# MiniMax Music 2.5 > Generate full-length songs with vocals, lyrics, and rich instrumentation from a text prompt and structured lyrics. - **Provider**: replicate - **Model ID**: minimax/music-2.5 - **Category**: music_generation - **Credits**: 350 per request - **Pricing Type**: fixed ## API Endpoint Base URL: https://api.core.today/v1 ### Create Prediction POST /predictions ### Get Status GET /predictions/{job_id} ### Cancel DELETE /predictions/{job_id} ## Authentication Header: `X-API-Key: YOUR_API_KEY` ## Input Parameters - `bitrate` (integer, optional): Bitrate for the generated music (Default: `256000`; Options: `32000`, `64000`, `128000`, `256000`) - `audio_format` (string, optional): Audio format for the output (Default: `mp3`; Options: `mp3`, `wav`, `pcm`) - `prompt` (string, optional): A description of the music style, mood, and scenario. For example: 'Pop, melancholic, perfect for a rainy night'. 0-2000 characters. (Default: ``) - `sample_rate` (integer, optional): Sample rate for the generated music (Default: `44100`; Options: `16000`, `24000`, `32000`, `44100`) - `lyrics` (string, **required**): Lyrics for the song. Use \n to separate lines. You can add structure tags like [Intro], [Verse], [Pre Chorus], [Chorus], [Interlude], [Bridge], [Outro], [Post Chorus], [Transition], [Break], [Hook], [Build Up], [Inst], [Solo] to control the arrangement. 1-3500 characters. ## Example Request ```json { "model": "minimax/music-2.5", "input": { "audio_format": "mp3", "bitrate": 256000, "sample_rate": 44100, "prompt": "Folk country, fingerpicked acoustic guitar, warm male vocal, nostalgic", "lyrics": "[Verse]\nOld screen door don't close right anymore\nCreaks like my knees on a cold morning\n\n[Chorus]\nBut time don't ask permission\nAnd rivers don't run backwards, friend" } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending", "provider": "replicate", "model": "black-forest-labs/flux-schnell", "created_at": "2026-01-01T00:00:00Z", "result": null, "error": null } ``` Status values: `pending`, `processing`, `completed`, `failed`, `cancelled` ## Usage Flow 1. POST /predictions with model and input → receive job_id 2. Poll GET /predictions/{job_id} until status is `completed` or `failed` 3. Result contains output URL(s) or data ## Output Type url ## Tags music-generation, text-to-music, audio, song, lyrics, minimax ## Documentation https://replicate.com/minimax/music-2.5