MiniMax Music 3.0
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.
- Input
- text
- Output
- audio
- License
- MiniMax-Music3 Community License (commercial use allowed with 'MiniMax-Music3' shown in the UI; separate authorization above US$20M annual revenue)
- Pricing
- per song: $0.15 (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
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| MiniMax API (existing paying users only since 2026-08-20) | music-3.0 | — | docs |
| Hugging Face | — | huggingface.co/MiniMaxAI/MiniMax-Music3 | — |
| GitHub | — | github.com/MiniMax-AI/MiniMax-Music3 | — |
| Web app (MiniMax Audio) | — | www.minimax.io/audio | — |
Notable capabilities (3)
- 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
- 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
- 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
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.
Sources: blog, HF model card, license, models intro, release notes, pricing.
Timeline entry
- MiniMax open-sources Music 3.0, a five-minute full-song generator ★★★
MiniMax released the weights of MiniMax Music 3.0 (8B Global LLM + 0.6B Local LLM + flow-matching renderer), which writes, arranges and sings complete songs of up to about five minutes in one pass, under a community license allowing commercial use; a week later it closed its paid music API to new…
Other MiniMax models
MiniMax H3 · MiniMax-M3 · MiniMax-M2.7 · MiniMax Speech 2.8 (HD / Turbo)