# Orpheus 3B (Canopy Labs) — API pricing and providers

> Text-to-speech. Model id `canopylabs/orpheus-3b`. Audio model by Canopy Labs.

- Page: https://infro.io/models/canopylabs/orpheus-3b
- Vendor: Canopy Labs (https://infro.io/models/canopylabs)
- Modality: Audio
- Endpoint through INFRO: `POST /v1/audio/speech` at https://api.infro.io/v1
- List rate: $15 per 1M characters
- Rates checked: 2026-10-05

Rates are Canopy Labs'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 |
| --- | --- |
| Together AI | `canopylabs/orpheus-3b-0.1-ft` |
| OpenRouter | `canopylabs/orpheus-3b-0.1-ft` |

## Questions

### How much does the Orpheus 3B API cost?

Canopy Labs's published list rate for Orpheus 3B is $15 per 1M characters (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 Orpheus 3B?

In INFRO's provider registry, Orpheus 3B can be served by Together AI and OpenRouter. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Orpheus 3B model ID?

Request it from INFRO as "canopylabs/orpheus-3b". INFRO sends each provider its own id: Together AI "canopylabs/orpheus-3b-0.1-ft", OpenRouter "canopylabs/orpheus-3b-0.1-ft".

### How do I call Orpheus 3B 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 "canopylabs/orpheus-3b" 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 Orpheus 3B usage?

No. Canopy Labs 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.