# ElevenLabs Flash v2.5 (ElevenLabs) — API pricing and providers

> Low-latency text to speech. Model id `elevenlabs/eleven-flash-v2.5`. Audio model by ElevenLabs.

- Page: https://infro.io/models/elevenlabs/eleven-flash-v2.5
- Vendor: ElevenLabs (https://infro.io/models/elevenlabs)
- Modality: Audio
- Endpoint through INFRO: `POST /v1/audio/speech` at https://api.infro.io/v1
- List rate: $40 per 1M characters
- Rates checked: 2026-10-05

Rates are ElevenLabs'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 |
| --- | --- |
| ElevenLabs | `eleven_flash_v2_5` |

## Questions

### How much does the ElevenLabs Flash v2.5 API cost?

ElevenLabs's published list rate for ElevenLabs Flash v2.5 is $40 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 ElevenLabs Flash v2.5?

In INFRO's provider registry, ElevenLabs Flash v2.5 can be served by ElevenLabs. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the ElevenLabs Flash v2.5 model ID?

Request it from INFRO as "elevenlabs/eleven-flash-v2.5". INFRO sends each provider its own id: ElevenLabs "eleven_flash_v2_5".

### How do I call ElevenLabs Flash v2.5 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 "elevenlabs/eleven-flash-v2.5" 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 ElevenLabs Flash v2.5 usage?

No. ElevenLabs 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.