Seedance 2.0 Fast

Seedance 2.0 Fast is the faster, more affordable variant of Seedance 2.0. It supports the same multi-modal capabilities — text, image, video, and audio references as input.

Model

Pricing

Formula-based billing with different rates depending on whether video references are used.

• Without video: output_duration × per_second
• With video: (input_video_duration + output_duration) × per_second

When using video references, input video duration is automatically detected. The total billable duration = input video duration + output video duration.

Examples:

• 720p, 5s, text-only: 33 × 5 = 165 credits ($0.825)
• 720p, 10s output, 5s input video: 20 × (5 + 10) = 300 credits ($1.50)
• 480p, 5s, text-only: 16 × 5 = 80 credits ($0.40)
• 480p, 15s output, 5s input video: 10 × (5 + 15) = 200 credits ($1.00)

Create Task

POST https://api.aivideoapi.ai/v1/videos/generations

Request Body

Input Object

Generation Type

Image URLs Format

image_urls supports both string array and object array format:

String array:

"image_urls": [
  "https://example.com/photo1.jpg",
  "https://example.com/photo2.jpg"
]

Object array:

"image_urls": [
  { "url": "https://example.com/photo1.jpg" },
  { "url": "https://example.com/photo2.jpg" }
]

About real person images: All images are automatically processed through our content moderation system. If an image contains celebrities, public figures, or other sensitive content, the task will fail and credits will be automatically refunded. Each image takes an additional 2-3 seconds to process.

Supported Input Combinations

• Text only
• Text (optional) + Image(s)
• Text (optional) + Video(s)
• Text (optional) + Image(s) + Audio
• Text (optional) + Image(s) + Video(s)
• Text (optional) + Video(s) + Audio
• Text (optional) + Image(s) + Video(s) + Audio

Audio cannot be used alone. It must be combined with at least one image or video.

Example: Text-to-Video

curl -X POST https://api.aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-fast",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "A drone shot flying over mountains at sunset, cinematic lighting",
      "duration": 5,
      "aspect_ratio": "16:9",
      "resolution": "480p",
      "generate_audio": true
    }
  }'

Example: Image + Video + Audio References

curl -X POST https://api.aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-fast",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "Use the person image as the main character, follow the camera movement in the videos, with audio as background music",
      "image_urls": [
        { "url": "https://example.com/person.jpg" },
        { "url": "https://example.com/background.jpg" }
      ],
      "video_urls": ["https://example.com/reference1.mp4", "https://example.com/reference2.mp4"],
      "audio_urls": ["https://example.com/bgm.mp3", "https://example.com/sfx.wav"],
      "duration": 5,
      "aspect_ratio": "16:9",
      "resolution": "480p"
    }
  }'

Example: First and Last Frames

Use generation_type: "first_and_last_frames" to control the start and end of the video. Provide 1 image (first frame only) or 2 images (first and last frame).

curl -X POST https://api.aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-fast",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "A person walks from the park to the city center",
      "generation_type": "first_and_last_frames",
      "image_urls": [
        { "url": "https://example.com/start-frame.jpg" },
        { "url": "https://example.com/end-frame.jpg" }
      ],
      "duration": 5,
      "aspect_ratio": "16:9",
      "resolution": "480p"
    }
  }'

In first_and_last_frames mode, video_urls and audio_urls are ignored. Pricing uses the "Without Video Reference" rate.

Example: Web Search Enabled

When web_search is enabled, the model can look up real-time information to enhance video generation.

curl -X POST https://api.aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-fast",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "Generate a short news clip about the latest SpaceX rocket launch",
      "duration": 5,
      "aspect_ratio": "16:9",
      "resolution": "480p",
      "web_search": true
    }
  }'

Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "cbf6b69d-4f03-4817-8ed7-94c0292184a8"
  }
}

Query Task

curl https://api.aivideoapi.ai/v1/tasks/{taskId} \
  -H "Authorization: Bearer sk-your-api-key"

Status transitions: pending -> processing -> completed or failed.

Processing

{
  "id": "e717a5ee-2ed4-47f4-8cc3-53394f1abb35",
  "status": "processing",
  "model": "doubao-seedance-2.0-fast",
  "created_at": 1774706165,
  "progress": null
}

Completed

{
  "id": "7d89c51e-9430-410e-909e-df347131ebaa",
  "status": "completed",
  "model": "doubao-seedance-2.0-fast",
  "created_at": 1774790227,
  "completed_at": 1774796529,
  "output": {
    "urls": [
      "/videos/2026/04/07/abc.mp4"
    ],
    "last_frame_url": "/images/2026/04/07/abc-last-frame.png",
    "metadata": {
      "seed": 41485,
      "ratio": "16:9",
      "duration": 5,
      "resolution": "480p",
      "generate_audio": true,
      "framespersecond": 24
    }
  }
}

last_frame_url is only present when return_last_frame: true was set in the request. See Last Frame. Video URLs expire in 24 hours. Download promptly after generation completes.

Failed

{
  "id": "57c8772c-f834-46f3-9b7d-81f92e104050",
  "status": "failed",
  "model": "doubao-seedance-2.0-fast",
  "created_at": 1774793758,
  "error": {
    "code": "upstream_error",
    "message": "The request failed because the input text may contain sensitive information. Request id: 0217747937596950e290995bd2535df6af5f05331d9ca5663eeee"
  }
}

When a task fails, pre-charged credits are automatically refunded.

Callback

Pass callback_url when creating the task. The system will automatically send a POST request to your URL when the task completes or fails.

On Task Completed

{
  "id": "7d89c51e-9430-410e-909e-df347131ebaa",
  "status": "completed",
  "model": "doubao-seedance-2.0-fast",
  "created_at": 1774790227,
  "completed_at": 1774796529,
  "output": {
    "urls": [
      "/videos/2026/04/07/abc.mp4"
    ],
    "last_frame_url": "/images/2026/04/07/abc-last-frame.png",
    "metadata": {
      "seed": 41485,
      "ratio": "16:9",
      "duration": 5,
      "resolution": "480p",
      "generate_audio": true,
      "framespersecond": 24
    }
  }
}

On Task Failed

{
  "id": "57c8772c-f834-46f3-9b7d-81f92e104050",
  "status": "failed",
  "model": "doubao-seedance-2.0-fast",
  "created_at": 1774793758,
  "error": {
    "code": "upstream_error",
    "message": "The request failed because the input text may contain sensitive information. Request id: 0217747937596950e290995bd2535df6af5f05331d9ca5663eeee"
  }
}

When a task fails, pre-charged credits are automatically refunded.

Parameters

Duration

Integer, unit: seconds. Default: 5.

• Range: 4-15
• Duration affects billing — see Pricing

Aspect Ratio

Default: adaptive.

Supported values: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive

When set to adaptive, the model auto-selects the best ratio based on the input:

• Text-to-video: intelligently chosen based on the prompt
• Image-to-video (first frame / first+last frame): matched to the uploaded image's aspect ratio
• Multi-modal reference: if the intent is first-frame / edit / extend, matched to that image or video; otherwise matched to the first media file (priority: video > image)

The actual ratio used is returned in the task response metadata.ratio field.

Seed

Integer. Default: -1.

• Range: integer in [-1, 4294967295]
• The actual seed used is returned in the task response metadata.seed field

Note

• For the same request, when the model receives different seed values — e.g., not specifying a seed, setting seed to -1 (which uses a random value), or manually changing the seed — it will produce different results.
• For the same request, when the model receives the same seed value, it will produce similar results, but they are not guaranteed to be identical.

Last Frame

Boolean. Default: false.

• true: Return the last frame image of the generated video. When set to true, the last frame image is available via the query task endpoint in the output.last_frame_url field. The image has the same width and height as the generated video, and contains no watermark.
• false: Do not return the last frame image.

This parameter enables generating multiple consecutive videos: use the last frame of the previous video as the first frame of the next video task to quickly produce a sequence of connected clips.

Input Requirements

Images

• Formats: JPEG, PNG, WebP, BMP, TIFF, GIF
• Aspect ratio (w/h): 0.4 ~ 2.5
• Dimensions: 300 ~ 6000 px per side
• Max size: 30 MB per image

Videos

• Formats: MP4, MOV
• Resolution: 480p, 720p
• Duration: 2-15s per video, up to 3 reference videos, total duration max 15s
• Aspect ratio (w/h): 0.4 ~ 2.5
• Dimensions: 300 ~ 6000 px per side
• Pixel count (w × h): 409,600 ~ 927,408 (e.g., 640×640=409,600 meets minimum; 834×1112=927,408 meets maximum)
• Max size: 50 MB per video
• FPS: 24 ~ 60

Audio

• Formats: WAV, MP3
• Duration: 2-15s per audio, total max 15s
• Max size: 15 MB per audio

Resolution Reference

480p

720p

ℹ️ Fast does not support 1080p. For 1080p output, use doubao-seedance-2.0.

Error Codes

When a request fails, the API returns a JSON error response:

{
  "error": {
    "code": "insufficient_credits",
    "message": "Your credit balance is too low. Please top up.",
    "type": "billing_error"
  }
}

Error Reference

Common Scenarios

invalid_request (400)

Returned when required fields are missing or invalid.

{
  "error": {
    "code": "invalid_request",
    "message": "'model' is required.",
    "type": "invalid_request_error"
  }
}

insufficient_credits (402)

Your balance is too low. Check your balance with GET /v1/credits and top up in Dashboard > Billing.

invalid_api_key (401)

Possible causes:

• The key does not start with sk-
• The key has been disabled or deleted
• The user account has been banned

upstream_error (503)

The upstream AI provider returned an error. This may happen when:

• The input contains sensitive or prohibited content
• The provider is temporarily unavailable
• The request parameters are not supported by the provider

Credits are automatically refunded when a task fails due to upstream errors.