Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Nebius 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
nebius/llama-4-405bHow Nebius AI billing works with kRouter
Nebius 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. 2 models are routable as nebius/<model>.
Through kRouter, Nebius AI serves chat and code completion and embeddings, exposed on /v1/embeddings. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Nebius AI is a one-line model change in your client rather than a rewrite.
Nebius AI models & pricing
Prices are USD per 1M tokens, cheapest first. kRouter bills nothing on top; this is the provider's own rate.
| Model | Route as | Input /1M | Output /1M |
|---|---|---|---|
| Qwen3 Embedding 8B | nebius/Qwen/Qwen3-Embedding-8B | $0.50 | $2.00 |
| Llama 3.3 70B Instruct | nebius/meta-llama/Llama-3.3-70B-Instruct | — | — |
Nebius AI links
Nebius AI FAQ
Is Nebius AI free through kRouter?
Nebius AI is pay-per-token: you bring your own API key and are billed by Nebius AI at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Nebius AI with Claude Code or Cursor?
Connect Nebius 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 nebius/<model>.
Which Nebius AI models can kRouter route to?
2 models, including Llama 3.3 70B Instruct, Qwen3 Embedding 8B. Every one is addressed as nebius/<model> from any client.
What happens when Nebius 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.