# MAI-Voice 2.1 Flash (Microsoft) — API pricing and providers

> Low-latency text-to-speech. Model id `microsoft/mai-voice-2.1-flash`. Audio model by Microsoft.

- Page: https://infro.io/models/microsoft/mai-voice-2.1-flash
- Vendor: Microsoft (https://infro.io/models/microsoft)
- 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 Microsoft'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 | `microsoft/mai-voice-2.1-flash` |

## Questions

### How much does the MAI-Voice 2.1 Flash API cost?

Microsoft's published list rate for MAI-Voice 2.1 Flash 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 MAI-Voice 2.1 Flash?

In INFRO's provider registry, MAI-Voice 2.1 Flash can be served by OpenRouter. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the MAI-Voice 2.1 Flash model ID?

Request it from INFRO as "microsoft/mai-voice-2.1-flash". INFRO sends each provider its own id: OpenRouter "microsoft/mai-voice-2.1-flash".

### How do I call MAI-Voice 2.1 Flash 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 "microsoft/mai-voice-2.1-flash" 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 MAI-Voice 2.1 Flash usage?

No. Microsoft 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.