Quick Start

Go from zero to generating an AI video in about 5 minutes.

Critical upfront: Seedance 2.0 has 6 models, not 1. There is no "automatic mode detection" — you must pick the correct model value based on your input type. See the full matrix in Models Overview.

Prerequisites

• An EvoLink account (Sign up free)
• An API key from your API Key Management Page
• Any HTTP client (cURL, Python, Node.js, etc.)

Base URL

https://api.evolink.ai

Step 1: Save Your API Key

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

Step 2: Pick the Right Model

Based on what you have:

Need faster generation and lower cost? Add the fast- prefix to any of the above, e.g. seedance-2.0-fast-text-to-video. See Fast Models.

Step 3: Make Your First Request

Here's a text-to-video example:

import os
import requests

response = requests.post(
    "https://api.evolink.ai/v1/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['EVOLINK_API_KEY']}",
        "Content-Type": "application/json"
    },
    json={
        "model": "seedance-2.0-text-to-video",
        "prompt": "A golden retriever running through a sunlit meadow, cinematic slow motion",
        "duration": 5,
        "quality": "720p",
        "aspect_ratio": "16:9"
    }
)

task = response.json()
print(f"Task ID: {task['id']}")
print(f"Status: {task['status']}")

Response (HTTP 200)

{
    "id": "task-unified-1774857405-abc123",
    "object": "video.generation.task",
    "created": 1774857405,
    "model": "seedance-2.0-text-to-video",
    "status": "pending",
    "progress": 0,
    "type": "video",
    "task_info": {
        "can_cancel": true,
        "estimated_time": 165,
        "video_duration": 5
    },
    "usage": {
        "billing_rule": "per_second",
        "credits_reserved": 50,
        "user_group": "default"
    }
}

Note that billing_rule is always per_second — longer duration values cost more.

Step 4: Poll for the Video

Every generation request is asynchronous. Use the task ID to poll for the result:

import time

task_id = task["id"]

while True:
    status = requests.get(
        f"https://api.evolink.ai/v1/tasks/{task_id}",
        headers={"Authorization": f"Bearer {os.environ['EVOLINK_API_KEY']}"}
    )
    result = status.json()

    if result["status"] == "completed":
        print(f"Video URL: {result['results'][0]}")
        break
    if result["status"] == "failed":
        print("Generation failed")
        break

    print(f"Progress: {result['progress']}%")
    time.sleep(5)

Important: Generated video URLs are valid for 24 hours. Download and save them to your own storage promptly.

For production use, prefer Webhooks (callback_url) over polling.

Common Pitfalls

Next Steps

• Models Overview — Full 6-model matrix and decision tree
• Authentication — Bearer token details
• Text-to-Video / Image-to-Video / Reference-to-Video
• Async Tasks — Polling endpoint details
• Webhooks — callback_url real-time notifications