Use Open WebUI with WebikAI
Open WebUI is the self-hosted chat portal agencies hand to clients. It takes any OpenAI-compatible connection, so a deployment per client — each on that client's labeled WebikAI key — gives every client a branded portal whose usage lands separately in your rebill report.
Setup
- Create an account, confirm your email, complete the four-question
onboarding, and copy your
wk_live_…key (shown once). - Add a supported provider credential for BYOK, fund the managed wallet, or do both for hybrid.
- Point the OpenAI connection at the gateway:
Open WebUI → Admin Panel → Settings → Connections → OpenAI API
API Base URL: https://gateway.webik.ai/v1
API Key: wk_live_...
# or as environment variables at deploy time:
OPENAI_API_BASE_URL=https://gateway.webik.ai/v1
OPENAI_API_KEY=wk_live_...The model list fills from our /v1/models endpoint; restrict which models users see in
Open WebUI's own model settings.
Models to start with
| Alias | Routes to |
|---|---|
| auto/chat | Balanced general-purpose chat |
| auto/cheap | Aggressively minimize cost |
| auto/vision | Multimodal — image or document input |
| auto/code | WebikAI lane ranked by coding evidence under your rules |
| z-ai/glm-5.2 | Pin an exact model (OpenRouter-style slug) |
Honest limit
A connection's key is shared by every user of that Open WebUI instance — WebikAI separates usage per key, not per portal user. For per-client separation, run one instance (or one connection) per client on that client's labeled key.
Route receipts and spend controls
Every successful routed response carries the five x-webik-* receipt headers, and per-key or client spend caps can stop a request before it is forwarded. Label the key
by client to separate usage in reports.
Full reference: docs · live scores: benchmarks · start free