Seedance 2.5 Flash API
Seedance 2.5 Flash is the faster edition of ByteDance's Seedance 2.5 video model, generating 480p and 720p video from text, images, reference videos and audio. Use this APIMart workspace to prepare a seedance-2.5-flash request, then review the Seedance 2.5 Flash API example and parameters below.
Seedance 2.5 Flash API workspace
- 480p or 720p, 4–30 seconds or Auto
- Up to 10 images, 5 videos and 5 audio clips
- Task types, audio, MP4/MOV and last frame
Leave it unset or choose auto to let the model decide. reference uses your references; edit and extend need at least one reference video.
Up to 10 images, 5 videos and 5 audio clips per request. Enter public http(s) URLs or asset:// IDs.
Your video will appear here
Seedance 2.5 Flash API: Faster 480p and 720p Video Generation
The Seedance 2.5 Flash model is built for speed. Prepare a request for 480p or 720p output: describe the shot, choose a task type, and add images, reference videos or audio. Review it as a form or as JSON before you call the API.
Seedance 2.5 Flash API Example: Text to Video and Image to Video
The Seedance 2.5 Flash API examples use APIMart's common asynchronous task format: submit a task, then query it with the returned task ID.
- 1
Authenticate Seedance 2.5 Flash API Requests
Save your APIMart API key as APIMART_API_KEY. The Seedance 2.5 Flash API examples send Authorization: Bearer <key> for submission and task queries.
- 2
Submit a seedance-2.5-flash Task
POST /v1/videos/generations with model set to seedance-2.5-flash, your prompt, size, resolution and duration. Add image_urls, video_urls or audio_urls for references. Read the task ID from data[0].task_id.
- 3
Get the Seedance 2.5 Flash Result
Use GET /v1/tasks/{task_id}. For a completed task, read data.result.videos[0].url[0]; for a failed task, read data.error.message.
See the APIMart documentation for APIMart authentication and general API usage.
curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.5-flash",
"prompt": "A cyclist rides along a coastal road at sunrise, the camera tracking alongside as waves catch the warm light",
"size": "16:9",
"resolution": "720p",
"duration": 10
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "seedance-2.5-flash",
"prompt": "A cyclist rides along a coastal road at sunrise, the camera tracking alongside as waves catch the warm light",
"size": "16:9",
"resolution": "720p",
"duration": 10
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["videos"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(10)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.5-flash",
"prompt": "The product from the reference image turns slowly on a white studio turntable under soft light as the camera pushes in to the label",
"image_urls": [
"https://example.com/product.jpg"
],
"size": "16:9",
"resolution": "720p",
"duration": 10
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"Seedance 2.5 Flash API Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: seedance-2.5-flash | The model value in this Seedance 2.5 Flash workspace and its examples: seedance-2.5-flash. |
prompt | string | Required | Default: — | Video description. Refer to inputs by index, such as @图片1, @视频1 or @音频1, in array order. |
resolution | string | Optional | Default: 720p | 480p or 720p. Seedance 2.5 Flash does not offer 1080p. |
size | string | Optional | Default: adaptive | Aspect ratio (also accepted as aspect_ratio): 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 or adaptive. Edit, extend and frame-only tasks require adaptive. |
duration | integer | Optional | Default: 5 | Clip length: 4–30 seconds, or -1 to let the model choose. Edit tasks follow the source video and use -1. |
generate_audio | boolean | Optional | Default: true | Generate audio together with the video (also accepted as audio). Set false for a silent video. |
image_urls | array | Optional | Default: — | Reference images as http(s) URLs or asset:// IDs. Images count toward the limit of 10 per request. Cannot be combined with image_with_roles. |
image_with_roles | array | Optional | Default: — | Images with a role: first_frame, last_frame or reference_image. A last frame needs a first frame; all roles count toward the 10-image limit. |
video_urls | array | Optional | Default: — | Up to 5 reference videos as http(s) URLs or asset:// IDs. Edit and extend tasks need at least one. |
audio_urls | array | Optional | Default: — | Up to 5 reference audio clips as http(s) URLs or asset:// IDs. |
omni_reference_task_type | string | Optional | Default: — | auto, reference, edit or extend. Leave it unset or use auto to let the model decide. |
output_format | string | Optional | Default: mp4 | mp4 or mov. |
return_last_frame | boolean | Optional | Default: false | Also return the last frame of the video as an image. |
seed | integer | Optional | Default: — | Random seed. The same seed gives similar, not identical, results. |
watermark | boolean | Optional | Default: false | Add an AI-generated watermark. |
tools | array | Optional | Default: — | Optional tools, such as [{"type": "web_search"}] to reference web information. |
nsfw_check | boolean | Optional | Default: false | APIMart field: moderate the prompt and input images before the task is submitted. |
