bytedance/seedance-2.0-fast

KindRouter Docs

General Description

Header Parameters

For every request endpoint, the following information must be included in the request header.

Parameter	Type	Required	Example value
Authorization	string	Yes	Bearer <token>
Content-Type	string	Yes	application/json

To get your <token>:
1. Log in from the homepage.
2. Click on "Profile" in the upper-right corner.
3. Your <token> will be displayed there.

Submitting a Video Generation Request

Credit consumption

Resolution	Credit consumption / Duration (seconds)
720p	5

If the Credit consumption / Duration (seconds) is 6, and your video duration is 5 seconds, the total credits consumed will be 6 × 5 = 30 .

Based on a rate of $15 per 1,000 credits, this would cost $0.45, which is approximately $0.09 per second.

EndPoint

https://kindrouter.com/api/v1/videos

Request Method

POST

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	The model to use for video generation (e.g., bytedance/seedance-2.0-fast)
prompt	string	Yes	Text description of the video to generate
duration	integer	Yes	Duration of the generated video in seconds, 4-15
resolution	string	Yes	Resolution of the output video (e.g., 720p)
aspect_ratio	string	Yes	Aspect ratio of the output video (e.g., 16:9, 9:16)
frame_images	array	No	Images for first/last frames (image-to-video)
input_references	array	No	Reference images for style guidance (reference-to-video)
callback_url	string	No	URL to receive a webhook notification when the job completes. Overrides the workspace-level default callback URL if set. Must be HTTPS

Using Images

There are two ways to provide images, each triggering a different generation mode:

frame_images: Specifies first or last frame images for image-to-video generation. Each entry must include a frame_type of first_frame or last_frame.

input_references: Provides style or content reference images for reference-to-video generation. The model uses these as visual guidance rather than exact frames.

If both fields are provided, frame_images takes precedence and the request is treated as image-to-video.

Image-to-Video (frame_images)

{
  "model": "bytedance/seedance-2.0-fast",
  "prompt": "A character walking through a forest",
  "frame_images": [
      {
      "type": "image_url",
      "image_url": {
          "url": "https://example.com/first-frame.png"
      },
      "frame_type": "first_frame"
      }
  ],
  "resolution": "1080p"
}

Reference-to-Video (input_references)

{
  "model": "bytedance/seedance-2.0-fast",
  "prompt": "A colossal solar flare beside a planet",
  "input_references": [
      {
          "type": "image_url",
          "image_url": {
              "url": "https://example.com/style-ref.png"
          }
      }
  ],
  "resolution": "1080p"
}

Response Format

{
    "id": "abc123",
    "polling_url": "https://openrouter.ai/api/v1/videos/abc123",
    "status": "pending"
}

Job Statuses

Status Description pending The job has been submitted and is queued in_progress The video is being generated completed The video is ready to download failed The generation failed (check the error field)

Poll Response

EndPoint

https://kindrouter.com/api/v1/videos/{id}

Request Method

GET