Seedance 2.5 API

seedance-2-5

Seedance 2.5 is a video model from ByteDance, available through the GPUniq API under the identifier `seedance-2-5`. Seedance 2.5 — newest ByteDance line, 480p/720p only. Billed per second: $0.198/s 480p, $0.426/s 720p (default) (official partner pricing minus 10%); 4-30s. First/last frame, up to 30 reference images, 10 reference videos and 10 reference audio tracks (≤30s each). Pricing starts at $0.43 per second of video. Generation runs as a job through the GPUniq API: you submit the prompt, poll for the result, and the exact charge comes back with the finished asset.

Try seedance-2-5 API documentation

Pricing

This model meters by output duration: the rate below is per second at the model’s default resolution, so a 5-second clip costs five times it. Higher resolutions bill at a higher per-second rate, and reference clips you attach are metered too. The API returns the exact charge with the job result, and failed jobs are not billed.

Billed for	GPUniq
Generationper second of video	$0.43

Billed from your GPUniq balance as you use it — no subscription, no monthly minimum, no per-seat fee. Prices refresh from the live catalog hourly.

Specifications

What the model accepts, what it returns, and the limits you will hit first.

API identifier: seedance-2-5
Pass this exact string as the "model" field of your request.
Type: Video generation
Served by ByteDance.

Detailed specs are not published for this model. Everything above comes from the GPUniq catalog; we would rather show less than guess.

How to call it

Generation runs as a job — submit the prompt, then poll the job id until the asset is ready.

Endpoint

POST /v1/llm/videos/jobs

Base URL

https://api.gpuniq.com

# 1. start the job — returns immediately with a job id
curl https://api.gpuniq.com/v1/llm/videos/jobs \
  -H "Authorization: Bearer YOUR_GPUNIQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-5",
    "prompt": "Drone shot over a misty pine forest at sunrise",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

# 2. poll every 3-5s until status is completed or failed
curl https://api.gpuniq.com/v1/llm/videos/jobs/JOB_ID \
  -H "Authorization: Bearer YOUR_GPUNIQ_API_KEY"

Create a key on /chat and send it as a bearer token. The same key works across every model in the catalog, so switching models means changing one string.

seedance-2-5 — frequently asked

How much does seedance-2-5 cost?

$0.43 per second of video on GPUniq, charged from your balance as you use it. There is no subscription and no monthly minimum.

How do I call seedance-2-5 from my code?

Send a generation request to the GPUniq API with "seedance-2-5" as the model, then poll the returned job id until the asset is ready. A GPUniq API key is the only credential involved.