Skip to main content
Access Notice Seedance 2.0 is not yet available to all users. Contact LaoZhang API support to request access: Telegram @laozhang_cn. Base URL: https://api.yelinai.comRequired endpoints: 2
  1. POST /v1/videos: create a video generation task
  2. GET /v1/videos/{task_id}: query task status and get the result URL
To download the video file, send a direct GET request to the video_url returned by the completed task.

​
API Flow

Seedance 2.0 video generation is an asynchronous task API. Create a task first, poll the task by id, then download the mp4 after the task returns video_url. 1 Create task Call POST /v1/videos with the model, prompt, video parameters, and optional reference assets. 2 Poll status Call GET /v1/videos/{task_id} and check status. 3 Download video When status=completed, read video_url from the response and download the mp4 file. Common status progression: 
submitted -> queued -> in_progress -> completed
Failed tasks usually return failed with an error field.

​
Models

ModelDescriptionRecommended use
doubao-seedance-2-0-fast-260128Seedance 2.0 fastFast generation, batch jobs, general video generation
doubao-seedance-2-0-260128Seedance 2.0 standardStandard-quality generation, video editing, workflows that need more stable output

​
Create Task

/v1/videos Create a Seedance 2.0 video generation task.

​
Headers

HeaderRequiredDescription
AuthorizationYesBearer $API_KEY
Content-TypeYesapplication/json

​
Request Parameters

ParameterTypeRequiredDescription
modelstringYesModel ID, for example doubao-seedance-2-0-fast-260128
promptstringYesVideo generation prompt. Text-only generation only requires model and prompt
contentarrayNoMultimodal content array for image, video, or audio references
ratiostringNoOutput aspect ratio, for example 16:9, 9:16, 1:1, 3:4, 4:3, or 21:9
durationintegerNoOutput duration. Use the 4-15 second range unless your account has different limits
watermarkbooleanNoWhether to add a watermark. false is common
generate_audiobooleanNoWhether to generate or keep audio

​
content Items

Use content to provide multimodal reference assets. Keep the top-level prompt, and for multimodal requests put the same text in the first content item for compatibility with the multimodal structure.
FieldTypeApplies toRequiredDescription
typestringallYestext, image_url, video_url, or audio_url
textstringtextYesPrompt text
image_url.urlstringimage_urlYesImage URL
video_url.urlstringvideo_urlYesVideo URL
audio_url.urlstringaudio_urlYesAudio URL
rolestringasset itemsRecommendedreference_image, reference_video, or reference_audio
Refer to assets by media type and order in the prompt:
ReferenceMeaning
image 1The first image_url item in content
image 2The second image_url item in content
video 1The first video_url item in content
audio 1The first audio_url item in content

​
Text-to-video Example

curl -X POST "https://api.yelinai.com/v1/videos" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  --data-raw '{
    "model": "doubao-seedance-2-0-fast-260128",
    "prompt": "First-person apple fruit tea ad, 8 seconds, fast-paced edit, show apple tea preparation and finished product, fresh bright style",
    "ratio": "16:9",
    "duration": 8,
    "watermark": false,
    "generate_audio": true
  }'

​
Multimodal Reference Example

curl -X POST "https://api.yelinai.com/v1/videos" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  --data-raw '{
    "model": "doubao-seedance-2-0-fast-260128",
    "prompt": "Use the first-person camera composition from video 1 throughout, and use audio 1 as background music. The first frame is image 1. Generate a first-person apple fruit tea ad and freeze the final frame as image 2.",
    "ratio": "16:9",
    "duration": 11,
    "watermark": false,
    "generate_audio": true,
    "content": [
      {
        "type": "text",
        "text": "Use the first-person camera composition from video 1 throughout, and use audio 1 as background music. The first frame is image 1. Generate a first-person apple fruit tea ad and freeze the final frame as image 2."
      },
      {
        "type": "image_url",
        "image_url": {
          "url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic1.jpg"
        },
        "role": "reference_image"
      },
      {
        "type": "image_url",
        "image_url": {
          "url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic2.jpg"
        },
        "role": "reference_image"
      },
      {
        "type": "video_url",
        "video_url": {
          "url": "https://ark-project.tos-cn-beijing.volces.com/doc_video/r2v_tea_video1.mp4"
        },
        "role": "reference_video"
      },
      {
        "type": "audio_url",
        "audio_url": {
          "url": "https://ark-project.tos-cn-beijing.volces.com/doc_audio/r2v_tea_audio1.mp3"
        },
        "role": "reference_audio"
      }
    ]
  }'

​
Create Response

{
  "id": "cgt-20260410125521-rpf27",
  "object": "video",
  "model": "doubao-seedance-2-0-fast-260128",
  "status": "submitted",
  "created_at": 1775796921
}
Response fields:
FieldTypeDescription
idstringTask ID used for status polling
objectstringObject type, usually video
modelstringModel used by the task
statusstringInitial status, commonly submitted or queued
created_atintegerCreation timestamp
billing_detailobjectOptional billing estimate or billing detail

​
Query Task

/v1/videos/{task_id} Query the status of a video generation task. 
curl "https://api.yelinai.com/v1/videos/cgt-20260410125521-rpf27" \
  -H "Authorization: Bearer $API_KEY"

​
Path Parameters

ParameterTypeRequiredDescription
task_idstringYesThe id returned by the create task response

​
Query Response

In progress: 
{
  "id": "cgt-20260410125521-rpf27",
  "object": "video",
  "model": "doubao-seedance-2-0-fast-260128",
  "status": "in_progress",
  "created_at": 1775796921,
  "updated_at": 1775796980
}
Completed: 
{
  "id": "cgt-20260410125521-rpf27",
  "object": "video",
  "model": "doubao-seedance-2-0-fast-260128",
  "status": "completed",
  "video_url": "https://example.com/generated-video.mp4",
  "created_at": 1775796921,
  "updated_at": 1775797043
}
Failed: 
{
  "id": "cgt-20260410125521-rpf27",
  "object": "video",
  "model": "doubao-seedance-2-0-fast-260128",
  "status": "failed",
  "error": {
    "message": "generation failed"
  }
}
Response fields:
FieldTypeDescription
idstringTask ID
objectstringObject type
modelstringModel used by the task
statusstringsubmitted, queued, in_progress, completed, failed, etc.
video_urlstringVideo URL returned after completion
urlstringSome responses may use this field for the video URL
created_atintegerCreation timestamp
updated_atintegerUpdate timestamp
errorobjectError details for failed tasks

​
Download Video

After the query response returns completed, read video_url and download it directly: 
curl -L "$VIDEO_URL" -o output.mp4
video_url is usually a temporary signed URL. Download it immediately or copy it to your own object storage.

​
Full Python Example

import os
import time
import requests

API_KEY = os.environ["API_KEY"]
BASE_URL = "https://api.yelinai.com/v1"

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
}

payload = {
    "model": "doubao-seedance-2-0-fast-260128",
    "prompt": "First-person apple fruit tea ad, 8 seconds, fast-paced edit, show apple tea preparation and finished product, fresh bright style",
    "ratio": "16:9",
    "duration": 8,
    "watermark": False,
    "generate_audio": True,
}

create_resp = requests.post(f"{BASE_URL}/videos", headers=headers, json=payload, timeout=60)
create_resp.raise_for_status()
task_id = create_resp.json()["id"]

while True:
    query_resp = requests.get(f"{BASE_URL}/videos/{task_id}", headers=headers, timeout=60)
    query_resp.raise_for_status()
    task = query_resp.json()
    status = task.get("status")

    if status == "completed":
        video_url = task.get("video_url") or task.get("url")
        video_resp = requests.get(video_url, timeout=120)
        video_resp.raise_for_status()
        with open(f"{task_id}.mp4", "wb") as f:
            f.write(video_resp.content)
        break

    if status == "failed":
        raise RuntimeError(task.get("error") or task)

    time.sleep(20)

​
Common Integration Questions

How many endpoints do I need to integrate? Two endpoints are required: POST /v1/videos to create a task and GET /v1/videos/{task_id} to query it. Download the final video by requesting the returned video_url. When do I need content? Text-to-video does not need content. Use the content array when you need image, video, or audio references, then refer to them in the prompt as image 1, video 1, or audio 1. Do I need both prompt and content[0].text? For text-to-video, top-level prompt is enough. For multimodal reference requests, keep top-level prompt and content[0].text the same for better compatibility with the multimodal structure. What should I check if no channel is available? Check whether the token group, billing mode, and model route are enabled. A correct model name does not guarantee that the current billing group has an available route.