Skip to content

MiniMax Music 2.6

Compose music from a style prompt and lyrics. Generate a complete song or an instrumental track, then retrieve the finished audio.

Modalities
Text
Audio
Price
$0.15per generation
Output formats
MP3 · WAV · PCM
Released
Apr 13, 2026

Overview

Mode
Output format
Sample rate
Music sample

Corazón de Fuego

MiniMax Music 2.6 launch sample

0:002:41

Published by MiniMax with the Music 2.6 launch. Not generated from your prompt or settings

Compose a full arrangement from a brief

MiniMax Music 2.6 generates complete songs or instrumentals from a style prompt and optional lyrics. MiniMax describes it as a model for fully arranged tracks, with control over tempo, key, structure, vocal performance and emotional progression.

Write the brief like a producer

The prompt (10–2,000 characters) carries style, mood and scenario. Naming instruments, tempo and how the energy should build gives the model more to work with than a genre label. Lyrics (10–3,000 characters) can use [Verse], [Chorus] and [Bridge] tags to shape the song. Without lyrics, turn on lyrics_optimizer to write them from the prompt, or is_instrumental for a track without vocals.

Know where it stands

In Artificial Analysis blind listening tests, Music 2.6 sits mid-table: Elo 998 on the vocal board and 1001 on the instrumental board, level with Eleven Music and MiniMax Music 2.5+. Suno v6 leads both boards by more than 140 points. Use Music 2.6 to sketch and iterate on ideas, and audition several takes before choosing one.

Plan for asynchronous delivery

Generation runs as a task. Submit the request, keep the returned ID and poll until the status is completed, then download audio_file.url. In audio_setting, choose MP3, WAV or PCM, a sample rate up to 44.1 kHz and a bitrate up to 256 kbps.

Benchmarks by Artificial Analysis

Blind listening tests place MiniMax Music 2.6 mid-table on both Artificial Analysis music boards.

Vocal music#11 / 13998Elo · AA-Music-Vocal v1.1Instrumental#12 / 191001Elo · AA-Music-Instrumental v1.1
Gap to the leader−146Elo vs Suno v6 on vocals (−147 instrumental)
Samples5,4673,206 vocal + 2,261 instrumental

Vocal music

Elo · AA-Music-Vocal v1.1

Instrumental

Elo · AA-Music-Instrumental v1.1

Same five models on both boards. Music 2.6 is within the margin of error of Eleven Music and MiniMax Music 2.5+. Lyria 2, also on AI/ML API, scores 926 on the instrumental board (#18 of 19). Snapshot 2026-10-30.

Pricing

MiniMax Music 2.6 pricing in US dollars
UsagePriceUnit
Music generation$0.15generation

Compare music prices

AI/ML API rates for music models billed per generation.

ModelPer generation
MiniMax Music 2.6Songs or instrumentals$0.15
Lyria 2Instrumental music$0.10

Eleven Music is billed per second of audio, so it is not compared here.

Estimate by number of tracks

Each request is one generation. Budget for several takes per finished track.

GenerationsCost on AI/ML API
1 track$0.15
10 tracks$1.50
100 tracks$15.00
1,000 tracks$150.00

Build with your agent

Give your agent the model details, code and documentation.

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v2/generate/audio' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/music-2.6",
  "prompt": "Warm, unhurried instrumental jazz with brushed drums and mellow piano.",
  "is_instrumental": true,
  "audio_setting": {
    "format": "mp3"
  }
}'
Retrieve your result

Save the returned id, then poll this endpoint while the status is queued or generating. A completed task includes audio_file.url.

GET /v2/generate/audio?generation_id=…

Related articles

All posts

Frequently asked questions

Is Music 2.6 a speech model?

No. It composes music, with or without sung vocals. For spoken narration or voice agents, use a text-to-speech model such as Eleven v4 Turbo.

How is music billed?

AI/ML API charges $0.15 per generation, whatever the length of the prompt or lyrics. 100 generations cost $15.

Can I supply my own lyrics?

Yes. Send 10–3,000 characters in lyrics, using tags such as [Verse], [Chorus] and [Bridge] to guide the structure. Or set lyrics_optimizer to true and the model writes lyrics from your prompt.

Can I generate an instrumental?

Yes. Set is_instrumental to true and describe the music in the prompt. The default is a track with vocals.

How do I retrieve the track?

POST /v2/generate/audio returns an ID. Poll GET /v2/generate/audio with generation_id while the status is queued or generating. When it is completed, download the file from audio_file.url.

Which audio formats are supported?

MP3, WAV and PCM, set in audio_setting.format. You can also set a sample rate of 16, 24, 32 or 44.1 kHz and a bitrate from 32 to 256 kbps.

How does Music 2.6 compare with other music models?

On the Artificial Analysis Music Arena (October 30, 2026), it scores Elo 998 on the vocal board (#11 of 13) and 1001 on the instrumental board (#12 of 19). Suno v6 leads both.

Start building with MiniMax Music 2.6

API

API key, code and agent prompt for MiniMax Music 2.6.

Build with your agent

Give your agent the model details, code and documentation.

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v2/generate/audio' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/music-2.6",
  "prompt": "Warm, unhurried instrumental jazz with brushed drums and mellow piano.",
  "is_instrumental": true,
  "audio_setting": {
    "format": "mp3"
  }
}'
Retrieve your result

Save the returned id, then poll this endpoint while the status is queued or generating. A completed task includes audio_file.url.

GET /v2/generate/audio?generation_id=…