MiniMax Music is a lyrics-driven audio generation model optimized for producing background tracks and bulk content at a low cost. Reach for it when you need to generate up to five minutes of audio per call without prioritizing generation speed.
Modalities
Text → Audio
Price
$0.045 / song
Speed
slow
Performance
Live production data from real requests on Kyma — not synthetic benchmarks.
Rank
#72
of 87 active models
Tokens served
56
all-time
Pricing
Flat per generated track regardless of duration.
$0.045 / songWhen to use MiniMax Music
Where this model earns its cost — and where it doesn't.
Part of the Music-2.0 family, this model converts text prompts up to 2000 tokens into audio tracks up to five minutes long. It operates in the strong quality tier and is designed specifically for lyrics-driven composition.
Kyma serves MiniMax Music through an OpenAI-compatible endpoint with automatic request failover. Prompt caching is enabled, billing repeated prompt prefixes at 10% of the standard input rate. Every response includes exact cost in usage.cost and reports the executing variant in the X-Kyma-Model header.
The model is classified as slow and does not support structured outputs, vision, or real-time streaming. It is billed per song rather than by token, making it suitable for batch workflows but not interactive applications.
Background Music Generation
Produce royalty-free audio tracks to accompany video content or podcasts.
Social Media Shorts Audio
Generate short, thematic soundtracks optimized for vertical video platforms.
Bulk Theme Generation
Create multiple musical variations at scale for prototyping or asset libraries.
Not ideal for: Do not use this model for real-time audio synthesis, interactive voice applications, or workflows requiring sub-second generation latency.
Quick start
Up and running in under two minutes.
- 1
Create an API key
Sign up and grab a key from the dashboard — $0.50 free credit, no card required.
Get API key → - 2
Make your first request
Drop in your key and send a chat completion — fully OpenAI-compatible.
curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax-music", "messages": [ {"role": "user", "content": "Explain prompt caching in one paragraph."} ] }' - 3
Stream responses
Add
"stream": trueto receive tokens as they arrive.curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax-music", "stream": true, "messages": [{"role": "user", "content": "Hello!"}] }'
FAQ
Common questions about this model.
How much does MiniMax Music cost?
How do I use MiniMax Music?
How does Kyma handle billing for this model?
Does Kyma route requests automatically if a provider fails?
Can I use this model for real-time voice applications?
More models by MiniMax
See all 13 →| Model | Context | Input | Output |
|---|---|---|---|
MiniMax M3 | 1M | $0.3852 | $1.54 |
MiniMax Music Pro | — | $0.21 / song | |
MiniMax M2.7 | 205K | $0.405 | $1.62 |
MiniMax M2.5 | 197K | $0.3826 | $1.346 |
MiniMax Voice Design | — | $4.20 / call | |
Hailuo 02 (1080p) | — | $0.78 / video | |
Hailuo 02 (768p) | — | $0.42 / video | |
Hailuo 02 (512p) | — | $0.14 / video | |
