MiniMax Music 2.6
minimax/music/2.6MiniMax Music 2.6 by MiniMax composes a full song with vocals and accompaniment from a style prompt and lyrics, or an instrumental track without lyrics.
- Base price
- $0.15USD / run
- Execution
- async
- Model type
- audio
- Input fields
- 7
Try the model
Playground
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "lyrics": "[verse]\nMorning light on the water\n[chorus]\nWe keep on running", "prompt": "Upbeat indie pop, bright guitars, female vocal" }
Model card
Specifications
Pricing
- Base price
- $0.15 / run
Context & modalities
- Input
- Schema-defined
- Output
- audio
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- MiniMax
- Model ID
- minimax/music/2.6
- Execution
- async
- Base URL
- https://api.sandbase.ai
- API
- Unified Run API
- Endpoint
- /v1/run
API README
MiniMax Music 2.6
MiniMax Music 2.6 generates a song with vocals from a style prompt and lyrics, or an instrumental track.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Style: genre, mood, instruments. |
lyrics | string | `[verse] | |
| Streetlights flicker, the night breeze sighs | |||
| Shadows stretch as I walk alone | |||
| An old coat wraps my silent sorrow | |||
| Wandering, longing, where should I go | |||
| [chorus] | |||
| Pushing the wooden door, the aroma spreads | |||
| In a familiar corner, a stranger gazes` | Lyrics with [verse] / [chorus] markers. | ||
is_instrumental | boolean | false | Generate without vocals. |
lyrics_optimizer | boolean | false | Let MiniMax polish the lyrics. |
sample_rate | 16000 / 24000 / 32000 / 44100 | — | Sample rate of generated audio. |
bitrate | 32000 / 64000 / 128000 / 256000 | — | Bitrate of generated audio. |
format | mp3 / wav / pcm | — | Format of generated audio. |
Billing
$0.15 per song.
| Request | Price |
|---|---|
| One song | $0.15 |
Failed runs are not charged.
Prompting
- Put style in
promptand words inlyrics.
Also on SandBase
Related: minimax/music/3 (newer, up to 5 minutes).
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "minimax/music/2.6",
"lyrics": "[verse]\nStreetlights flicker, the night breeze sighs\nShadows stretch as I walk alone\nAn old coat wraps my silent sorrow\nWandering, longing, where should I go\n[chorus]\nPushing the wooden door, the aroma spreads\nIn a familiar corner, a stranger gazes",
"prompt": "Indie folk, melancholic, introspective, longing, solitary walk, coffee shop",
"is_instrumental": false,
"lyrics_optimizer": false
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Input Schema
7 parameters · 1 required · 6 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | A description of the music style, mood, genre, and scenario. · Min length: 1 · Max length: 2000 · Default: "Indie folk, melancholic, introspective, longing, solitary walk, coffee shop" |
format | string | Optional | Format of generated audio. · Options: mp3, wav, pcm mp3wavpcm |
lyrics | string | Optional | Lyrics of the song. Use \n to separate lines. Supports structure tags: [Intro], [Verse], [Pre Chorus], [Chorus], [Bridge], [Outro], [Interlude], [Hook], [Break], [Solo], [Inst]. · Max length: 3500 · Default: "[verse]\nStreetlights flicker, the night breeze sighs\nShadows stretch as I walk alone\nAn old coat wraps my silent sorrow\nWandering, longing, where should I go\n[chorus]\nPushing the wooden door, the aroma spreads\nIn a familiar corner, a stranger gazes" |
bitrate | integer | Optional | Bitrate of generated audio. · Options: 32000, 64000, 128000, 256000 3200064000128000256000 |
sample_rate | integer | Optional | Sample rate of generated audio. · Options: 16000, 24000, 32000, 44100 16000240003200044100 |
is_instrumental | boolean | Optional | When true, generates vocal-free instrumental music. · Default: false |
lyrics_optimizer | boolean | Optional | When true and lyrics is empty, auto-generates lyrics from the prompt. · Default: false |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model runs asynchronously. Submit a request, then poll for the result.
- Submit: POST to /v1/run and read the returned
id. - Poll: GET /v1/run/{id} until status is
completed,failedortimeout. - Retrieve: read
outputsfrom the completed response.
Choose your model
Compare models
| Model | Type | Default price | Released |
|---|---|---|---|
MiniMax Music 2.6This model MiniMax | Audio | $0.15 / run | Apr 11, 2026 |
MiniMax | Audio | $0.12 / run | Oct 5, 2026 |
MiniMax | Audio | $0.10 / run | Feb 4, 2026 |
MiniMax | Audio | $0.06 / run | Feb 4, 2026 |
MiniMax | Audio | $0.06 / run | Oct 29, 2025 |
MiniMax | Audio | $0.10 / run | Oct 29, 2025 |
Questions
FAQ
How do I call MiniMax Music 2.6 through SandBase?
Create a SandBase API key, then send requests with the model ID "minimax/music/2.6" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.
Do I need a separate MiniMax account?
No. One SandBase API key and balance gives you access to MiniMax Music 2.6 and the other models in the catalog; you do not need to sign up with MiniMax separately.
