# Lyria 2 (Google) — API pricing and providers

> Instrumental music clips. Model id `google/lyria-2`. Audio model by Google.

- Page: https://infro.io/models/google/lyria-2
- Vendor: Google (https://infro.io/models/google)
- Modality: Audio
- Endpoint through INFRO: `POST /v1/audio/speech` at https://api.infro.io/v1
- List rate: $0.0020 per second of video
- Rates checked: 2026-10-05

Rates are Google's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| Google Vertex AI | `lyria-002` |
| fal.ai | `fal-ai/lyria2` |
| Replicate | `google/lyria-2` |

## Questions

### How much does the Lyria 2 API cost?

Google's published list rate for Lyria 2 is $0.0020 per second of video (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve Lyria 2?

In INFRO's provider registry, Lyria 2 can be served by Google Vertex AI, fal.ai and Replicate. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Lyria 2 model ID?

Request it from INFRO as "google/lyria-2". INFRO sends each provider its own id: Google Vertex AI "lyria-002", fal.ai "fal-ai/lyria2", Replicate "google/lyria-2".

### How do I call Lyria 2 through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "google/lyria-2" to POST /v1/audio/speech. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up Lyria 2 usage?

No. Google or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.