Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Jina 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
jina/<model-id>How Jina AI billing works with kRouter
Jina 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. 3 models are routable as jina/<model>.
Through kRouter, Jina 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 Jina AI is a one-line model change in your client rather than a rewrite.
10M free tokens on signup (non-commercial), no credit card required.
Jina AI models & pricing
These are the model ids kRouter routes to. This provider does not publish per-token rates.
| Model | Route as |
|---|---|
| Jina Embeddings v3 | jina/jina-embeddings-v3 |
| Jina Embeddings v2 Base EN | jina/jina-embeddings-v2-base-en |
| Jina Embeddings v2 Base Code | jina/jina-embeddings-v2-base-code |
Jina AI links
Jina AI FAQ
Is Jina AI free through kRouter?
Jina AI is pay-per-token: you bring your own API key and are billed by Jina AI at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Jina AI with Claude Code or Cursor?
Connect Jina 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 jina/<model>.
Which Jina AI models can kRouter route to?
3 models, including Jina Embeddings v3, Jina Embeddings v2 Base EN, Jina Embeddings v2 Base Code. Every one is addressed as jina/<model> from any client.
What happens when Jina 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.