# Speech 2.8 HD (MiniMax) — API pricing and providers

> Text-to-speech. Model id `minimax/speech-2.8-hd`. Audio model by MiniMax.

- Page: https://infro.io/models/minimax/speech-2.8-hd
- Vendor: MiniMax (https://infro.io/models/minimax)
- Modality: Audio
- Endpoint through INFRO: `POST /v1/audio/speech` at https://api.infro.io/v1
- List rate: $100 per 1M characters
- Rates checked: 2026-10-05

Rates are MiniMax'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 |
| --- | --- |
| OpenRouter | `minimax/speech-2.8-hd` |
| MiniMax | `speech-2.8-hd` |

## Questions

### How much does the Speech 2.8 HD API cost?

MiniMax's published list rate for Speech 2.8 HD is $100 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 Speech 2.8 HD?

In INFRO's provider registry, Speech 2.8 HD can be served by OpenRouter and MiniMax. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Speech 2.8 HD model ID?

Request it from INFRO as "minimax/speech-2.8-hd". INFRO sends each provider its own id: OpenRouter "minimax/speech-2.8-hd", MiniMax "speech-2.8-hd".

### How do I call Speech 2.8 HD 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 "minimax/speech-2.8-hd" 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 Speech 2.8 HD usage?

No. MiniMax 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.