API docs · Models & billing
Model capabilities
Modes, resolutions, durations, aspect ratios and input limits.
The tables below are rendered live from GET /portal/public/models and use the same capability definitions the API validates parameters against. Call GET /v1/models with a key to list the models available to that key.
Seedance 2.0 Fast
seedance-2.0-fast- Modes
- Text to videoFirst frameFirst & last frameMultimodal reference
- Resolution
- 480p / 720p
- Duration
- 4–15 s, or chosen by the model
- Aspect ratio
- 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / Adaptive
- Frame rate
- 24 fps
- Inputs
- Up to 9 images, each ≤ 30.0 MBUp to 3 videos, ≤ 15 s in totalUp to 3 audio clips, alongside an image or video
- Prompt
- Up to 2000 characters
Seedance 2.0 Mini
seedance-2.0-mini- Modes
- Text to videoFirst frameFirst & last frameMultimodal reference
- Resolution
- 480p / 720p
- Duration
- 4–15 s, or chosen by the model
- Aspect ratio
- 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / Adaptive
- Frame rate
- 24 fps
- Inputs
- Up to 9 images, each ≤ 30.0 MBUp to 3 videos, ≤ 15 s in totalUp to 3 audio clips, alongside an image or video
- Prompt
- Up to 2000 characters
Seedance 2.0
seedance-2.0-standard- Modes
- Text to videoFirst frameFirst & last frameMultimodal reference
- Resolution
- 480p / 720p / 1080p
- Duration
- 4–15 s, or chosen by the model
- Aspect ratio
- 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / Adaptive
- Frame rate
- 24 fps
- Inputs
- Up to 9 images, each ≤ 30.0 MBUp to 3 videos, ≤ 15 s in totalUp to 3 audio clips, alongside an image or video
- Prompt
- Up to 2000 characters
Seedance 2.5
seedance-2.5- Modes
- Text to videoFirst frameFirst & last frameMultimodal reference
- Resolution
- 480p / 720p / 1080p
- Duration
- 4–30 s, or chosen by the model
- Aspect ratio
- 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / Adaptive
- Frame rate
- 24 fps
- Inputs
- Up to 30 images, each ≤ 30.0 MBUp to 10 videos, ≤ 30 s in totalUp to 10 audio clips
- Prompt
- Up to 4000 characters
Input roles
| role | Asset type | Description |
|---|---|---|
first_frame | Image | First-frame generation; combine with last_frame for first-and-last-frame generation. Cannot be combined with reference roles |
last_frame | Image | Last frame; requires first_frame |
reference_image | Image | Multimodal reference |
reference_video | Video | Multimodal reference; billed at the "with video input" rate |
reference_audio | Audio | Multimodal reference; where the capabilities require it, must be accompanied by a reference_image or reference_video (first and last frames do not count) |
Unsupported parameter combinations return 422 invalid_parameter with the offending field in param. The platform never rewrites parameters. Undefined top-level fields in the request body are ignored; put model-specific parameters in provider_options, where unknown keys return 422.
Reference image + reference audio
POST https://cn-api.aitoken.tools/v1/videos/generations
{
"model": "seedance-2.0-standard",
"prompt": "The subject looks into the camera and smiles, background blurred",
"inputs": [
{ "type": "image", "asset_id": "asset_xxx", "role": "reference_image" },
{ "type": "audio", "asset_id": "asset_yyy", "role": "reference_audio" }
],
"duration": 8,
"resolution": "1080p",
"ratio": "9:16",
"max_budget": "30.000000",
"callback_url": "https://example.com/hooks/video",
"metadata": { "order_id": "A-1001" }
}