Use DaoXE in Open WebUI

Open WebUI speaks the OpenAI API, so DaoXE plugs in as a Connection: set the base URL and key, and it lists your models automatically. One connection serves every user on the instance. See the cheapest APIs guide for using a cheap model for background tasks and a frontier one for chat.

Why route Open WebUI through DaoXE#

• Self-hosted, multi-user. One DaoXE connection powers chat for your whole team.
• One key, many models. GPT, Claude, Gemini and DeepSeek appear in the model picker from a single connection.
• Cheap task model. Point title/tag generation at a cheap DaoXE model and keep a frontier one for real chat.

Set it up in Open WebUI#

1. Open Connections. Admin Panel → Settings → Connections (or your profile's Connections for a personal setup).
2. Add an OpenAI connection. Set the API Base URL to https://daoxe.com/v1 and paste your DaoXE key, then save.
3. Confirm models populate. Open the model selector — DaoXE model IDs from GET /v1/models should appear. If the list is empty, the connection failed.
4. Set a task model (optional). In Admin settings, point title/tag/autocomplete tasks at a cheap DaoXE model to cut background cost.

Verify you actually get the model#

Prove the endpoint works before blaming the client — if this fails, no setting will fix it:

export DAOXE_API_KEY="your_api_key"

# List the exact model IDs your account can call
curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/models \
  -H "Authorization: Bearer ${DAOXE_API_KEY}"

Prove the endpoint independently of Open WebUI first, then diff a fixed prompt against the official API at temperature 0:

curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/chat/completions \
  -H "Authorization: Bearer ${DAOXE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_EXACT_MODEL_ID",
    "max_tokens": 64,
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Frequently asked questions#