt describes the shot exactly. Default: |
seed | No | 0 to 2147483647. Hold it steady to compare one changed field at a time; drop it for variety. |
Pricing
Billed per second of the new segment at the resolution tier you choose; the source clip you send is not billed. If the new segment is generated but the join cannot be built, the task fails and the full charge is refunded.
| Specification | Price |
|---|---|
| $0.144 / second |
| $0.16 / second |
| $0.184 / second |
Use cases
Lengthen a shot that ended too early: a product turntable that stops before the label faces camera, or a walk that cuts before the subject reaches the door. Extend it by a few seconds and describe only the remaining motion.
Build a longer sequence step by step. Generate a first shot, extend it, then extend the joined result again; each step bills only the seconds it adds. Because every step starts from a single frame, watch each seam before stacking the next one.
Prompt guide & pro tips
Describe the next beat, not the whole scene. The frame already fixes who and where, so spend the prompt on the action that follows and the camera move. Repeat the camera language your clip ended on, such as a slow push in or a locked shot, so the seam reads as one take. The prompt is optional; without one, the model continues from the frame alone.
Trim before you extend. The last frame is the only thing the model sees, so a blurred, mid-cut or heavily compressed ending carries straight into the continuation. Cut your source on a clean, sharp frame first. Sources of up to 60 seconds are accepted as MP4, MOV or WebM.
Keep the tier in step with your source and set duration_seconds to the length you actually need: the charge follows the new segment only. Settle the motion at 1080p with a fixed seed before you pay for a 2k or 4k render.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "alibaba/wan-3.0-pro/video-extend",
"input": {
"duration_seconds": 5,
"resolution": "1080p",
"video_url": "https://example.com/reference.mp4"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.
