> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Seedance 2.0 Video Models

> Choose between Seedance 2.0, Seedance 2.0 Fast, and Seedance 2.0 Mini for video generation.

Seedance 2.0 is a video model family for text-to-video, image-to-video, reference-to-video, video editing, and video extension workflows. Use product-level model IDs in `model`, then choose the workflow with `operation`.

## Model Choice

| Model               | Best for                            | Public resolutions            | Reference inputs                                                                                                         |
| ------------------- | ----------------------------------- | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| `seedance-2.0`      | Highest quality and 4K output       | `480p`, `720p`, `1080p`, `4k` | Up to 9 reference images plus up to 3 reference videos and 3 reference audios for `reference-to-video`                   |
| `seedance-2.0-fast` | Faster, lower-cost 480p/720p output | `480p`, `720p`                | Up to 9 reference images plus up to 3 reference videos and 3 reference audios for `reference-to-video`                   |
| `seedance-2.0-mini` | Lowest-cost 480p/720p output        | `480p`, `720p`                | Supports the Seedance 2.0 operation family; read the current model detail before relying on exact reference count limits |

`seedance-2.0-fast` and `seedance-2.0-mini` are fail-closed to `480p` / `720p`; do not send `1080p` or `4k` to those models.

## Supported Operations

The public Seedance 2.0 family supports:

| Operation            | Typical inputs                                                             |
| -------------------- | -------------------------------------------------------------------------- |
| `text-to-video`      | `prompt`                                                                   |
| `image-to-video`     | `prompt`, `image_url` or compatible image input                            |
| `start-end-to-video` | `prompt`, `start_image`, `end_image`                                       |
| `reference-to-video` | `prompt`, `reference_images`, optional `video_urls`, optional `audio_urls` |
| `video-to-video`     | `prompt`, `video_url` or compatible video input                            |
| `video-extension`    | `task_id` or model-specific continuation input                             |

Pure audio-only and text-plus-audio-only Seedance requests are not part of the public contract. Use audio as a reference input only in supported `reference-to-video` flows.

## 4K Reference-To-Video

Use `seedance-2.0` when you need 4K output. The base model supports `4k` across the governed public contract, including `reference-to-video`.

```bash theme={null}
curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "operation": "reference-to-video",
    "prompt": "Keep the same product identity and lighting while creating a slow cinematic rotation.",
    "reference_images": [
      "https://example.com/product-front.jpg",
      "https://example.com/product-side.jpg"
    ],
    "video_urls": ["https://example.com/motion-reference.mp4"],
    "duration": 6,
    "resolution": "4k",
    "aspect_ratio": "16:9"
  }'
```

## Fast And Mini Requests

Use `seedance-2.0-fast` when latency matters, and `seedance-2.0-mini` when the lowest cost tier is more important than maximum quality.

```bash theme={null}
curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-fast",
    "operation": "text-to-video",
    "prompt": "A clean product reveal on a white studio background, gentle camera push-in.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'
```

## Pricing And Billing

Seedance 2.0 pricing is token-based and depends on output resolution and whether the request includes video input. TokenLab's USD price truth for these models is converted from official CNY pricing using `6.8` CNY per USD.

Use the [Pricing API](/api-reference/pricing/get-pricing) or [Models API](/api-reference/models/list-models) for the current billable price before hard-coding product UI.

## Async Results

Video generation is asynchronous. Follow the `poll_url` returned by the create request, or use `GET /v1/tasks/{id}` with the returned task ID.

See [Create Video](/api-reference/video/create-video), [Get Task Status](/api-reference/tasks/get-task-status), and [Cancel Task](/api-reference/tasks/cancel-task) for endpoint details.