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

# Seedance 2.0 Mini

> Generate a video with Seedance 2.0 Mini from text, from a first and/or last frame, or guided by references (up to 9 images, 3 videos, 3 audios). Up to 15 s.

Model id `seedance-2.0-mini` · ByteDance · video · 3 modes: `text-to-video`, `image-to-video`, `reference-to-video`.

> [!NOTE]
>
> This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls [`get_model`](https://docs.argil.ai/v2/mcp/tools) with the mode.

## Text To Video

Mode `text-to-video`. Text to video.

### Input

| Field | Type | Required | Allowed | Default | Description |
| - | - | - | - | - | - |
| `prompt` | string | Yes | up to 5,000 characters | | What the video should show: subject, action, camera and style. |
| `duration` | number or integer | | `-1`, or 4 to 15 | | Video duration in seconds. Integer 4-15, or -1 to let the model pick the length (billed on the length it picks); defaults to 5 when omitted. |
| `aspect_ratio` | string | | `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9` | | Aspect ratio. Defaults to 16:9. |
| `resolution` | string | | `480p`, `720p` | `720p` | Video resolution. 1080p needs the standard tier. |

### Pricing

\~3.66 credits per second at 720p (Seedance 2.0 Mini; rate varies by resolution; output + input-video seconds both billed).

Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded.

For the exact price of a request, use [`estimate_generation`](https://docs.argil.ai/v2/mcp/tools).

### Example

The arguments of [`generate_media`](https://docs.argil.ai/v2/mcp/tools#generate_media):

```json theme={null}
{
  "model": "seedance-2.0-mini",
  "mode": "text-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}
```

## Image To Video

Mode `image-to-video`. Animate a first frame, or go from a first to a last frame.

### Input

| Field | Type | Required | Allowed | Default | Description |
| - | - | - | - | - | - |
| `prompt` | string | Yes | up to 5,000 characters | | What the video should show: subject, action, camera and style. |
| `duration` | number or integer | | `-1`, or 4 to 15 | | Video duration in seconds. Integer 4-15, or -1 to let the model pick the length (billed on the length it picks); defaults to 5 when omitted. |
| `aspect_ratio` | string | | `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9` | | Aspect ratio. Defaults to 16:9. |
| `resolution` | string | | `480p`, `720p` | `720p` | Video resolution. 1080p needs the standard tier. |
| `first_frame` | [File](https://docs.argil.ai/v2/mcp/how-it-works.md#your-files) | | | | The image to use as the first frame of the video. |
| `last_frame` | [File](https://docs.argil.ai/v2/mcp/how-it-works.md#your-files) | | | | The image to use as the last frame. With a first frame, the video goes from one to the other. |

### Pricing

\~3.66 credits per second at 720p (Seedance 2.0 Mini; rate varies by resolution; output + input-video seconds both billed).

Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded.

For the exact price of a request, use [`estimate_generation`](https://docs.argil.ai/v2/mcp/tools).

### Example

The arguments of [`generate_media`](https://docs.argil.ai/v2/mcp/tools#generate_media):

```json theme={null}
{
  "model": "seedance-2.0-mini",
  "mode": "image-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}
```

## Reference To Video

Mode `reference-to-video`. A video guided by references: up to 9 images, 3 videos and 3 audios.

### Input

| Field | Type | Required | Allowed | Default | Description |
| - | - | - | - | - | - |
| `prompt` | string | Yes | up to 5,000 characters | | What the video should show: subject, action, camera and style. |
| `duration` | number or integer | | `-1`, or 4 to 15 | | Video duration in seconds. Integer 4-15, or -1 to let the model pick the length (billed on the length it picks); defaults to 5 when omitted. |
| `aspect_ratio` | string | | `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9` | | Aspect ratio. Defaults to 16:9. |
| `resolution` | string | | `480p`, `720p` | `720p` | Video resolution. 1080p needs the standard tier. |
| `references` | [File](https://docs.argil.ai/v2/mcp/how-it-works.md#your-files) list | | 0 to 15 items | | References the output must follow. The kind of each one (image, video, audio) is read from the file; per-kind limits are in the mode’s `capabilities.references`. |

**References:** up to 15: 9 images, 3 videos of 1.8 to 15.2 s (15 s in total), 3 audio files (15 s in total). Assets, URLs and elements are accepted.

### Pricing

\~3.66 credits per second at 720p (Seedance 2.0 Mini; rate varies by resolution; output + input-video seconds both billed).

Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded.

For the exact price of a request, use [`estimate_generation`](https://docs.argil.ai/v2/mcp/tools).

### Example

The arguments of [`generate_media`](https://docs.argil.ai/v2/mcp/tools#generate_media):

```json theme={null}
{
  "model": "seedance-2.0-mini",
  "mode": "reference-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera, keeping the look of the reference",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "references": [
      "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24"
    ]
  }
}
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.