# Suno Music V4.5 - Core.Today AI API

> Suno V4.5 music generation. Creates two complete songs from a text description, or from exact lyrics with style and title in custom mode. Returns audio, cover image, and metadata for each track.

- **Provider**: Suno
- **Model ID**: suno/music-v4-5
- **Category**: Audio & TTS
- **Credits**: 140 per generation (2 songs)
- **Speed**: Medium
- **Quality**: High

## Features
- Two complete songs per generation
- Custom mode with exact lyrics, style, and title
- Instrumental-only option
- Vocal gender and style weight controls
- Cover image generated with each track

## Use Cases
- Background music for videos and podcasts
- Jingles and brand sound logos
- Song prototypes from lyric drafts
- Game and app background tracks
- Personalized songs for events

## 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
- **customMode**: boolean - true: control style/title yourself (prompt becomes exact lyrics). false: simple mode
- **instrumental**: boolean - Generate instrumental music without vocals

### Optional
- **prompt**: string - Song description (simple mode, max 500 chars) or exact lyrics (custom mode, max 3000 chars)
- **style**: string - Music style, required in custom mode (max 200 chars)
- **title**: string - Song title, required in custom mode (max 80 chars)
- **negativeTags**: string - Music styles to avoid, comma separated (custom mode)
- **vocalGender**: string - Preferred vocal gender: m or f
  Options: m, f
- **styleWeight**: number - Style adherence weight, 0-1 (custom mode)
- **weirdnessConstraint**: number - Creativity/novelty constraint, 0-1 (custom mode)
- **audioWeight**: number - Relative weight of the audio factors, 0-1 (custom mode)

## Examples

### Simple mode song from a description
Generate two full songs from a short mood/genre/topic description
```json
{
  "model": "suno/music-v4-5",
  "input": {
    "customMode": false,
    "instrumental": false,
    "prompt": "A dreamy synthwave track about driving through a neon city at night"
  }
}
```

## 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
- In simple mode (customMode=false), just describe mood, genre, and topic in prompt.
- In custom mode, prompt is used as the exact lyrics — structure it with [Verse]/[Chorus] markers.
- Each generation returns two variations; pick the better one.

## Documentation
https://docs.sunoapi.org/suno-api/generate-music