Seedance API documentation: generate, status, 1080p and pricing

Seedance 1.5 Pro reference

Seedance API docs Seedance API documentation: generate, status, 1080p and pricing

Until 21 October 2026 the Seedance API worked like this: authenticate with a Bearer key, create jobs with POST /seedance/generate/, and poll GET /seedance/status/{generation_id}/ until the video was ready, with 480p, 720p, and 1080p output in 4, 8, or 12 second durations. That route now returns HTTP 410. For new Seedance jobs use the Video Studio API: POST /api/v1/video-studio/generate/ with model_slug seedance_2_5, seedance_2, seedance_2_fast or seedance_2_mini, documented on the Video API docs.

Current route: Seedance 2.x through the Video Studio API

New Seedance integrations use the Video Studio API. Authenticate with the same Bearer key, send a model_slug, and poll the job status. Supported Seedance slugs today: seedance_2_5 (up to 30 s, up to 50 multimodal references), seedance_2, seedance_2_fast and seedance_2_mini. Fetch the live model matrix and current per-model credit rates from GET /api/v1/models/video/.

curl -X POST https://ulazai.com/api/v1/video-studio/generate/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_slug": "seedance_2_mini",
    "prompt": "A quiet Dutch canal at dusk, bicycles on the bridge, warm window light, gentle camera push-in",
    "aspect_ratio": "16:9",
    "duration_seconds": 4,
    "quality_mode": "480p"
  }'

curl https://ulazai.com/api/v1/video-studio/status/JOB_ID/ \
  -H "Authorization: Bearer YOUR_API_KEY"

This payload is the cheapest possible test call (seedance_2_mini, 480p, 4 seconds, text-to-video) and it is the exact request behind the captured responses below; swap in seedance_2_5, seedance_2 or seedance_2_fast for higher quality tiers. The generate call answers immediately with a job id list and your remaining credit balance; per-model credit rates come from the models matrix, and the exact amount a job charged shows up as credits_charged in the status response once the job completes:

// POST /api/v1/video-studio/generate/ (captured response, 2026-10-26)
{
  "success": true,
  "job_ids": ["0752648f-c0b1-451d-a1dc-6d0261600197"],
  "credits_remaining_total": 98
}

// GET /api/v1/video-studio/status/0752648f-c0b1-451d-a1dc-6d0261600197/ after the job finished
{
  "success": true,
  "job": {
    "job_id": "0752648f-c0b1-451d-a1dc-6d0261600197",
    "model_slug": "seedance_2_mini",
    "status": "completed",
    "duration_seconds": 4,
    "quality_mode": "480p",
    "result_urls": ["https://media.ulazai.com/video_studio/seedance/.../video_1.mp4"],
    "credits_charged": 38,
    "completed_at": "2026-10-26T11:51:00.320868+00:00"
  }
}

Error responses follow the same shape. A missing or invalid Bearer key returns 401 {"detail": "..."}, an unsupported duration_seconds for the slug returns 400 {"success": false, "error": "Invalid duration for this model"}, and an unknown slug returns 404 {"success": false, "error": "Unknown model"}. A 4-second 480p seedance_2_mini text-to-video render charged exactly 38 credits (9.5 credits/second), matching the rate in the models matrix.

The full request contract (all fields, reference inputs and status flow) lives on the Video API docs; per-second credit rates per slug come from GET /api/v1/models/video/, and the status response confirms the exact credits_charged per job.

Seedance 1.5 Pro pricing as it stood until retirement (historical table)

The retired Seedance 1.5 Pro route billed per render in credits, not per subscription. The table below is the exact matrix that route charged until 21 October 2026, the same numbers its generate response reported as credits_used. It stays here as a pricing reference, not as a current offer. Current Seedance 2.x pricing runs per model in the Video Studio credit system.

The Seedance model family: 1.5 Pro, 2.0 and 2.5

Seedance is ByteDance's text-to-video and image-to-video model. ByteDance launched the first Seedance in June 2025, released Seedance 2.0 in February 2026, and has since shown Seedance 2.5. Each generation pushes the same core idea further: cinematic motion, stronger prompt-following, multi-shot scenes, image and video references, and optional native audio in a single render. The API guide covers the currently supported Seedance versions without requiring you to set up ByteDance's own platform.

Seedance 2.5 on this API: model IDs and referencing

Queries for seedance 2.5 api usually want two things: the model identifier to send, and how image references work on the new generation. ByteDance positions Seedance 2.5 around one-take creation and flexible referencing - more input images steering the same scene - while keeping the generate-and-poll job shape that this page documents.

This section describes the retired 1.5 Pro contract for reference. Production work moves to the Video Studio API with model_slug (for example seedance_2_5): different endpoints, a job-based status flow, and pricing per model_slug per second, see the Video API docs.

ByteDance and ARK: the official model, one unified route

People searching for ByteDance Seedance official documentation or the ARK Seedance API are usually looking for two different things: the model itself, and a way to actually call it. Seedance is ByteDance's own model, published through ByteDance's Volcano Engine ARK platform. That route means setting up an ARK account, region access, and raw model endpoints.

UlazAI sits in front of that as a third-party API layer. You get one Bearer key, a hosted image upload step, a shared credit wallet, and the small set of endpoints on this page, no ARK onboarding, no regional workaround, and no VPN or Chinese phone number to reach the model. If you specifically searched ARK API Seedance image upload, the equivalent here is a single call: POST /seedance/upload/ returns a permanent URL that you drop into input_urls on generate (see the upload endpoint below).

Quick integration summary

Public endpoint summary