Connect → Open WebUI

Use AxForge with Open WebUI

Open WebUI is a chat app you host yourself. Add AxForge as one connection and our models appear in its model menu.

Set it up

1. Start Open WebUI

   docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main

   Open localhost:3000. The first visit asks for a name, an email and a password: that makes the admin account, on your machine only.

   

2. Open Connections

   Click your name at the bottom left, then Admin Panel → Settings → Connections. Press the + beside Manage OpenAI API Connections.

   

3. Add AxForge

   URL https://api.axforge.ai/v1, your key in the field beside Bearer. Press the round arrows to test it: Server connection verified means the key works. Then Save, and Save again at the bottom of the page.

   

4. Pick a model

   Start a new chat and open the model menu at the top. Type a name to find it: qwen3.8-27b, glm-5.3-flash or mimo-v2.6-flash. The menu also lists short aliases (such as chat, which is Qwen3.8 27B) and our image, speech and embedding models; those last are not chat models.

   

5. Ask something

   The answer streams in, word by word.

   

The settings

Which model for what: qwen3.8-27b is the everyday default and reads images, glm-5.3-flash thinks before it answers, mimo-v2.6-flash is the fastest.

Or set it when you start it

Open WebUI can take the connection on its first start instead:

docker run -d -p 3000:8080 \
    -e OPENAI_API_BASE_URL=https://api.axforge.ai/v1 \
    -e OPENAI_API_KEY="$AXFORGE_API_KEY" \
    -v open-webui:/app/backend/data \
    --name open-webui ghcr.io/open-webui/open-webui:main

docker run -d -p 3000:8080 `
    -e OPENAI_API_BASE_URL=https://api.axforge.ai/v1 `
    -e OPENAI_API_KEY="$env:AXFORGE_API_KEY" `
    -v open-webui:/app/backend/data `
    --name open-webui ghcr.io/open-webui/open-webui:main

Read once. Open WebUI saves these on its first start. On a later start with the same volume they are ignored: change the connection under Admin Panel → Settings → Connections.

Check that it works

The verify button says Server connection verified, our models are in the model menu, and a question gets an answer. The call also shows in the console under API Keys → Recent calls within a minute.

When it does not work

Not sure which it is? The connection doctor makes seven small checks on your key and names the fix: irm https://dev.axforge.ai/assets/axforge-doctor.ps1 | iex in PowerShell, curl -fsSL https://dev.axforge.ai/assets/axforge-doctor.sh | bash on macOS and Linux.

Test a call says in one click whether a problem is your key, your balance or us.