Introduction
Send video_url (a clip of up to 60 seconds) and a prompt describing what happens next; duration_seconds, resolution, generate_audio, last_image_url and watermark are optional. The platform lifts the last frame of your clip, renders the continuation with Flash image-to-video and splices it onto your footage, keeping your clip's frame rate and its own soundtrack.
| Field | Value |
|---|---|
| Input | Video |
| Output | Video |
| Publisher | ByteDance (Seedance 2.5 Flash, speed tier of Seedance 2.5, announced by BytePlus on 12 November 2026) |
| API names | bytedance/seedance-2.5-flash/text-to-video, image-to-video, reference-to-video, video-edit, video-extend |
| Resolution | 480p or 720p (default 720p); 1080p and 4K not supported |
| Clip length | 4–30 whole seconds, default 5; video-edit follows its 4–30 s source |
| Aspect ratio | 16:9 (default), 9:16, 4:3, 3:4, 1:1, 21:9 or adaptive on text and reference requests; image-to-video follows the start image |
| Reference limits | Up to 10 images, 5 clips (30 s in total) and 5 audio files on reference-to-video |
| Reference clip rules | Each clip counts as at least 2 s and needs about 409,600 pixels (854×480 or larger) |
| Edit inputs |
|
| Audio |
|
| Output options | mp4 (default) or mov; watermark off by default; |
| Billing basis | Per second by resolution; reference clips add their seconds; edits bill source seconds; failed generations are free |
| Measured render time | 84 s to about 11 min for 4 s at 480p (13 November 2026 runs) |
Key features & highlights
Flagship workflows at a lower ceiling
Flash keeps the four Seedance 2.5 workflows that fit drafting (text, start and end frames, mixed references, clip editing), drops 1080p and 4K, and adds a video-extend built on its image-to-video mode. BytePlus presents the trade as results close to the flagship at nearly twice the speed. Our 4-second 480p renders took anywhere from 84 seconds to about 11 minutes, so measure speed on your own queue.
Give every upload a job in the prompt
Name uploads by type and order with a space: @Image 1, @Video 1, @Audio 1. With two portraits as @Image 1 and @Image 2 in 16:9, both people appeared together in one elevator scene and kept their faces, hair and clothes. With one image, one clip and one voice file, the clip's street, yellow tram and tracking camera carried over, but the person stayed back to the camera and the face of @Image 1 barely showed.
A sunny street turned into a snowy evening
Both riders, their bikes, the tram and the camera move matched the source frame by frame, and the weather and light changed while nothing else did. That was a 4.0 s clip at 480p with audio off, which also kept the original soundtrack.
One switch decides whose soundtrack you get
generate_audio is on by default and produces speech, effects and ambience with the picture. In video-edit, switching it off keeps the source clip's own track (44.1 kHz in our test), while switching it on generates a new one that can follow @Audio 1. The switch has no effect on the price.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | Required. Describe only what happens after the last frame: the next action, where the camera goes and what is heard. at least 1 characters · at most 20000 characters |
video_url | Yes | Required. MP4, MOV or WebM, up to 60 seconds and 3840 pixels on the long edge. at least 1 characters |
last_image_url | No | Optional picture for the new segment to finish on, for shots that must arrive at a known pose or framing. |
resolution | No | 480p or 720p for the new segment, default 720p, and the per-second rate follows this choice. |
duration_seconds | No | Length of the new segment in whole seconds, 4 to 30, default 5. Only these seconds are billed; the source footage is placed in front of them in the joined file at no charge. |
generate_audio | No | On by default: Flash creates sound for the new segment from the prompt and the picture, and it is crossfaded into your clip's soundtrack at the join. Default: |
watermark | No | Off by default. Turn it on to have the model put its visible AI-generated mark on the new segment; the footage you supplied is joined unmarked, and the price does not change. Default: |
Pricing
Billed like a Flash image-to-video request for the new segment alone: each requested second at the rate of the resolution you pick. The source clip and the joining step cost nothing extra, sound, an end frame and the watermark leave the price unchanged, and an extension that fails is not charged.
| Specification | Price |
|---|---|
| $0.115 / second |
| $0.2392 / second |
Use cases
Trying a shot plan before a final render
Send a 4-second, 480p, 16:9 prompt that ends with an Audio: line, such as a rain-soaked night crosswalk. Our run returned 854×480 at 24 fps, 4.064 s long, with an AAC stereo track of rain and laughter. Change one phrase and rerun to see what moved.
Restyling footage you already shot
Upload a 4–30 second clip, describe the change, then list what must stay. A sunny street with two cyclists and a tram became a snowy evening in our test, and with generate_audio switched off the original soundtrack came back unchanged.
Character and product mockups
Attach a portrait and a product photo as @Image 1 and @Image 2 and ask for 9:16. Our two-image test returned 480×854 with the man lifting a glass dropper bottle toward the lens, so both references showed up. Use the result to judge the idea before building a polished version.
Looping a portrait animation
Give the same photo as image_url and last_image_url and describe the motion between them. Our potter portrait returned a 562×748 clip of 4.064 s whose opening and closing frames both matched the source pose.
Chaining one shot into the next
Set return_last_frame to true and the MP4 arrives with a JPEG of its closing frame (854×480 at 480p 16:9 in our test). Pass that JPEG as image_url of the next image-to-video request so the following shot begins where the last one stopped.
Prompt guide & pro tips
Choose the endpoint for your input
Use text-to-video for a prompt alone, image-to-video for a start frame, reference-to-video for images, clips or a voice, video-edit for an existing 4–30 second clip, and video-extend to add 4–30 seconds to a clip of up to 60 seconds. All five share the 480p/720p range and the
generate_audioswitch.Send the createTask request
POST to https://api.spicyapi.ai/api/v1/jobs/createTask with the header Authorization: Bearer YOUR_SPICY_API_KEY and the body {"model": "bytedance/seedance-2.5-flash/text-to-video", "input": {"prompt": "A lighthouse keeper climbs a spiral stair at dawn and wipes fog from the lamp glass. Audio: wind, boots on iron.", "
duration_seconds": 4, "resolution": "480p"}}.Poll for the finished clip
The response gives a taskId in state queued. Call GET /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID, or pass a callBackUrl, until the state is succeeded, then read the MP4 address from output.assets. Field details are in the task guide at docs.spicyapi.ai/docs/tasks.
Change one phrase, then move up
Compare variations at 480p and 4 seconds, altering a single phrase per run. When a take works, rerun it at 720p and your target length, or send the same brief to Seedance 2.5 for 1080p.
Seedance 2.5 Flash video extend in one call
Seedance 2.5 Flash video extend adds new footage to a clip you already have. SpicyAPI lifts the final frame of video_url, hands it to Flash image to video as the opening picture together with your prompt, and joins the 4 to 30 second result onto the end of your footage. You get one MP4 that plays straight through, plus the new segment as its own file, at 480p or 720p with generated sound.
Request example
POST https://api.spicyapi.ai/api/v1/jobs/createTask with Authorization: Bearer YOUR_SPICY_API_KEY. Five more seconds for a six-second clip:
{
"model": "bytedance/seedance-2.5-flash/video-extend",
"input": {
"video_url": "https://example.com/cyclist.mp4",
"prompt": "The cyclist rests one foot on the curb, the light turns green, and she pushes off out of frame to the left while the camera holds still. Audio: idling traffic, a short bell ring.",
"duration_seconds": 5,
"resolution": "720p"
}
}
Response example
{"code": 200, "msg": "success", "data": {"taskId": "task_abc123", "state": "queued"}}
Poll GET /api/v1/jobs/recordInfo?taskId=task_abc123 or pass callBackUrl. output.assets lists the joined clip (video) first and the new part (segment) second; real durations carry fractions:
{"code": 200, "msg": "success", "data": {"taskId": "task_abc123", "state": "succeeded", "output": {"assets": [{"url": "https://example.com/joined.mp4", "role": "video", "durationSeconds": 11.0}, {"url": "https://example.com/segment.mp4", "role": "segment", "durationSeconds": 5.0}]}}}
Parameters
| Parameter | Values | Default |
|---|---|---|
video_url | MP4, MOV or WebM, up to 60 s | Required |
prompt | What happens after the last frame | Required |
duration_seconds | 4 to 30, new segment | 5 |
resolution | 480p, 720p | 720p |
generate_audio | true, false | true |
last_image_url | Picture the new segment ends on | Optional |
watermark | Model mark on the new segment | false |
The new segment takes the shape of your clip's last frame, and the joined file is always an MP4.
How billing works
The new segment costs the same as a Flash image to video request: each requested second at the rate of your resolution. The source clip and the joining step are free, and audio, an end frame or the watermark do not change the price. A failed continuation or join is refunded in full.
Tips for good results
- End the source on a clear, steady frame. Blur, a cut or a fade in the last frame carries into the new segment, so trim to a clean moment.
- Describe what comes next, not the scene. The frame already fixes who is there and how it is lit.
- Restate motion that must continue. A still holds no speed, so write "keeps walking left at the same pace".
- Plan the sound. Close with an
Audio:line that suits the source's room tone, or turngenerate_audiooff and score later.
Limits and errors
- Output is 480p or 720p; a 1080p source is accepted, but the new part looks softer on its canvas.
- One frame carries nothing that is out of view, nor camera momentum or the beat of the soundtrack, and light can shift at the seam, so check the join.
- Sources over 60 seconds or 3840 pixels on the long edge, or unreadable files, are refused without charge.
- Use the full endpoint name: a family-level call with
video_urlcomes here only if it also setsduration_seconds,last_image_urlorwatermark, and otherwise runs a video edit. - Extend only footage you own or may use, and never a real person's video without their consent.
When to use the flagship's extend instead
Seedance 2.5 video extend renders up to 1080p and reads up to the last 30 seconds of your clip instead of one frame, which helps a movement or a voice keep going; those reference seconds are billed too.
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: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seedance-2.5-flash/video-extend",
"input": {
"duration_seconds": 5,
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"resolution": "720p",
"video_url": "https://example.com/reference.mp4"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.










