seedance-2-0 ByteDance’s frontier video model — the first partner model on the Sogni API.
No GPU. No setup. Cancel anytime.
Seedance 2.0 is ByteDance’s frontier generation model and the first third-party partner model routed through the Sogni API: same key, same workflow endpoints, frontier-grade motion and prompt understanding up to 1080p with native audio.
It accepts a uniquely rich reference set — up to nine images, three videos, and three audio clips (twelve assets total, addressed as @Image1 / @Video1 / @Audio1 in the prompt). As a partner model it is Premium-Spark-only, runs on vendor infrastructure rather than Supernet workers, ignores negative prompts, and is priced by generated duration and resolution; supplying a video reference applies the lower v2v rate.
Seedance 2.0 exposes these workflow variants — pass the matching model id.
| Workflow | Model id |
|---|---|
| Text → video | seedance-2-0 |
| Image → video | seedance-2-0 |
| Image + audio → video | seedance-2-0 |
| Video → video | seedance-2-0 |
On the Sogni API you pay per clip in Spark (1 Spark = $0.005). Prefer a flat rate? The Sogni app runs Seedance 2.0 and 100+ other models credit-free under fair use.
| Configuration | Spark | USD |
|---|---|---|
| 5 s · 720p | 198 Spark | $0.99 |
| 5 s · 1080p | 487 Spark | $2.43 |
| 5 s · 720p · video reference (v2v) | 121 Spark | $0.60 |
| 5 s · 1080p · video reference (v2v) | 297 Spark | $1.49 |
Premium Spark required — purchased credits; no SOGNI fallback.
No negative prompts. Fixed 24 fps. Reference assets must be public HTTPS URLs.
Vendor capacity — does not consume Supernet GPU workers.
One Sogni API key reaches every model on the Supernet — call Seedance 2.0 by id.
import { SogniClient } from '@sogni-ai/sogni-client';
const client = await SogniClient.createInstance({
appId: crypto.randomUUID(),
apiKey: process.env.SOGNI_API_KEY,
network: 'fast',
});
const project = await client.projects.create({
type: 'video',
modelId: 'seedance-2-0',
positivePrompt: 'a slothicorn surfing a wave of liquid paint, slow push-in, cinematic',
numberOfMedia: 1,
duration: 5,
});
const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24h curl https://api.sogni.ai/v1/creative-agent/workflows \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SOGNI_API_KEY" \
-d '{
"input": {
"title": "First render",
"steps": [{
"id": "step1",
"toolName": "generate_video",
"arguments": { "prompt": "a slothicorn surfing a wave of liquid paint, slow push-in, cinematic", "videoModel": "seedance2", "duration": 5 }
}]
},
"confirm_cost": true
}' REST workflow alias: seedance2. Pin the exact id with the SDK. Full reference at docs.sogni.ai.
Most platforms ration credits or rent a cloud GPU by the hour. Sogni gives you a flat monthly price for credit-free fair-use generation, powered by a creator-owned GPU network — or per-render Spark pricing if you'd rather pay as you go via the API.
One flat price in the app. Generate under fair use without a per-image meter.
Image, video, music, and language models in one workspace and one API key.
Prefer pay-as-you-go? Call Seedance 2.0 by id and pay in Spark.
Runs on a decentralized GPU network where workers share subscription revenue.
Seedance 2.0 is ByteDance’s frontier generation model and the first third-party partner model routed through the Sogni API: same key, same workflow endpoints, frontier-grade motion and prompt understanding up to 1080p with native audio.
From 198 Spark ($0.99) per clip on the Sogni API (1 Spark = $0.005) — or unlimited under fair use on a flat monthly Sogni plan.
Create instantly in the Sogni app, or call the Sogni API with model id seedance-2-0.
No. Seedance 2.0 runs on the Sogni Supernet — a decentralized network of creator GPUs — with no local install or graphics card required.
Create in the app, or build with the API. Your call.