Post-Cutoff
Search For AI agents

MiniMaxMiniMax Music familyCurrentMusic generationReleased 16 Jul 2026

MiniMax Music 3.0

MiniMax’s flagship music model, now the strongest-known open-weights song generator from a major lab. Run locally from Hugging Face (MiniMaxAI/MiniMax-Music3) or use the MiniMax Audio web app.

Model idmusic-3.0

Price$0.15 per song

Checked29 September 2026

Where it stands

4newer music generation models since its release

All music generation models

Weights
Weights are public. Licence: MiniMax-Music3 Community License. See the licence for commercial terms.

How to call it

4 ways to use MiniMax Music 3.0, with the model id each provider expects.

Providers, model ids, endpoints and docs for MiniMax Music 3.0
ProviderModel idEndpointDocs
MiniMax API (existing paying users only since 2026-08-20) music-3.0 platform.minimax.io
Hugging Face huggingface.co
GitHub github.com
Web app (MiniMax Audio) minimax.io

Pricing

Prices for MiniMax Music 3.0
Per song$0.15

As published: “USD per generation of up to 5 minutes (music-3.0 and music-2.6 API). Paid music APIs closed to NEW users from 2026-08-20; existing paying users keep access”.

Source: platform.minimax.io, checked 29 September 2026.

Specs

Input
Text
Output
Audio
Context window
Not published
Max output
Not published
Open weights
Yes
Licence
MiniMax-Music3 Community License (commercial use allowed with 'MiniMax-Music3' shown in the UI; separate authorization above US$20M annual revenue)
Released
16 July 2026
Status
Current
Type
Music generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Open-weights full songs up to ~5 minutes in one pass

    Composes, arranges, performs and produces a complete song (vocals + arrangement) up to about five minutes from lyrics with section tags and a structured caption; 32 kHz 16-bit stereo WAV.

    Source: minimax.io

  • Hierarchical Global/Local LLM with continuous hidden-state synthesis

    8B Global LLM (initialized from Qwen3.5-8B) for long-range structure + 0.6B Local LLM for frame-level acoustics, rendered by a 2.4B flow-matching module and 123M Flow-VAE instead of discrete token decoding.

    Source: minimax.io

  • Consumer-GPU inference

    24 GB+ VRAM recommended; runs on 8 GB with CPU offloading; diffusers modular pipeline and ComfyUI support (Comfy-Org/MiniMax-Music-3).

    Source: huggingface.co

Notes

music-3.0 shipped on the MiniMax API on 2026-07-16 (release notes); open weights published 2026-08-13. Earlier API models: music-2.6 (Apr 2026, covers), music-cover, music-2.5 (Jan 2026), music-2.0 (legacy). On 2026-08-20 MiniMax stopped offering the paid Music and Lyrics Generation APIs to new users and points them to MiniMax Audio or the open model. Demonstrated with English and Mandarin lyrics; no third-party benchmark vs Suno found.

Sources: blog, HF model card, license, models intro, release notes, pricing.