# Kokoro 82M (Kokoro) — API pricing and providers

> Lightweight text-to-speech. Model id `hexgrad/kokoro-82m`. Audio model by Kokoro.

- Page: https://infro.io/models/hexgrad/kokoro-82m
- Vendor: Kokoro (https://infro.io/models/hexgrad)
- Modality: Audio
- Endpoint through INFRO: `POST /v1/audio/speech` at https://api.infro.io/v1
- List rate: $4.00 per 1M characters
- Rates checked: 2026-10-05

Rates are Kokoro'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 | `hexgrad/Kokoro-82M` |
| OpenRouter | `hexgrad/kokoro-82m` |

## Questions

### How much does the Kokoro 82M API cost?

Kokoro's published list rate for Kokoro 82M is $4.00 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 Kokoro 82M?

In INFRO's provider registry, Kokoro 82M 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 Kokoro 82M model ID?

Request it from INFRO as "hexgrad/kokoro-82m". INFRO sends each provider its own id: Together AI "hexgrad/Kokoro-82M", OpenRouter "hexgrad/kokoro-82m".

### How do I call Kokoro 82M 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 "hexgrad/kokoro-82m" 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 Kokoro 82M usage?

No. Kokoro 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.