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