Video model · ByteDance
Seedance 2.5 Flash API
Seedance 2.5 Flash is the speed-focused tier of ByteDance's Seedance 2.5 video model, served on TokenRa under the ID seedance-2.5-flash. It takes text and reference images and returns a video with audio, and it uses the same request format as Seedance 2.5 Pro, with 480p added as a cheaper output size.
- Model ID
seedance-2.5-flash- Input
- Text, reference images
- Output
- 480p or 720p video
- Mode
- Async task
- Price
- $6.522 / 1M tokens
- For AI agents
- llms.txt guide
Capabilities
Capabilities & endpoints
Video generation is asynchronous: create a task, then poll it. The body is the one Seedance 2.5 Pro accepts, so moving between the two tiers is a change to the model field only. A Flash task run on 2026-11-16 finished in about two minutes; a 4–5 second 720p clip on 2.5 Pro took about five.
task_id immediately.data.result_url when data.status is SUCCESS.The rate is flat: $6.522 per 1M video tokens at both 480p and 720p. The token count grows with resolution and duration, so a 720p clip still costs more than the same clip at 480p. See the model page for the pricing detail.
Modes
Generation modes
A. Text to video
Output settings sit at the top level of the request. This example asks for 480p, the size only the Flash tier accepts.
{
"model": "seedance-2.5-flash",
"prompt": "A paper boat drifting down a rainy neon street at night, cinematic close-up",
"resolution": "480p",
"ratio": "9:16",
"duration": 4,
"generate_audio": false
}B. Reference images
Image URLs in images are passed to the model as reference images, usually to pin a character, product or packaging look. Send the settings you care about explicitly rather than relying on defaults.
{
"model": "seedance-2.5-flash",
"prompt": "The logo card slowly zooms in while a soft light sweeps across it",
"images": ["https://example.com/logo-card.png"],
"resolution": "720p"
}Request
Request parameters
resolution, ratio, duration and generate_audio from the top level of the request. This is the opposite of Seedance 2.0, which reads them from metadata.| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | seedance-2.5-flash |
prompt | string | Yes | Describe the scene, the motion and the camera. Optional when content contains a text item. |
resolution | string | Yes | 480p or 720p, at the top level. A missing value is rejected. Within the Seedance 2.5 family only Flash offers 480p; for 1080p output use Seedance 2.5 Pro. Also decides how many tokens a task uses. |
ratio | string | No | Aspect ratio such as 16:9 or 9:16. |
duration | integer | No | Length in seconds. Default 5. |
generate_audio | boolean | No | Generate a soundtrack. On by default; false returns a silent video. |
images | string[] | No | Reference image URLs, see mode B. |
content | array | No | Text and image items in the same shape as Seedance 2.5 Pro. Replaces prompt and images. |
metadatais ignored. A request that putresolutiononly inmetadatawas rejected withinvalid_resolution.- Video and audio references are not available:
video_urlandaudio_urlitems fail withunsupported content type. - Only the fields in the table are sent to the model. Others, such as
seed,watermark,return_last_frameorcallback_url, are dropped without an error.
Response
Response format
Create response
{
"id": "task_RxuCqxISrGGv04KFM4xStexL4PW60sCC",
"task_id": "task_RxuCqxISrGGv04KFM4xStexL4PW60sCC",
"object": "video",
"model": "seedance-2.5-flash",
"status": "queued",
"progress": 0,
"created_at": 1794831017
}Query response
{
"code": "success",
"message": "",
"data": {
"task_id": "task_RxuCqxISrGGv04KFM4xStexL4PW60sCC",
"action": "generate",
"status": "SUCCESS",
"fail_reason": "",
"result_url": "https://example.com/output.mp4",
"submit_time": 1794831017,
"start_time": 1794831028,
"finish_time": 1794831147,
"progress": "100%",
"data": {
"id": "cgt-20261116201017-upxtp",
"object": "video.generation",
"status": "completed",
"data": [{"url": "https://example.com/output.mp4"}],
"usage": {"total_tokens": 108900, "completion_tokens": 108900}
}
}
}data.data holds the raw upstream task. It does not repeat the resolution, ratio or duration; usage.total_tokens is the billed video token count. The task above reported 108,900 tokens.
| data.status | Meaning |
|---|---|
NOT_START / SUBMITTED / QUEUED | Accepted, waiting to start. |
IN_PROGRESS | Generating. |
SUCCESS | Done. Download result_url. |
FAILURE | Failed. The reason is in fail_reason; the pre-charged amount is refunded. |
Errors
Errors & limits
Errors from this model
| HTTP | code | Message | Cause |
|---|---|---|---|
400 | invalid_resolution | resolution must be 480p, 720p or 1080p | resolution missing, not one of the listed values, or only inside metadata. |
400 | invalid_request | prompt is required | No prompt and no text item in content. |
500 | build_request_failed | unsupported content type: video_url | A content item other than text or image_url. |
Common errors
| HTTP | error.code | Meaning | What to do |
|---|---|---|---|
401 | — | Missing, wrong or deleted API key. The message is Invalid token. | Check the Authorization: Bearer header and the key in the console. |
400 | — | The body is not valid JSON. | Fix the JSON and send Content-Type: application/json. |
500 | invalid_request | A required field is missing, for example messages. | Add the field named in the message. Retrying will not help. |
403 | insufficient_user_quota | Your balance or plan quota is used up. | Top up in the console, then retry. |
503 | model_not_found | Unknown model ID, or no channel serves it for your group. | Check the ID in the model list or with GET /v1/models. |
429 | — | Too many requests. | Back off exponentially and retry. |
5xx | — | The upstream provider failed or timed out. | Retry a few times; keep the request id if it persists. |
Limits and notes
- Poll every 10–15 seconds. A 2.5 Flash task run on 2026-11-16 finished in about two minutes; actual time depends on queueing and resolution.
result_urlis a temporary link. Download and store the video yourself.- Pricing is flat at $6.522 per 1M video tokens for 480p and 720p alike, settled against
usage.total_tokens. For 1080p output use Seedance 2.5 Pro (artsdance-2-5-pro-260801). See the live rate in the Model Square.