All guides / Chat clients

Use XHuoAPI in Open WebUI

Open WebUI can hold several OpenAI-compatible connections at once. Add one pointing at XHuoAPI and every available model shows up in the model selector.

Before you start

Verify first

Before touching the tool, confirm the key and model work with curl. This rules out half of the 'I configured it and nothing happens' cases.

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v3.2","messages":[{"role":"user","content":"ping"}]}'

Steps

1

Sign in as an admin, go to Admin Settings → Connections, find the OpenAI row and click the wrench icon (Manage).

2

Click Add New Connection. Set Connection Type to External and fill in URL and API Key:

URL:      https://api.xhuoapi.ai/v1
API Key:  sk-...
3

Leave Model IDs empty; Open WebUI fetches every available model via /models. Fill it only if you want to expose a subset — the field acts as an allowlist.

4

With Docker you can use environment variables instead; the result is the same:

OPENAI_API_BASE_URL=https://api.xhuoapi.ai/v1
OPENAI_API_KEY=sk-...
ENABLE_OPENAI_API=true

Notes

If another connection exposes the same model names (two providers both offering qwen3.8-max, say), set a Prefix ID on the connection; models then appear as prefix/model-name.
Qwen models and image/video models are only available in the Standard and Official tiers. A token created in the Saver or Spot tier will get a 'model not available' error for them.

Commonly used models

These are common choices for this kind of tool; click a model to see its price in each tier. The full list is on the pricing page.

Steps follow the tool's current official documentation; the UI may change after updates. Tell us if something no longer matches.