Skip to content

Open WebUI with Keln

Chat with Keln models in Open WebUI. Add Keln as a connection and its models appear in the model selector.

What you need to start

  • Open WebUI running, and an admin account on it.
  • A Keln API key. Sign up at app.keln.ai, then open Keys → Create key.

Connect Open WebUI to Keln

1. Open the connections page

In Open WebUI, open Settings → Admin → Connections and find the Manage OpenAI API Connections list.

2. Add the Keln connection

Click + next to Manage OpenAI API Connections and fill in:

Field Value
URL https://api.keln.ai/v1
API Key sk-keln-… your key

Enter the URL without a slash at the end.

3. Choose the models to show

Open WebUI loads the model list from Keln. It also includes non-chat models: decision, speech, transcription, embedding and rerank models. To show only chat models, click Advanced. Under Model IDs, type one model ID and click +. Repeat for each model you want, for example:

zai-org/glm-5.3
zai-org/glm-5.3-flash
moonshotai/kimi-k3
qwen/qwen3.8-2.4t-a95b
deepseek-ai/deepseek-v4.1-flash

Click Save.

The Add Connection dialog with the URL https://api.keln.ai/v1, a masked key and 2 model IDs under Advanced

Open WebUI's connection check passes with any key. If your first message returns a 401 error, check the key.

4. Pick a model and chat

Start a new chat and open the model selector in the message box. Pick a Keln model and send a message.

The model selector in the Open WebUI message box, listing zai-org/glm-5.3 and zai-org/glm-5.3-flash

Open WebUI sends no reasoning setting, so Keln runs the model at its deepest thinking level. To lower it, click the controls icon in the message box, open Advanced Params, click Default next to Reasoning Effort and enter low or medium. Avoid none on GLM 5.3, GLM 5.3 Flash and Qwen. Those models always think, and Keln returns a 400 error (Reasoning control).

Advanced Params in the chat controls with Reasoning Effort switched to Custom

Open WebUI enables Vision for every model. For a text-only model such as zai-org/glm-5.3, open Settings → Admin → Models, click the pencil icon, turn Vision off under Capabilities and click Save & Update.

New models are Private. Only admins can see them. To share one, open the model, click Access and choose Public.

Before your first message, add credit under Billing → Add credit. Keln returns a 402 error if your balance is empty.

Models

Open WebUI works with all Keln chat models. See Models & pricing for the full list, with each model's context window, image support and pricing.

Usage

Your Keln Usage page shows your spend, tokens, latency and error rate. Keln stores metadata only (ZDR).

The Keln Usage page with sample data: spend, requests, tokens, time to first token, error rate and a spend-by-day chart

Turn Keln off

Each connection has a toggle on the Connections page. Turn the Keln connection off to hide its models, and on again to bring them back. Open WebUI keeps the URL and key.

Where to go next

Try Keln

Create a Keln account and API key to run open models in Open WebUI.

Get an API key Models & pricing ↗