ByteDanceSeedance 2.5 API
ByteDance's newest video model — longer, sharper, more controllable
per second of video · 480p
Operational99.23% uptime (30 days)median 4m 13sTry Seedance 2.5
Runs on your balance at the price shown on the button. Results are saved to your account.
Output frame shape.
Output resolution. Higher resolutions cost more per second.
Length of the generated clip in seconds (4–30s). You pay per second.
Create a free account with Google or email — pay only for what you generate.
Your video will appear here
Write a prompt, pick your settings and hit Run. You only pay for successful generations.
Made with Seedance 2.5
A white spiral staircase seen from below breaks apart like a jigsaw puzzle, revealing the word “BELIEVE” in light and shadow
A paper boat drifts down a rain-soaked city gutter, camera tracking at water level, reflections of neon signs
An astronaut removes her helmet inside a greenhouse on Mars, soft volumetric light
What is Seedance 2.5?
Seedance 2.5 is ByteDance's latest video model with stronger motion, prompt adherence and multi-reference control, generating clips of up to 30 seconds at up to 1080p, with audio.
The newest Seedance
Seedance 2.5 improves motion realism, physics and prompt following over 2.0, and handles more reference assets in one request — ideal for branded content that must stay on-model.
Draft, then render
Iterate on composition cheaply at 480p, then render the final cut at 720p or 1080p with the same prompt and seed.
Seedance 2.5 pricing
Pay per second of video as you go, with no subscription required (monthly plans are optional). Failed generations are refunded automatically.
| Tier | Official price | CheaperGen | You save |
|---|---|---|---|
480p 16:9 · 24 fps | $0.0969/s | −6% | |
720p 16:9 · 24 fps | $0.2151/s | −7% | |
1080p 16:9 · 24 fps | $0.53/s | −7% |
- Official price: BytePlus ModelArk international list price for dreamina-seedance-2-5 ($10.7 / 1M video tokens at 480p–720p, $11.7 at 1080p; with video input $6.4 / $7; 480p 16:9 renders 854×480). Prices verified October 18, 2026.
- Billed by video tokens; per-second figures assume 16:9 and no input video.
- With reference videos, (reference video seconds + output seconds) are billed at the lower with-video rate. If the reference videos add up to less than ⅔ of the output's length rounded up to a whole second (4 s for a 5 s output, 7 s for 10 s, 10 s for 15 s), they are billed as that many seconds (ByteDance's official rule).
Specifications
- Resolutions
- 480p · 720p · 1080p
- Duration
- 4–30 s
- Aspect ratios
- 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9
- Frame rate
- 24 fps
- Audio
- Yes (included)
- Released
- Aug 7, 2026
Use Seedance 2.5 via API
One request to start a job, one to fetch the result. Same shape for every model.
const API = "https://cheapergen.com/api/v1";
const headers = {
Authorization: `Bearer ${process.env.CHEAPERGEN_API_KEY}`,
"Content-Type": "application/json",
};
// 1. Submit the job
let job = await fetch(`${API}/run/bytedance/seedance-2.5/text-to-video`, {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A slow dolly-in on a ceramicist shaping a vase at golden hour, dust in the light, shallow depth of field",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5
}),
}).then((r) => r.json());
// 2. Poll until it finishes (or pass webhook_url and skip polling)
while (job.status === "queued" || job.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
job = await fetch(`${API}/generations/${job.id}`, { headers }).then((r) => r.json());
}
console.log(job.status === "succeeded" ? job.output.video.url : job.error);Seedance 2.5 FAQ
More from ByteDance
Popular ByteDance models, on the same API key.
Seedance2.0 Fast
Text · Image · Reference → Video
Seedance 2.0 quality at lower latency and cost
Seedance2.0
Text · Image · Reference → Video
Cinematic multi-shot video with native audio, up to 4K
Seedance2.0 Mini
Text · Image · Reference → Video
The lowest-cost Seedance for drafts and high volume
Seedream5.0 Pro
Text → Image · Image Edit
Production-grade image generation and precise editing
Similar video models
Popular text-to-video models from other developers.
MiniMaxH3
Text · Image · Reference → Video
Hailuo H3 — expressive motion and physics, up to 2K
MiniMaxH3 Fast
Text · Image · Reference → Video
MiniMax H3 in seconds, not minutes — an accelerated build of the open weights
Wan3.0
Text · Image · Reference → Video
Up to 30-second videos with audio from Alibaba
ViduQ3 Turbo
Text · Image → Video
Fast, low-cost Vidu Q3 with audio, 1–16 s
Seedance 2.5 is developed by ByteDance. CheaperGen provides API access and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI