Seedance 2.0 API: Complete Developer Guide for Video Generation (2026)

What Is Seedance 2.0?

Seedance 2.0 is ByteDance's production-grade AI video generation model, released in February 2026. It generates 4 to 15 second video clips with realistic physics simulation, native multi-shot storytelling, and output from 480p up to 1080p and 4K. It's one of the first models to handle motion coherence across scene cuts without post-processing.

To call it from code, use the ModelsLab Seedance 2.0 API (price per second for every Seedance model and provider, checked September 27, 2026): send a POST request to https://modelslab.com/api/v7/video-fusion/text-to-video with model_id set to seedance-2-text-to-video, plus prompt, duration and aspect_ratio. Seedance 2.0 is billed per second of video from your wallet balance: $0.10/sec at 480p, $0.23/sec at 720p and $0.45/sec at 1080p, so a 5-second 720p clip costs about $1.15.

What sets Seedance 2.0 apart from earlier video generation models:

• Up to 15-second clips — significantly longer than the 4-5 second clips most models generate

• Realistic physics — objects fall, collide, and deform with physically accurate motion

• Multi-shot storytelling — maintains character and scene consistency across cuts

• Native audio — set generate_audio to generate a synced soundtrack with the clip

• 1080p and 4K output — production-ready resolution without upscaling (the Fast and Mini variants cap at 720p)

ModelsLab exposes the Seedance 2.0 family as model_id values on two endpoints:

The newer Seedance 2.5 uses the same endpoints with seedance-2-5-text-to-video and seedance-2-5-image-to-video.

How to get started: Authentication

Every ModelsLab video request carries your API key in the key field of the JSON body. Create a ModelsLab account, subscribe to a plan (API access starts at $21/month), add wallet balance for third-party models such as Seedance, and copy your key from the dashboard.

{
  "key": "YOUR_MODELSLAB_API_KEY",
  "model_id": "seedance-2-text-to-video",
  "prompt": "..."
}

The base URL for Seedance text-to-video requests is:

POST https://modelslab.com/api/v7/video-fusion/text-to-video

Seedance 2.0 Text-to-Video API

The text-to-video endpoint generates a video from a text prompt. Set model_id to seedance-2-text-to-video to route your request through Seedance 2.0.

Python Example

import time
import requests
,[object Object],
,[object Object],
,[object Object],
,[object Object],
,[object Object],[object Object],
,[object Object],

video_url = generate_seedance_video(
prompt="A futuristic city at sunset, flying cars weaving between glass towers, cinematic wide shot",
duration=5,
)
print(f"Video ready: {video_url}")

cURL Example

curl -X POST "https://modelslab.com/api/v7/video-fusion/text-to-video" \
  -H "Content-Type: application/json" \
  -d '{
    "key": "YOUR_API_KEY",
    "model_id": "seedance-2-text-to-video",
    "prompt": "A timelapse of a city waking up at dawn, golden light, wide aerial shot",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }'
,[object Object],
,[object Object],

curl -X POST "https://modelslab.com/api/v7/video-fusion/fetch/REQUEST_ID" ,[object Object],
-H "Content-Type: application/json" ,[object Object],
-d '{"key": "YOUR_API_KEY"}'

Seedance 2.0 Image-to-Video API

The image-to-video endpoint animates a still image into a video. Use model_id seedance-2.0-fast-i2v and pass the image as a public URL in the init_image array. This is particularly effective for product shots, architectural visualizations, and portrait animations.

Python Example

def image_to_video(image_url: str, prompt: str) -> str:
    """Animate an image with Seedance 2.0 Fast image-to-video."""
    response = requests.post(
        f"{BASE_URL}/image-to-video",
        json={
            "key": API_KEY,
            "model_id": "seedance-2.0-fast-i2v",
            "prompt": prompt,
            "init_image": [image_url],   # public image URL(s)
            "duration": 5,
            "resolution": "720p",
        },
        timeout=60,
    )
    data = response.json()
,[object Object],
,[object Object],

video = image_to_video(
"https://example.com/product_photo.jpg",
"The product rotates slowly, studio lighting, professional reveal",
)

Node.js Integration

const API_KEY = 'your_modelslab_api_key';
const BASE_URL = 'https://modelslab.com/api/v7/video-fusion';
,[object Object],
,[object Object],
,[object Object],
,[object Object],

generateVideo('A mountain lake at sunrise, perfect reflection, cinematic')
.then((url) => console.log('Video:', url))
.catch(console.error);

Key API Parameters

Common Parameters for Both Endpoints

• key : Your ModelsLab API key (required)

• model_id : seedance-2-text-to-video, seedance-2.0-fast-t2v or seedance-2-mini-t2v (text-to-video), or seedance-2.0-fast-i2v (image-to-video)

• prompt : Detailed description of the video content. More detail = better results.

• duration : Clip length in seconds, 4 to 15 (default 5)

• aspect_ratio : For example 16:9 (landscape), 9:16 (portrait) or 1:1

• resolution : 480p, 720p, 1080p or 4k (Fast and Mini: 480p or 720p). Price per second rises with resolution.

• init_image : Array of image URLs (image-to-video only)

• generate_audio : true to generate a synced soundtrack

• webhook / track_id : Optional URL for async notification when generation completes, plus your own job ID

Prompt Engineering for Seedance 2.0

Seedance 2.0's physics engine responds well to specific motion descriptions. Here are prompt patterns that consistently produce strong results:

Effective Prompt Patterns

• Camera movement : "slow pan left", "tracking shot", "aerial drone view", "zoom out from"

• Physics specifics : "water splashing", "leaves falling", "fabric rippling in wind"

• Lighting cues : "golden hour light", "neon reflections on wet pavement", "volumetric fog"

• Style qualifiers : "cinematic", "film grain", "studio lighting", "documentary style"

Prompt Templates

# Landscape/Nature
"[scene], [time of day], [weather], [camera movement], cinematic, film grain"
,[object Object],
,[object Object],
,[object Object],
,[object Object],
,[object Object],

"[subject] [action], [setting], [lighting], tracking shot, smooth motion"

Handling Async Generation

Seedance 2.0 videos typically take 60-180 seconds to generate depending on length and resolution. The API answers with status: processing, an id and a fetch_result URL. POST {"key": "..."} to https://modelslab.com/api/v7/video-fusion/fetch/{id} every 10 seconds until you get status: success.

For production applications, use webhooks instead of polling:

payload = {
    "key": API_KEY,
    "model_id": "seedance-2-text-to-video",
    "prompt": "...",
    "duration": 5,
    "webhook": "https://your-app.com/webhooks/video-ready",
    "track_id": "job_12345",  # Your internal job ID for tracking
}

ModelsLab will POST to your webhook URL when the video is ready, including the track_id so you can match the result to your job queue.

Seedance 2.0 vs Competing Models

Here's how Seedance 2.0 compares to other video generation models available via API:

• Seedance 2.0 (seedance-2-text-to-video) : Best physics realism, 4-15s clips, up to 4K, native audio

• Kling 3.0 : Strong character consistency, shorter clips (5-10s), excellent for people

• Sora 2 : No longer available. OpenAI shut down the Sora 2 API on September 24, 2026

• Runway Gen-4 : Fast generation, good for short clips, limited to 10s max

• Wan 2.2 : Open-weights, self-hostable, lower quality ceiling, included on the ModelsLab $149/month Open Source Unlimited plan

For most production use cases — product videos, marketing content, short films — Seedance 2.0 via ModelsLab gives a strong quality-to-cost ratio, and Seedance 2.0 Mini is the cheapest way to draft before you render the final take.

Error Handling and Rate Limits

import requests
from tenacity import retry, stop_after_attempt, wait_exponential
,[object Object],
,[object Object],[object Object],
,[object Object],
,[object Object],
,[object Object],
,[object Object],

undefined

Pricing

Seedance 2.0 is a third-party model, so ModelsLab bills it per second of output from your wallet balance, on top of any plan. Plans do not cover it. Rates listed on the model pages on September 23, 2026:

The price for your exact duration and resolution shows on the model page before you generate, and you can check your balance and usage in the ModelsLab dashboard. For high-volume production (100+ videos/day), contact ModelsLab for enterprise pricing with volume discounts and dedicated capacity.

Build With Seedance 2.0 on ModelsLab

Seedance 2.0 is production-ready and available now via the ModelsLab API. With one key for text-to-video and image-to-video, you can integrate state-of-the-art video generation into your application in under an hour. See the Seedance API page for every Seedance model_id, current prices and copy-paste examples.

Sign up for a ModelsLab account to get your API key and start generating. API access starts at $21/month, and Seedance renders are billed per second from your wallet balance.