Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Runway ML
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
runway/<model-id>How Runway ML billing works with kRouter
Runway ML 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. 4 models are routable as runway/<model>.
Through kRouter, Runway ML serves image generation, exposed on /v1/images/generations and video generation, exposed on /v1/videos. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Runway ML is a one-line model change in your client rather than a rewrite.
Runway ML models & pricing
These are the model ids kRouter routes to. This provider does not publish per-token rates.
| Model | Route as |
|---|---|
| Gen-4 Image | runway/gen4_image |
| Gen-4 Image Turbo | runway/gen4_image_turbo |
| Gen-4 Turbo | runway/gen4_turbo |
| Gen-3 Alpha Turbo | runway/gen3a_turbo |
Runway ML links
Runway ML FAQ
Is Runway ML free through kRouter?
Runway ML is pay-per-token: you bring your own API key and are billed by Runway ML at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Runway ML with Claude Code or Cursor?
Connect Runway ML 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 runway/<model>.
Which Runway ML models can kRouter route to?
4 models, including Gen-4 Image, Gen-4 Image Turbo, Gen-4 Turbo. Every one is addressed as runway/<model> from any client.
What happens when Runway ML 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.