Skip to main content
kRouter
All providers

Pay-per-token

local-device/

Local Device

Local Device — connect via API key.

Quick setup

  1. Open the kRouter dashboard at http://localhost:20128

  2. Go to Providers → click Local Device

  3. Paste your API key, click Save

  4. Test the connection

Use in your IDE

Point any OpenAI-compatible client at kRouter using your local API key.

ide configbash
# Endpoint
http://localhost:20128/v1

# API key (from Dashboard → API Keys)
sk-krouter-XXXX

# Model
local-device/<model-id>

How Local Device billing works with kRouter

Local Device is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via free. 1 model are routable as local-device/<model>.

Through kRouter, Local Device serves text-to-speech, exposed on /v1/audio/speech. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Local Device is a one-line model change in your client rather than a rewrite.

Local Device models & pricing

These are the model ids kRouter routes to. This provider does not publish per-token rates.

ModelRoute as
System Default Voicelocal-device/default

Local Device FAQ

Is Local Device free through kRouter?

Local Device is pay-per-token: you bring your own API key and are billed by Local Device at their rates. kRouter adds nothing on top and is free and MIT-licensed.

How do I use Local Device with Claude Code or Cursor?

Connect Local Device in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as local-device/<model>.

Which Local Device models can kRouter route to?

1 model, including System Default Voice. Every one is addressed as local-device/<model> from any client.

What happens when Local Device is rate limited?

kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.