Back to models

Seedance 2.5 Uncensored

ByteDance Seedance 2.5 video generation model served through an uncensored deployment, with single-shot clips up to 30 seconds and omni-reference image/video/audio conditioning

Model IDseedance-2-5-uncensored
RoutePOST /v1/videos
Video preview

Start from code that runs.

This model's contract and its own limits, beside the same request in curl, TypeScript and Python. The route is asynchronous, so the call returns a task you retrieve once it finishes.

InputPrompt
OutputMP4 video file
DeliveryAsync task
Billing$0.1028–$0.52 per generated second
Model limitsWhat this model accepts
Duration
4–30s
Frame sizes
848x480, 854x480, 480x854, 1280x720, 720x1280, 1920x1080, 1080x1920
Audio
Optional
Quick startThis model's request
request.sh
API reference
curl -X POST https://api.offrail.ai/v1/videos \  -H "Authorization: Bearer $OFFRAIL_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "seedance-2-5-uncensored",    "prompt": "Slow dolly through a neon-lit studio, shallow focus.",    "seconds": 8  }'

Point the base URL at OffRail and name this model. One API key reaches the whole catalogue.

One route, a visible lifecycle.

  1. 01
    Send the request

    Authenticate once and address the public model ID.

  2. 02
    OffRail manages the route

    Eligible upstream selection and metering happen behind the API contract.

  3. 03
    Receive or track the result

    Poll the task or use a webhook when your result is ready.

Build against one managed API.

Seedance 2.5 Uncensored runs on the same key, billing and task tracking as every other route in the catalogue.

Sign in