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

# Video models and pricing

> Seedance models, durations, resolutions, costs and file retention.

These tables describe model limits. For the inputs and controls exposed by each format, see its creation endpoint: [Ark / Seedance](/en/api/video-ark), [OpenAI video](/en/api/video-openai), [Gemini API](/en/api/video-gemini), [Vertex AI](/en/api/video-vertex) or [Jimeng compatible](/en/api/video-jimeng).

## Models

| Model | Resolutions | Duration (s) | Audio | Web search |
| - | - | - | - | - |
| `doubao-seedance-2-5-260628` | `480p`, `720p`, `1080p` | 4 to 30 | yes | yes |
| `doubao-seedance-2-0-260128-libtv` | `480p`, `720p`, `1080p`, `4k` | 4 to 15 | yes | yes |
| `doubao-seedance-2-0-fast-260128` | `480p`, `720p` | 4 to 15 | yes | yes |
| `doubao-seedance-2-0-mini-260615` | `480p`, `720p` | 4 to 15 | yes | yes |

Every output is an MP4 at 24 fps with no watermark. Ark / Seedance defaults are `720p`, 5 seconds, `adaptive` ratio and audio on. Other formats use the defaults in their respective sections.

Aspect ratios: `adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `21:9`. `adaptive` lets the model follow the prompt or the input image.

| Resolution | 16:9 | 4:3 | 1:1 | 3:4 | 9:16 | 21:9 |
| - | - | - | - | - | - | - |
| 480p | 854x480 | 752x560 | 640x640 | 560x752 | 480x854 | 992x432 |
| 720p | 1280x720 | 1112x834 | 960x960 | 834x1112 | 720x1280 | 1470x630 |
| 1080p | 1920x1080 | 1664x1248 | 1440x1440 | 1248x1664 | 1080x1920 | 2206x946 |
| 4k | 3840x2160 | 3326x2494 | 2880x2880 | 2494x3326 | 2160x3840 | 4398x1886 |

Seedance 2.0 models output 864x496 and 496x864 at 480p for `16:9` and `9:16`.

## Pricing

A task reserves quota at creation and settles against the delivered video. Only successful tasks are charged.

```text theme={"system"}
tokens = ceil((output_frames + input_video_seconds × 24) × width × height / 1024)
cost   = tokens / 1,000,000 × rate × group ratio
```

`output_frames` is the delivered frame count (24 per second), `width` and `height` the delivered pixel size, and `input_video_seconds` the total length of reference videos. Ark task reads return billed usage as `usage.completion_tokens`. For other formats, check costs in the [usage log](https://api.aiohub.org/console/log).

Rates in USD per million tokens:

| Model | 480p / 720p | 480p / 720p with video input | 1080p | 1080p with video input | 4k | 4k with video input |
| - | - | - | - | - | - | - |
| `doubao-seedance-2-5-260628` | 10.70 | 6.40 | 11.70 | 7.00 | | |
| `doubao-seedance-2-0-260128-libtv` | 7.00 | 4.30 | 7.70 | 4.70 | 4.00 | 2.40 |
| `doubao-seedance-2-0-fast-260128` | 5.60 | 3.30 | | | | |
| `doubao-seedance-2-0-mini-260615` | 3.50 | 2.10 | | | | |

The `seedance` group ratio is shown on the [console pricing page](https://api.aiohub.org/pricing). Example: a 4 second 1280x720 Seedance 2.5 clip is 97 frames and 87,300 tokens, USD 0.93 at list rate before the group ratio.

<Note>Rates change when the model provider changes its prices. The console price at call time and the [usage log](https://api.aiohub.org/console/log) are authoritative.</Note>

## File and task retention

Successful video files remain available for 72 hours, after which downloads return 410. Task records remain available for 7 days. Download URLs require an API key; copy the file to your own storage before it expires. Retention does not change with the API format.


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