Skip to main content
kRouter
All providers

Pay-per-token

sdwebui/

SD WebUI

SD WebUI — connect via API key.

github.com

Quick setup

  1. Open the kRouter dashboard at http://localhost:20128

  2. Go to Providers → click SD WebUI

  3. Paste your API key, click Save

  4. Test the connection

Use in your IDE

Point any OpenAI-compatible client at kRouter using your local API key.

ide configbash
# Endpoint
http://localhost:20128/v1

# API key (from Dashboard → API Keys)
sk-krouter-XXXX

# Model
sdwebui/<model-id>

How SD WebUI billing works with kRouter

SD WebUI 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 sdwebui/<model>.

Through kRouter, SD WebUI 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 SD WebUI is a one-line model change in your client rather than a rewrite.

SD WebUI models & pricing

These are the model ids kRouter routes to. This provider does not publish per-token rates.

ModelRoute as
Stable Diffusion v1.5sdwebui/stable-diffusion-v1-5
SDXL Base 1.0sdwebui/sdxl-base-1.0

SD WebUI links

SD WebUI FAQ

Is SD WebUI free through kRouter?

SD WebUI is pay-per-token: you bring your own API key and are billed by SD WebUI at their rates. kRouter adds nothing on top and is free and MIT-licensed.

How do I use SD WebUI with Claude Code or Cursor?

Connect SD WebUI 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 sdwebui/<model>.

Which SD WebUI models can kRouter route to?

2 models, including Stable Diffusion v1.5, SDXL Base 1.0. Every one is addressed as sdwebui/<model> from any client.

What happens when SD WebUI 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.