Back to home
Dashboard

Seedance 2.0 Economy

Seedance 2.0 Economy engineered as a high-value supplementary pipeline for large-scale cost reduction, its transparent pricing model charges exclusively on output duration (in seconds), with zero fees for input videos. Whenever connected, it maintains exceptional motion stability and native audio synchronization. Due to tight compute availability dynamically fluctuating around 60%–70% (with optimal daily throughput windows spanning roughly 6–7 hours), programmatical API integration with automated retry and polling logic is strongly recommended. Seedance 2.0 Economy efficiently powers high-volume e-commerce product videos, automated social media content matrices, and low-cost ad creative pipelines.

Seedance 2.0 Economy

Seedance 2.0 Economy delivers the highest visual quality. It can generate videos between 4 and 15 seconds long from text prompts and supports multiple aspect ratios, audio generation, and enhanced web search capabilities.

Base URL

https://api.icreat.ai

Authentication

All API requests require authentication using an API key. You can obtain an API key from the console.

export ICREAT_API_KEY="your-api-key-here"

HTTP Request Headers

import os

API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + API_KEY,
}

Keep Your API Key Secure

Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

Video generation uses a two-step asynchronous workflow: first submit a task to obtain a task_id, then poll the query task result endpoint for progress. The response contains status and result. While the task is processing, result is []. When the status is SUCCEEDED, result contains a list of generated resources and the response includes costUSD. The examples below use the same task_id for both steps.

1. Submit a Task

Send a generation request to the submission endpoint.

POST/v1/task/submit/bytedance/seedance-2-0-economy

2. Query Task Results (Polling)

Use the task_id returned by the submission step to query the task’s progress. You can call this endpoint repeatedly until the task reaches a terminal state. The response contains status and result. While the task is processing, result is []. When the status is SUCCEEDED, result contains an array of generated resources and the response includes costUSD. A status of FAILED indicates that the task failed.

POST/v1/task/result

Input Parameters

Submit Task - Input Parameters

The following parameters are accepted in the task submission request body.

Total: 8; Required: 1; Optional: 7

promptstringrequired

The text prompt describing the video to generate. Multiline text is supported.

imagesstring[]

A list of publicly accessible image URLs to use as visual references.

videosstring[]

A list of publicly accessible video URLs to use as video references. Reference video duration is included when calculating the total cost.

audiosstring[]

A list of publicly accessible audio URLs to use as audio references.

resolutionstring

The output resolution. Supported values: 480p and 720p.

ratiostring

The output aspect ratio. Supported values: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive. When set to adaptive, the model automatically selects the most appropriate aspect ratio based on the input.

durationinteger

The output video duration in seconds. Accepts an integer from 4 to 15, or -1 to let the model select the duration automatically.

watermarkboolean

Whether to add an “AI Generated” watermark to the output video.

Query Task Results - Input Parameters

Total: 1; Required: 1; Optional: 0

task_idstringrequired

The task ID returned by the task submission endpoint.

Output Parameters

Submit Task - Output Parameters

Total: 1

task_idstring

The task ID returned by the task submission endpoint.

Query Task Results - Output Parameters

Total: Variable

statusstring

The current task status. When the task has not succeeded, result is typically []. When the status is SUCCEEDED, result contains generated resource items and the response includes costUSD.

SUBMITTEDSUCCEEDEDFAILED
resultarray[object]

The list of generated resources. While the task is processing or has not succeeded, this is []. On success, it is an array of objects.

costUSDnumber

The task cost in USD. This field appears only when status is SUCCEEDED.

LLM-Friendly Prompt

The following is an LLM-friendly Markdown prompt that can be copied into AI assistants such as Cursor or ChatGPT to help the AI understand the model’s API integration method, invocation workflow, and key parameters. Click the “Copy LLM Prompt” button or copy the full text from the code block below.

# bytedance/seedance-2-0-economy

> Seedance 2.0 Economy delivers the highest visual quality.

## Overview

Use iCreat’s two-step asynchronous task API to submit a video generation request, then poll the task result endpoint. When the task succeeds, retrieve the video resource URL from `result`. The successful response also includes `costUSD`.

## API Information

- **Base URL**: `https://api.icreat.ai`
- **Submit endpoint (POST)**: `/v1/task/submit/bytedance/seedance-2-0-economy`
- **Query result endpoint (POST)**: `/v1/task/result`
- **Model ID**: `bytedance/seedance-2-0-economy`
- **Authentication**: `Authorization: Bearer ${ICREAT_API_KEY}`

## Invocation Workflow

1. **Submit**: Send a POST request to the submission endpoint with the generation parameters. The response is `{ "task_id": "..." }`.
2. **Query result**: Send a POST request to `/v1/task/result` with `{ "task_id": "..." }`. The response contains `status` and `result`. While processing, `result` is `[]`. When the status is `SUCCEEDED`, `result` contains an array of generated resources and the response includes `costUSD`. Read `url` or `download_url` from resources whose `type` is `Video`.

## Submit Request Example

```json
{
  "prompt": "Example multiline\ntext",
  "images": [
    "https://example.com/example.png"
  ],
  "videos": [
    "https://example.com/example.mp4"
  ],
  "audios": [
    "https://example.com/example.mp3"
  ],
  "resolution": "480p",
  "ratio": "9:16",
  "duration": 4,
  "watermark": true
}

Input Notes

  • prompt (required): The text prompt describing the video to generate. Multiline text is supported.
  • images (optional): A list of publicly accessible image URLs to use as visual references.
  • videos (optional): A list of publicly accessible video URLs to use as video references. Reference video duration is included when calculating the total cost.
  • audios (optional): A list of publicly accessible audio URLs to use as audio references.
  • resolution (optional): The output resolution. Supported values: 480p and 720p.
  • ratio (optional): The output aspect ratio. Supported values: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive. When set to adaptive, the model automatically selects the most appropriate aspect ratio based on the input.
  • duration (optional): The output video duration in seconds. Accepts an integer from 4 to 15, or -1 to let the model select the duration automatically.
  • watermark (optional): Whether to add an “AI Generated” watermark to the output video.

Output Notes

  • Polling: Check status. While the task is processing, result is [].
  • Success: result is [{ "type": "Video", "url": "...", "download_url": "..." }], and the response also includes costUSD.

Important Notes

  • Use the same task_id for both steps.
  • Continue polling while the task is processing and result is [].
  • FAILED is a terminal state. Check the request parameters and reference resources to diagnose the failure.