# MiniMax Music 3.0

> MiniMax Music 3.0 generates music from a text prompt. Billing is flat per generation — $0.03 through RouteMux against MiniMax's $0.15 — with no duration or quality tiers, so the cost of a run is simply the number of generations.

Canonical: https://routemux.com/minimax/music-3.0
Provider: MiniMax

## Key facts

| Field | Value |
| --- | --- |
| Model ID | minimax/music-3.0 |
| Official model ID | music-3.0 |
| Input modalities | text |
| Output modalities | audio |
| Capabilities | Music Generation |
| Availability | available |

## Pricing

- RouteMux: $0.03 per generation
- Official: $0.15 per generation
- Saving vs official: 80%

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_audio_speech

## What is MiniMax Music 3.0

MiniMax Music 3.0 generates music from a text prompt. Billing is flat per generation — $0.03 through RouteMux against MiniMax's $0.15 — with no duration or quality tiers, so the cost of a run is simply the number of generations.

It answers on the OpenAI Audio Speech protocol. Like other generative audio and video models, output is produced asynchronously rather than returned inline with the request.

Note that this is a generation model, not text-to-speech: the input is a description of the music you want, not a script to be read aloud.

## Key capabilities

- **Flat $0.03 per generation** — No duration or quality tiers — cost of a run is the number of generations, nothing else.
- **Music, not speech** — Input is a description of the music you want, not a script to be read aloud.
- **Asynchronous output** — The result is produced asynchronously rather than returned inline.
- **OpenAI Audio Speech protocol** — Reachable on the same endpoint family as the other audio models here.

## Sources

- [MiniMax — API docs](https://platform.minimaxi.com/document)

_Content reviewed by Jerry Fan on 2026-08-09._