Cheaper Gen.
ByteDancevideoBest valueUnavailable

Seedance 2.0 Mini API

The lowest-cost Seedance for drafts and high volume

FromUp to −41%
$0.021/sOfficial price $0.035

per second of video · 480p

Try Seedance 2.0 Mini

Runs on your balance at the price shown on the button. Results are saved to your account.

Open full-screen Studio
0/5000

Output frame shape.

Output resolution. Higher resolutions cost more per second.

5s

Length of the generated clip in seconds (4–15s). You pay per second.

Generate synchronized sound, ambience and dialogue. No extra cost.
Estimated cost…

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.

What is Seedance 2.0 Mini?

Seedance 2.0 Mini generates 480p and 720p videos with audio at the lowest price in the Seedance family — ideal for previews, A/B tests and volume.

Lowest price
Cheapest Seedance tier
480p / 720p
Fast-loading outputs
Audio included
Synchronized sound
Same API
Swap models with one string

Lowest cost per second

Mini is the most affordable way to run Seedance: perfect for storyboards, previews, UGC-style content and large batches where cost matters most.

Seedance 2.0 Mini pricing

Pay per second of video. No subscription. Failed generations are refunded automatically.

TierOfficial priceCheaper Gen.
480p
16:9 · 24 fps
$0.035/s$0.021/s
720p
16:9 · 24 fps
$0.076/s$0.045/s
  • Official price: BytePlus ModelArk official price ($3.5 / 1M tokens; $2.1 with video input). Prices verified 2026-10-14.
  • 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.

Specifications

Resolutions
480p · 720p
Duration
4–15 s
Aspect ratios
16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9
Audio
Yes (included)
Released
Aug 11, 2026

Use Seedance 2.0 Mini via API

One request to start a job, one to fetch the result. Same shape for every model.

Full API reference
import os, time, requests

API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}

# 1. Submit the job
job = requests.post(f"{API}/run/bytedance/seedance-2.0-mini/text-to-video", headers=headers, json={
    "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
}).json()

# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
    time.sleep(3)
    job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()

print(job["status"], job["output"]["video"]["url"] if job["status"] == "succeeded" else job["error"])

Example prompts

Copy a prompt into the playground above to try it.

  • Time-lapse of clouds rolling over a mountain lake, wide shot

    Try it
  • A cat knocks a cup off a table, comedic slow motion

    Try it

Seedance 2.0 Mini FAQ

Seedance 2.0 Mini is billed by video tokens, exactly like ByteDance's official API: tokens = output seconds × width × height × 24 ÷ 1024. The tables above show the equivalent price per second at 16:9. With reference videos, the reference seconds are added to the output seconds and all of them are billed at a lower "with video input" rate. Audio is included at no extra cost and failed generations are never charged.

Yes. Requests run on ByteDance's Seedance 2.0 Mini through official API channels — the same weights and output quality, at a lower price.

Yes, generated videos can be used commercially, subject to ByteDance's content policy and our Terms of Service. Do not upload content you do not have rights to.

Typical 5-second clips finish in about one to three minutes depending on resolution and queue load. You can poll the task or receive a webhook when it completes.

Seedance 2.0 Mini is developed by ByteDance. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI