model field.
The exact set your key can call, and each model’s supported options, is returned by
GET /v1/models.
Audio is priced per track or per minute of output depending on the model; for per-model rates see
deepshi.ai.
Lyria 3 Pro
lyria3-pro · Prompt 5KThe full-length Lyria tier: a complete multi-minute vocal song from a single prompt. Vocals
MiniMax Music 2.5
minimax-music-v2.5 · Prompt 2KVocal songs or instrumentals, with optional lyrics. Vocals InstrumentalMiniMax Music 2.6
minimax-music-v2.6 · Prompt 2KThe latest MiniMax tier, with the same controls as 2.5. Vocals InstrumentalLyria 3
lyria3 · Prompt 2KGoogle’s Lyria 3 generates a multilingual vocal song from a single prompt, ~30 seconds. Vocals
ElevenLabs Music
elevenlabs-music · Prompt 2KA song from a style prompt, with controllable length and optional vocals. Vocals Instrumental Duration
Stable Audio 2.5
stable-audio-25 · Prompt 2KStability’s instrumental music and sound effects, with controllable length. Instrumental Duration
CassetteAI Music Generator
cassetteai-music · Prompt 2KCassetteAI’s instrumental music, from 10 to 180 seconds. Instrumental DurationMiniMax Music 2.0
minimax-music-v2 · Prompt 300Studio-quality vocal songs from a style prompt and required lyrics. Vocals