Seedance API Examples

Since the Seedance model is a multimodal model, the OpenAI SDK currently does not support direct access to this model. You need to use the request method to access the Seedance model.

Basic Configuration

Before starting to use the API, please ensure you have obtained an API Key. If not, please refer to Create API Key.

Basic Information

• API Base URL: https://api.agentsflare.com/byteplus/v3/contents/generations/tasks
• Authentication Method: Bearer Token
• Content Type: application/json

Request Examples

Create Video

cURL

curl --location --request POST 'https://api.agentsflare.com/byteplus/v3/contents/generations/tasks' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {API-KEY}' \
--data-raw '{
    "model": "dreamina-seedance-2-0-260128",
    "content": [
        {
            "type": "text",
            "text": "The lady in the picture drives a sports car out of the podium and crashes through the exhibition hall glass."
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://*******.jpeg|png...."
            }
        }
    ],
    "ratio": "adaptive",
    "duration": 6,
    "watermark": false
}'

Python

import requests
import json

url = "https://api.agentsflare.com/byteplus/v3/contents/generations/tasks"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer {API-KEY}"
}

payload = {
    "model": "dreamina-seedance-2-0-260128",
    "content": [
        {
            "type": "text",
            "text": "The lady in the picture drives a sports car out of the podium and crashes through the exhibition hall glass."
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://*******.jpeg|png...."
            }
        }
    ],
    "ratio": "adaptive",
    "duration": 6,
    "watermark": False
}

response = requests.post(url, headers=headers, json=payload)

print(response.status_code)
print(response.json())

Node.js

const fetch = require('node-fetch');

const url = 'https://api.agentsflare.com/byteplus/v3/contents/generations/tasks';

const payload = {
    model: 'dreamina-seedance-2-0-260128',
    content: [
        {
            type: 'text',
            text: 'The lady in the picture drives a sports car out of the podium and crashes through the exhibition hall glass.'
        },
        {
            type: 'image_url',
            image_url: {
                url: 'https://*******.jpeg|png....'
            }
        }
    ],
    ratio: 'adaptive',
    duration: 6,
    watermark: false
};

const options = {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json',
        'Authorization': 'Bearer {API-KEY}'
    },
    body: JSON.stringify(payload)
};

fetch(url, options)
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => {
        console.error('Error:', error);
    });

Go

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io"
	"net/http"
)

func main() {
	url := "https://api.agentsflare.com/byteplus/v3/contents/generations/tasks"

	payload := map[string]interface{}{
		"model": "dreamina-seedance-2-0-260128",
		"content": []map[string]interface{}{
			{
				"type": "text",
				"text": "The lady in the picture drives a sports car out of the podium and crashes through the exhibition hall glass.",
			},
			{
				"type": "image_url",
				"image_url": map[string]string{
					"url": "https://*******.jpeg|png....",
				},
			},
		},
		"ratio":     "adaptive",
		"duration":  6,
		"watermark": false,
	}

	jsonData, err := json.Marshal(payload)
	if err != nil {
		fmt.Println("Error marshaling JSON:", err)
		return
	}

	req, err := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
	if err != nil {
		fmt.Println("Error creating request:", err)
		return
	}

	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer {API-KEY}")

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		fmt.Println("Error sending request:", err)
		return
	}
	defer resp.Body.Close()

	body, err := io.ReadAll(resp.Body)
	if err != nil {
		fmt.Println("Error reading response:", err)
		return
	}

	fmt.Println("Status:", resp.StatusCode)
	fmt.Println("Response:", string(body))
}

Response Example

After successful creation, returns the task ID, which you can use to query task status and download the video.

{
  "id": "cgt-2026******-****"
}

File Retrieval

cURL

curl --location --request GET 'https://api.agentsflare.com/byteplus/v3/contents/generations/tasks/cgt-2026******-****' \
--header 'Authorization: Bearer {API-KEY}'

Python

import requests

url = "https://api.agentsflare.com/byteplus/v3/contents/generations/tasks/cgt-2026******-****"

headers = {
    "Authorization": "Bearer {API-KEY}"
}

response = requests.get(url, headers=headers)

print(response.status_code)
print(response.json())

Node.js

const fetch = require('node-fetch');

const url = 'https://api.agentsflare.com/byteplus/v3/contents/generations/tasks/cgt-2026******-****';

const options = {
    method: 'GET',
    headers: {
        'Authorization': 'Bearer {API-KEY}'
    }
};

fetch(url, options)
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => {
        console.error('Error:', error);
    });

Go

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	url := "https://api.agentsflare.com/byteplus/v3/contents/generations/tasks/cgt-2026******-****"

	req, err := http.NewRequest("GET", url, nil)
	if err != nil {
		fmt.Println("Error creating request:", err)
		return
	}

	req.Header.Set("Authorization", "Bearer {API-KEY}")

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		fmt.Println("Error sending request:", err)
		return
	}
	defer resp.Body.Close()

	body, err := io.ReadAll(resp.Body)
	if err != nil {
		fmt.Println("Error reading response:", err)
		return
	}

	fmt.Println("Status:", resp.StatusCode)
	fmt.Println("Response:", string(body))
}

Response Example

The video status response contains the video download URL, which you can directly access to download the video.

{
    "id": "cgt-2026******-****",
    "model": "dreamina-seedance-2-0-260128",
    "status": "succeeded",
    "content": {
        "video_url": "https://ark-content-generation-ap-southeast-1.tos-ap-southeast-1.volces.com/seedance-1-0-pro/021768294532558000000000ffffc0a8bc10474251.mp4?X************"
    },
    "usage": {
        "completion_tokens": 295800,
        "total_tokens": 295800
    },
    "created_at": 1768294532,
    "updated_at": 1768294581,
    "seed": 44457,
    "resolution": "1080p",
    "ratio": "16:9",
    "duration": 6,
    "framespersecond": 24,
    "service_tier": "default",
    "execution_expires_after": 172800,
    "draft": false
}

BytePlus Native Request Parameters

Parameter	Required	Description
model	Yes	Model name, e.g. dreamina-seedance-2-0-260128
content	Yes	Array of text/image objects for the prompt
ratio	Optional	Aspect ratio, e.g. 16:9, 9:16, adaptive
duration	Optional	Video duration in seconds
watermark	Optional	Whether to add a watermark (true / false)
seed	Optional	Random seed (integer) for reproducibility
camera_fixed	Optional	Lock camera movement (true / false)
frames	Optional	Total frames (alternative to duration, choose one)
return_last_frame	Optional	Return the last frame as an image (true / false)

Alternative: OpenAI-Compatible /v1/videos/generations

In addition to the BytePlus native API above, Agentsflare also supports the OpenAI-compatible /v1/videos/generations endpoint for Seedance. This endpoint uses a simpler prompt + duration style and is useful for integrations that expect the videos.generate interface.

For more request methods and parameters, see Seedance Request Parameters.

cURL

curl https://api.agentsflare.com/v1/videos/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "seedance",
    "prompt": "A bird flying over mountains",
    "duration": 5
  }'

Python

from openai import OpenAI

url = "https://api.agentsflare.com/v1"

client = OpenAI(
    base_url=url,
    api_key="YOUR_API_KEY"
)

video = client.videos.generate(
    model="seedance",
    prompt="A bird flying over mountains",
    duration=5
)

print(video.data[0].url)

Response Example

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://..."
    }
  ]
}

Request Parameters

For detailed parameters, see Videos API.

Supported Models

The following models are available through this interface (sorted by recommendation):

• dreamina-seedance-2-0-260128
• dreamina-seedance-2-0-fast-260128
• seedance-1-5-pro-251215
• seedance-1-0-pro-fast-251015
• seedance-1-0-lite-t2v-250428 Retired
• seedance-1-0-lite-i2v-250428 Retired

💡 Tip

The model field in the request example can be replaced with any model name above.