# Seedance 2.5

> ByteDance's flagship multimodal video model with native audio, native 30-second single-pass generation, and large multimodal reference sets (up to 30 images, 10 videos, 10 audios). Supports text-to-video, image-to-video, first/last-frame control, and lip-sync. Served directly from BytePlus ModelArk.

- **Provider**: byteplus
- **Model ID**: bytedance/seedance-2.5
- **Category**: video_generation
- **Credits**: 5500 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `generate_audio` (boolean, optional): Generate synchronized audio with the video, including dialogue (use double quotes in prompt), sound effects, and background music. (Default: `True`)
- `resolution` (string, optional): Video resolution. 1080p is supported by BytePlus since 2026-08-17 and billed at a higher per-second rate. (Default: `720p`; Options: `480p`, `720p`, `1080p`)
- `prompt` (string, optional): Text prompt for video generation. Maximum 20000 characters (BytePlus states no hard cap and recommends no more than 1,000 English words / 500 Chinese characters for best results — longer prompts scatter the model's attention and details get dropped). Optional when a media input (image, reference images/videos/audios) is supplied.
- `last_frame_image` (string, optional): Last-frame image. Requires a first-frame image. Cannot be combined with reference images, videos, or audios. Each image must be at least 300px wide and 300px tall — BytePlus rejects smaller images (InvalidParameter) before generation starts.
- `watermark` (boolean, optional): Add a watermark to the generated video. (Default: `False`)
- `aspect_ratio` (string, optional): Video aspect ratio. 'adaptive' (upstream default) lets the model choose the best ratio based on inputs. First/last-frame, editing, and extension modes require 'adaptive'. (Default: `adaptive`; Options: `adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `21:9`)
- `seed` (integer, optional): Random seed. Set for reproducible generation. Reproducibility is not guaranteed.
- `reference_audios` (array, optional): Reference audio files (up to 10, each 2-30s, combined duration max 30s) for audio-driven generation and lip-sync. Requires at least one reference image or video. Reference them in your prompt as [Audio1], [Audio2], etc. (Default: `[]`)
- `output_format` (string, optional): Output video container format. (Default: `mp4`; Options: `mp4`, `mov`)
- `reference_images` (array, optional): Reference images (up to 30) for character consistency, style guidance, and scene composition. Cannot be combined with first/last frame images. Reference them in your prompt as [Image1], [Image2], etc. Each image must be at least 300px wide and 300px tall — BytePlus rejects smaller images (InvalidParameter) before generation starts. (Default: `[]`)
- `duration` (integer, **required**): Video duration in seconds (4-30). Required: upstream also accepts -1 for intelligent duration, but the resulting length is unknown at request time and cannot be billed accurately, so this gateway requires an explicit duration. (Default: `5`; Range: min: 4, max: 30)
- `image` (string, optional): First-frame image for image-to-video or first/last-frame generation. Cannot be combined with reference images, videos, or audios. Each image must be at least 300px wide and 300px tall — BytePlus rejects smaller images (InvalidParameter) before generation starts.
- `reference_videos` (array, optional): Reference videos (up to 10, each 2-30s, combined duration max 30s) for motion transfer, style reference, editing, and extension. Reference them in your prompt as [Video1], [Video2], etc. Supplying any reference video switches billing to the higher video_in rate. (Default: `[]`)

## Example Request

```json
{
  "model": "bytedance/seedance-2.5",
  "input": {
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "seed": 42,
    "prompt": "a golden retriever puppy running across a green meadow toward the camera, slow motion, warm afternoon light",
    "resolution": "720p"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

bytedance, seedance, video-generation, text-to-video, image-to-video, multimodal-reference, native-audio, lip-sync

## Documentation

https://docs.byteplus.com/en/docs/ModelArk/2607688