Preview first, then 1080p

Seedance 2.5 Draft API

Seedance 2.5 as a cheap 480p preview, then the 1080p render of the one worth keeping.

Seedance 2.5 Draft is a video generation model from ByteDance, available on OttoPort's OpenAI-compatible API as the model ID seedance-2.5-draft at $0.203 / second as of 2026-10-17.

Provider

ByteDance

Price

$0.203 / second

Model ID

seedance-2.5-draft

Type

video generation model

Prompt explorationPicking a takeCheap iteration

Create with Seedance 2.5 Draft

video

Prompt

ExampleSelect to edit

Duration

Every run is a 480p draft at $0.203/s. Render the one you keep in 1080p at $0.899/s, within seven days.

Your result appears here

Start with the example prompt or make it your own. Your OttoPort account is used securely for generation.

Pricing

Seedance 2.5 Draft API pricing

What OttoPort bills for Seedance 2.5 Draft, and what that works out to per unit. Rates are read from the same catalog the gateway meters against, and were current on 2026-10-17.

480p draft	$0.203 / s	every request
5-second draft	$1.02
1080p from a draft	$0.8995 / s	renders a finished draft by its draft_id
5 seconds, draft + 1080p	$5.51	one preview kept and rendered

No subscription and no minimum — OttoPort bills prepaid credits against usage. See the full rate card.

Quickstart

Call Seedance 2.5 Draft in three lines

Send "model": "seedance-2.5-draft" to POST https://ottoport.ai/api/v1/videos/generations with an OttoPort key. No ByteDance account, no waitlist, no separate SDK.

curl https://ottoport.ai/api/v1/videos/generations \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5-draft",
    "prompt": "cinematic product reveal, slow dolly, black background",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

import requests

job = requests.post(
    "https://ottoport.ai/api/v1/videos/generations",
    headers={"Authorization": "Bearer " + API_KEY},
    json={
        "model": "seedance-2.5-draft",
        "prompt": "cinematic product reveal, slow dolly, black background",
        "duration": 5,
        "aspect_ratio": "16:9",
    },
).json()

# Video is a job: poll it, or pass webhook_url and be told.
print(job["id"], job["status"])

const res = await fetch("https://ottoport.ai/api/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "seedance-2.5-draft",
    prompt: "cinematic product reveal, slow dolly, black background",
    duration: 5,
    aspect_ratio: "16:9",
  }),
});

// Video is a job: poll it, or pass webhook_url and be told.
const job = await res.json();
console.log(job.id, job.status);

Before you start

1. Create a key at /api-keys.
2. Top up credits — the smallest pack is $25.
3. Paste the request. It returns a job ID; poll it or pass a webhook_url.

Full reference at /docs, or drive it from an agent with the MCP server and CLI.

Reference

Request parameters

The body POST https://ottoport.ai/api/v1/videos/generations accepts for Seedance 2.5 Draft.

Field	Type	Required	Notes
model	string	Yes	Always seedance-2.5-draft for Seedance 2.5 Draft.
prompt	string	Yes	Subject, action, and camera movement.
duration	integer	No	Seconds of output. This is the billed unit.
resolution	string	No	480p only: a draft renders there, and its completion at 1080p. Leave it out.
aspect_ratio	string	No	e.g. 16:9 or 9:16.
image_url	string	No	The first frame, for image-to-video.
last_frame_url	string	No	The closing frame. With image_url, this is first-and-last-frame generation.
reference_image_urls	array	No	Subjects the shot carries through — a character, a product — on models that accept references. Up to 9.
draft	boolean	No	Implied: every request is a 480p draft, and false is refused — use seedance-2.5 for a full clip. The job's id is a draft_id.
draft_id	string	No	Render a finished draft in 1080p, within seven days: the draft's job id, sent with model and nothing else — prompt, inputs and length all come from the draft. Drafts made under seedance-2.5 complete here too.
webhook_url	string	No	Called when the job settles, so you need not poll.
webhook_secret	string	No	Signs the webhook so you can verify it came from OttoPort.

Comparison

Seedance 2.5 Draft direct vs through OttoPort

Seedance 2.5 Draft is the same model either way — what changes is how many accounts, keys, and integrations you carry to reach it.

	ByteDance direct	Via OttoPort
Accounts and keys	A ByteDance account, plus one more for every other model you add	One OttoPort account and one key for the whole catalog
Request shape	ByteDance's own SDK and response format	OpenAI-compatible — point baseURL at OttoPort and change the model string
Switching models	A new integration per provider	Replace seedance-2.5-draft with any other model ID in the catalog
Billing	A separate invoice and contract per provider	Prepaid credits, no subscription, one usage ledger
Provider outages	Your call fails	Configured backup routes are tried in order on provider failure

Every run is a 480p draft at a fraction of the full price.

Render the take you like in 1080p — same shot, same length — within seven days.

Reference images work; reference video and audio do not.

FAQ

Seedance 2.5 Draft API questions

Cost, keys, and model IDs for Seedance 2.5 Draft on OttoPort.

How much does the Seedance 2.5 Draft API cost?

On OttoPort, Seedance 2.5 Draft costs $0.203 / second as of 2026-10-17. For scale, 5-second draft: $1.02. Billing is prepaid usage with no subscription and no minimum, and the current rate is always published at ottoport.ai/pricing.

How do I get a Seedance 2.5 Draft API key?

You do not need a ByteDance key. Create an OttoPort account, generate a key at ottoport.ai/api-keys, and send it as "Authorization: Bearer <key>" to POST https://ottoport.ai/api/v1/videos/generations with "model": "seedance-2.5-draft". The same key reaches every other model in the catalog.

What is the model ID for Seedance 2.5 Draft?

The OttoPort model ID for Seedance 2.5 Draft is seedance-2.5-draft. Pass it as the model field on POST https://ottoport.ai/api/v1/videos/generations, or list it programmatically from GET https://ottoport.ai/api/v1/models.

Is Seedance 2.5 Draft generation synchronous?

No. POST https://ottoport.ai/api/v1/videos/generations returns a job ID immediately. Poll GET https://ottoport.ai/api/v1/videos/generations/{id} for status, or pass webhook_url and webhook_secret and OttoPort will call you when the job settles. You are billed per second of output, so a failed job costs nothing.

Do I need a ByteDance account to use Seedance 2.5 Draft?

No. OttoPort connects to ByteDance on your behalf, so one OttoPort account covers Seedance 2.5 Draft and every other model in the catalog — no per-provider contracts, keys, or invoices.

Alternatives