Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Voyage AI
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
voyage/<model-id>How Voyage AI billing works with kRouter
Voyage AI 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 apikey. 7 models are routable as voyage/<model>.
Through kRouter, Voyage AI serves embeddings, exposed on /v1/embeddings. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Voyage AI is a one-line model change in your client rather than a rewrite.
Voyage AI models & pricing
These are the model ids kRouter routes to. This provider does not publish per-token rates.
| Model | Route as |
|---|---|
| Voyage 3 Large | voyage/voyage-3-large |
| Voyage 3.5 | voyage/voyage-3.5 |
| Voyage 3.5 Lite | voyage/voyage-3.5-lite |
| Voyage Code 3 | voyage/voyage-code-3 |
| Voyage Finance 2 | voyage/voyage-finance-2 |
| Voyage Law 2 | voyage/voyage-law-2 |
| Voyage Multilingual 2 | voyage/voyage-multilingual-2 |
Voyage AI links
Voyage AI FAQ
Is Voyage AI free through kRouter?
Voyage AI is pay-per-token: you bring your own API key and are billed by Voyage AI at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Voyage AI with Claude Code or Cursor?
Connect Voyage AI 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 voyage/<model>.
Which Voyage AI models can kRouter route to?
7 models, including Voyage 3 Large, Voyage 3.5, Voyage 3.5 Lite. Every one is addressed as voyage/<model> from any client.
What happens when Voyage AI 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.