Lyria 3 Pro Preview
Google· released 30 Mar 2026
google/lyria-3-pro-preview- Input / 1M tokens
- free
- Output / 1M tokens
- free
Longest answer: 66K tokens
About
Lyria 3 Pro Preview is a Google model in the Lyria 3 family of music generation models, available through the Gemini API. Full-length songs are priced at $0.08 per song. The listed model accepts text and images, and its outputs are text and audio. Its model ID is `google/lyria-3-pro-preview`; it was released on 2026-03-30. A 1,048,576-token context window and maximum output of 65,536 tokens are listed. The entry also lists free access and vision support. The modality field is text, while the outputs include audio. For builders evaluating a music-generation option in an existing stack, the Gemini API availability, listed song price and text-and-image inputs are relevant details. The preview designation is part of the model name; no further preview behavior is specified here.
Who it is for
It may suit teams exploring music generation through the Gemini API, particularly where text or image inputs and audio output fit the workflow. The listed price is $0.08 per full-length song.
What is good
- Full-length songs cost $0.08 per song
- Available through the Gemini API
- Accepts text and image inputs
- Outputs text and audio
What to know first
- Preview model designation
- Modality is listed as text
Verdict
Lyria 3 Pro Preview offers audio output as part of Google's Lyria 3 music model family, with Gemini API availability and a per-song price. Its preview designation and listed modality details are worth noting when evaluating fit.
Details
- Lab
- Googleopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- Freeopenrouter.ai · 3 Oct 2026
- Output price
- Freeopenrouter.ai · 3 Oct 2026
- Max output
- 65,536 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, imageopenrouter.ai · 3 Oct 2026
- Open weights
- Noopenrouter.ai · 3 Oct 2026
More longest-context models
See the listListed on Inferse
- Longest-Context Models in 2026466 listed
- Newest Models in 2026466 listed
- Vision Language Models in 2026295 listed
- Google Models: Pricing per 1M Tokens and Context (2026)43 listed
- Free Models in 202622 listed
Sources
- openrouter.ai/google/lyria-3-pro-preview· checked 3 Oct 2026



