# Seedance 1 Pro - Core.Today AI API

> A pro version of Seedance that offers text-to-video and image-to-video support for 2-12 second videos, at 480p, 720p, and 1080p resolution.

- **Provider**: ByteDance
- **Model ID**: bytedance/seedance-1-pro
- **Category**: Video Generation
- **Credits**: 700 per 5s 1080p video — billed per second (480p 28/s, 720p 56/s, 1080p 140/s; defaults to 1080p)
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Higher fidelity than Seedance 1 Lite, up to full 1080p output
- Text-to-video and image-to-video generation in one model
- 2-12 second duration range with per-second billing
- Fixed-camera mode and last-frame conditioning
- Defaults to 1080p output for maximum quality

## Use Cases
- High-quality marketing and product videos
- Cinematic shots from a text prompt
- Animating a portrait or product photo at full 1080p
- Fixed-camera shots for consistent framing
- Longer-form clips up to 12 seconds

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt for video generation

### Optional
- **fps**: integer (default: 24) - Frame rate (frames per second)
  Options: 24
- **seed**: integer - Random seed for reproducible generation
- **image**: string - Input image for image-to-video generation
- **duration**: integer (default: 5) - Video duration in seconds (2-12). Billed per second of output
- **resolution**: string (default: 1080p) - Video resolution. Defaults to the highest tier (1080p)
  Options: 480p, 720p, 1080p
- **aspect_ratio**: string (default: 16:9) - Video aspect ratio. Ignored if an image is used
  Options: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21
- **camera_fixed**: boolean (default: false) - Whether to fix camera position
- **last_frame_image**: string - Last frame image (requires a first frame image)

## Examples

### Cinematic 1080p Shot (Default)
Text-to-video at the default 1080p resolution for maximum fidelity
```json
{
  "model": "bytedance/seedance-1-pro",
  "input": {
    "prompt": "The sun rises slowly between tall buildings. [Ground-level follow shot] Bicycle tires roll over a dew-covered street at dawn. The cyclist passes through dappled light under a bridge as the entire city gradually wakes up.",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }
}
```

### 720p Preview
A cheaper 720p pass useful for iterating on prompts before the final 1080p render
```json
{
  "model": "bytedance/seedance-1-pro",
  "input": {
    "prompt": "A chef plating a dessert in slow motion in a modern restaurant kitchen",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- The default resolution is 1080p ($0.15/s) — explicitly set resolution to 720p or 480p while iterating to save credits
- 1080p costs 2.5x the 720p rate and 5x the 480p rate
- Billing is per second of output; duration ranges from 2 to 12 seconds
- camera_fixed is useful for product shots that need a stable, static frame

## Documentation
https://replicate.com/bytedance/seedance-1-pro