Seedance 2.5

Seedance 2.5

Use Seedance 2.5 to create videos with text and optional image, video, and audio references through the SJinn REST API

Tool Overview

Seedance 2.5 creates videos from a text prompt and optional image, video, and audio references. It supports durations from 4 to 30 seconds and output at 480P Draft, 480P, 720P, or 1080P. A completed 480p-draft can be upscaled to 1080P within 7 days.

Tool Identifier

seedance25-video-api

Parameters

Required Parameters

prompt

  • Type: string
  • Description: Text description of the video to generate. Use the referenced media in the order provided by the URL arrays.

Optional Parameters

duration

  • Type: number
  • Default: 5
  • Range: 4–30 seconds

ratio

  • Type: string
  • Default: "16:9"
  • Supported Values: "adaptive", "16:9", "9:16", "1:1", "3:4", "4:3", "21:9"

resolution

  • Type: string
  • Default: "480p"
  • Supported Values: "480p", "480p-draft", "720p", "1080p"

image_urls

  • Type: string[]
  • Default: []
  • Limit: Up to 30 public HTTP/HTTPS URLs

video_urls

  • Type: string[]
  • Default: []
  • Limit: Up to 10 public HTTP/HTTPS URLs

audio_urls

  • Type: string[]
  • Default: []
  • Limit: Up to 10 public HTTP/HTTPS URLs

Pricing

  • 480P: 170 credits per second
  • 480P Draft: 170 credits per second
  • 720P: 350 credits per second
  • 1080P: 850 credits per second

The total is duration × resolution rate, rounded up to the nearest credit.

Draft creation and upscaling are separate paid tasks. Upscaling costs an additional 850 credits per saved draft second.

Request Examples

Draft Then Upscale

Create a draft with tool_type: "seedance25-video-api" and input.resolution: "480p-draft". Once Query Task Status reports status: 1, submit the returned SJinn task_id:

{
  "tool_type": "seedance25-upscale-api",
  "input": {
    "draft_task_id": "YOUR_COMPLETED_DRAFT_TASK_ID"
  }
}

The upscale request returns a new task ID for polling. It inherits the draft's prompt, references, duration, and aspect ratio; see Seedance 2.5 Upscale for requirements and pricing.

Prompt Only

curl -X POST https://sjinn.ai/api/un-api/create_tool_task \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_type": "seedance25-video-api",
    "input": {
      "prompt": "A cinematic tracking shot through a neon-lit night market",
      "duration": 5,
      "ratio": "16:9",
      "resolution": "480p"
    }
  }'

Multimodal References

curl -X POST https://sjinn.ai/api/un-api/create_tool_task \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_type": "seedance25-video-api",
    "input": {
      "prompt": "Keep the character from the image, follow the camera motion in the video, and use the audio as the soundtrack reference.",
      "duration": 10,
      "ratio": "9:16",
      "resolution": "720p",
      "image_urls": [
        "https://example.com/character.jpg"
      ],
      "video_urls": [
        "https://example.com/camera-motion.mp4"
      ],
      "audio_urls": [
        "https://example.com/soundtrack.mp3"
      ]
    }
  }'

JavaScript

const response = await fetch('https://sjinn.ai/api/un-api/create_tool_task', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    tool_type: 'seedance25-video-api',
    input: {
      prompt: 'A dancer performs under warm theatrical lighting',
      duration: 8,
      ratio: '9:16',
      resolution: '1080p',
      audio_urls: ['https://example.com/music.mp3'],
    },
  }),
});

const result = await response.json();
console.log('Task ID:', result.data.task_id);

Python

import requests

response = requests.post(
    'https://sjinn.ai/api/un-api/create_tool_task',
    headers={
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json',
    },
    json={
        'tool_type': 'seedance25-video-api',
        'input': {
            'prompt': 'A dancer performs under warm theatrical lighting',
            'duration': 8,
            'ratio': '9:16',
            'resolution': '1080p',
            'audio_urls': ['https://example.com/music.mp3'],
        },
    },
)

result = response.json()
print('Task ID:', result['data']['task_id'])

Response

The create endpoint returns a pending task ID. Poll query_tool_task_status until the task completes or fails.

{
  "success": true,
  "errorMsg": "",
  "error_code": 0,
  "data": {
    "task_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

Related Links