AI model · Google
Lyria 3 Clip Preview
Model ID: google/lyria-3-clip-preview
- Input
- Free per 1M tokens
- Output
- Free per 1M tokens
- Context
- 1M tokens at once
- Max output
- 66K tokens per reply
- Released
- 30 Mar 2026 Google
What it can do
- NoReasoning
- NoTool calling
- YesImage input
- NoOpen weights
- YesFree to use
Takes text, image; gives text, audio.
How its listing describes it
30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API.
Sources
- Google: Lyria 3 Clip Preview on OpenRouter — read 2 Oct 2026